var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/SchulzLab/MakeTitlesGreatAgain/master/Publications.bib&commas=true&showsearch=1&fullnames=1&authorFirst=1&jsonp=1&theme=side&hidemenu=true&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/SchulzLab/MakeTitlesGreatAgain/master/Publications.bib&commas=true&showsearch=1&fullnames=1&authorFirst=1&jsonp=1&theme=side&hidemenu=true\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https://raw.githubusercontent.com/SchulzLab/MakeTitlesGreatAgain/master/Publications.bib&commas=true&showsearch=1&fullnames=1&authorFirst=1&jsonp=1&theme=side&hidemenu=true\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
  2. \n
  3. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
  4. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2023\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n Markus Hoffmann, Nico Trummer, Leon Schwartz, Jakub Jankowski, Hye Kyung Lee, Lina-Liv Willruth, Olga Lazareva, Kevin Yuan, Nina Baumgarten, Florian Schmidt, Jan Baumbach, Marcel H Schulz, David B Blumenthal, Lothar Hennighausen, & Markus List.\n\n\n \n \n \n \n \n TF-Prioritizer: a Java pipeline to prioritize condition-specific transcription factors.\n \n \n \n \n\n\n \n\n\n\n GigaScience, 12: giad026. 05 2023.\n giad026\n\n\n\n
\n\n\n\n \n \n \"TF-Prioritizer:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{Hoffmann2023,\n    author = {Hoffmann, Markus and Trummer, Nico and Schwartz, Leon and Jankowski, Jakub and Lee, Hye Kyung and Willruth, Lina-Liv and Lazareva, Olga and Yuan, Kevin and Baumgarten, Nina and Schmidt, Florian and Baumbach, Jan and Schulz, Marcel H and Blumenthal, David B and Hennighausen, Lothar and List, Markus},\n    title = "{TF-Prioritizer: a Java pipeline to prioritize condition-specific transcription factors}",\n    journal = {GigaScience},\n    volume = {12},\n    year = {2023},\n    month = {05},\n    issn = {2047-217X},\n    pages={giad026},\n    doi = {10.1093/gigascience/giad026},\n    url = {https://doi.org/10.1093/gigascience/giad026},\n    note = {giad026},\n    eprint = {https://academic.oup.com/gigascience/article-pdf/doi/10.1093/gigascience/giad026/50184346/giad026\\_reviewer\\_3\\_report\\_revision\\_1.pdf},\n}\n\n\n\n\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Dennis Hecker, Fatemeh Behjati Ardakani, Alexander Karollus, Julien Gagneur, & Marcel H. Schulz.\n\n\n \n \n \n \n The adapted Activity-By-Contact model for enhancer-gene assignment and its application to single-cell data.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England),btad062. January 2023.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{hecker_adapted_2023,\n\ttitle = {The adapted {Activity}-{By}-{Contact} model for enhancer-gene assignment and its application to single-cell data},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/btad062},\n\tlanguage = {eng},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Hecker, Dennis and Behjati Ardakani, Fatemeh and Karollus, Alexander and Gagneur, Julien and Schulz, Marcel H.},\n\tmonth = jan,\n\tyear = {2023},\n\tpmid = {36708003},\n\tpages = {btad062},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Frederike Boos, James A. Oo, Timothy Warwick, Stefan Günther, Judit Izquierdo Ponce, Melina Lopez, Diba Rafii, Giulia Buchmann, Minh Duc Pham, Zahraa S. Msheik, Tianfu Li, Sandra Seredinski, Shaza Haydar, Sepide Kashefiolasl, Karl H. Plate, Rüdiger Behr, Matthias Mietsch, Jaya Krishnan, Soni S. Pullamsetti, Sofia-Iris Bibli, Rabea Hinkel, Andrew H. Baker, Reinier A. Boon, Marcel H. Schulz, Ilka Wittig, Francis J. Miller, Ralf P. Brandes, & Matthias S. Leisegang.\n\n\n \n \n \n \n The endothelial-enriched lncRNA LINC00607 mediates angiogenic function.\n \n \n \n\n\n \n\n\n\n Basic Research in Cardiology, 118(1): 5. January 2023.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{boos_endothelial-enriched_2023,\n\ttitle = {The endothelial-enriched {lncRNA} {LINC00607} mediates angiogenic function},\n\tvolume = {118},\n\tissn = {1435-1803},\n\tdoi = {10.1007/s00395-023-00978-3},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Basic Research in Cardiology},\n\tauthor = {Boos, Frederike and Oo, James A. and Warwick, Timothy and Günther, Stefan and Izquierdo Ponce, Judit and Lopez, Melina and Rafii, Diba and Buchmann, Giulia and Pham, Minh Duc and Msheik, Zahraa S. and Li, Tianfu and Seredinski, Sandra and Haydar, Shaza and Kashefiolasl, Sepide and Plate, Karl H. and Behr, Rüdiger and Mietsch, Matthias and Krishnan, Jaya and Pullamsetti, Soni S. and Bibli, Sofia-Iris and Hinkel, Rabea and Baker, Andrew H. and Boon, Reinier A. and Schulz, Marcel H. and Wittig, Ilka and Miller, Francis J. and Brandes, Ralf P. and Leisegang, Matthias S.},\n\tmonth = jan,\n\tyear = {2023},\n\tpmid = {36700983},\n\tpmcid = {PMC9879848},\n\tkeywords = {Humans, Animals, Mice, Chromatin, RNA, Long Noncoding, Gene regulation, Endothelial Cells, Nuclear Proteins, BRG1, DNA Helicases, Endothelial cell, ERG, Hypoxia, Long non-coding RNA, Mice, SCID, Neovascularization, Physiologic},\n\tpages = {5}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Chaonan Zhu, Nina Baumgarten, Meiqian Wu, Yue Wang, Arka Provo Das, Jaskiran Kaur, Fatemeh Behjati Ardakani, Thanh Thuy Duong, Minh Duc Pham, Maria Duda, Stefanie Dimmeler, Ting Yuan, Marcel Schulz, & Jaya Krishnan.\n\n\n \n \n \n \n \n CVD-associated SNPs with regulatory potential drive pathologic non-coding RNA expression.\n \n \n \n \n\n\n \n\n\n\n bioRxiv. 2023.\n \n\n\n\n
\n\n\n\n \n \n \"CVD-associatedPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 5 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article {Zhu2023.02.12.528184,\n\ttitle = {CVD-associated SNPs with regulatory potential drive pathologic non-coding RNA expression},\n\tauthor = {Zhu, Chaonan and Baumgarten, Nina and Wu, Meiqian and Wang, Yue and Das, Arka Provo and Kaur, Jaskiran and Ardakani, Fatemeh Behjati and Duong, Thanh Thuy and Pham, Minh Duc and Duda, Maria and Dimmeler, Stefanie and Yuan, Ting and Schulz, Marcel and Krishnan, Jaya},\n\tyear = {2023},\n\tdoi = {10.1101/2023.02.12.528184},\n\tpublisher = {Cold Spring Harbor Laboratory},\n\tURL = {https://www.biorxiv.org/content/early/2023/02/12/2023.02.12.528184},\n\teprint = {https://www.biorxiv.org/content/early/2023/02/12/2023.02.12.528184.full.pdf},\n\tjournal = {bioRxiv}\n}\n\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Nina Baumgarten, Laura Rumpf, Thorsten Kessler, & Marcel H. Schulz.\n\n\n \n \n \n \n \n A statistical approach to identify regulatory DNA variations.\n \n \n \n \n\n\n \n\n\n\n bioRxiv. February 2023.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 4 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{baumgarten_statistical_2023,\n\ttitle = {A statistical approach to identify regulatory {DNA} variations},\n\ttype = {preprint},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2023.01.31.526404},\n\tpublisher = {Cold Spring Harbor Laboratory},\n\turldate = {2023-02-05},\n\tauthor = {Baumgarten, Nina and Rumpf, Laura and Kessler, Thorsten and Schulz, Marcel H.},\n\tmonth = feb,\n\tyear = {2023},\n\tdoi = {10.1101/2023.01.31.526404},\n\tjournal = {bioRxiv}\n}\n\n\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2022\n \n \n (10)\n \n \n
\n
\n \n \n
\n \n\n \n \n Paola Cattaneo, Michael G. B. Hayes, Nina Baumgarten, Dennis Hecker, Sofia Peruzzo, Galip S. Aslan, Paolo Kunderfranco, Veronica Larcher, Lunfeng Zhang, Riccardo Contu, Gregory Fonseca, Simone Spinozzi, Ju Chen, Gianluigi Condorelli, Stefanie Dimmeler, Marcel H. Schulz, Sven Heinz, Nuno Guimarães-Camboa, & Sylvia M. Evans.\n\n\n \n \n \n \n DOT1L regulates chamber-specific transcriptional networks during cardiogenesis and mediates postnatal cell cycle withdrawal.\n \n \n \n\n\n \n\n\n\n Nature Communications, 13(1): 7444. December 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{cattaneo_dot1l_2022,\n\ttitle = {{DOT1L} regulates chamber-specific transcriptional networks during cardiogenesis and mediates postnatal cell cycle withdrawal},\n\tvolume = {13},\n\tissn = {2041-1723},\n\tdoi = {10.1038/s41467-022-35070-2},\n\tabstract = {Mechanisms by which specific histone modifications regulate distinct gene networks remain little understood. We investigated how H3K79me2, a modification catalyzed by DOT1L and previously considered a general transcriptional activation mark, regulates gene expression during cardiogenesis. Embryonic cardiomyocyte ablation of Dot1l revealed that H3K79me2 does not act as a general transcriptional activator, but rather regulates highly specific transcriptional networks at two critical cardiogenic junctures: embryonic cardiogenesis, where it was particularly important for left ventricle-specific genes, and postnatal cardiomyocyte cell cycle withdrawal, with Dot1L mutants having more mononuclear cardiomyocytes and prolonged cardiomyocyte cell cycle activity. Mechanistic analyses revealed that H3K79me2 in two distinct domains, gene bodies and regulatory elements, synergized to promote expression of genes activated by DOT1L. Surprisingly, H3K79me2 in specific regulatory elements also contributed to silencing genes usually not expressed in cardiomyocytes. These results reveal mechanisms by which DOT1L successively regulates left ventricle specification and cardiomyocyte cell cycle withdrawal.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Nature Communications},\n\tauthor = {Cattaneo, Paola and Hayes, Michael G. B. and Baumgarten, Nina and Hecker, Dennis and Peruzzo, Sofia and Aslan, Galip S. and Kunderfranco, Paolo and Larcher, Veronica and Zhang, Lunfeng and Contu, Riccardo and Fonseca, Gregory and Spinozzi, Simone and Chen, Ju and Condorelli, Gianluigi and Dimmeler, Stefanie and Schulz, Marcel H. and Heinz, Sven and Guimarães-Camboa, Nuno and Evans, Sylvia M.},\n\tmonth = dec,\n\tyear = {2022},\n\tpmid = {36460641},\n\tpmcid = {PMC9718823},\n\tkeywords = {Cell Cycle, Cell Division, Gene Regulatory Networks, Heart Ventricles, Myocytes, Cardiac},\n\tpages = {7444},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/BYXCCSPI/Cattaneo et al. - 2022 - DOT1L regulates chamber-specific transcriptional n.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Mechanisms by which specific histone modifications regulate distinct gene networks remain little understood. We investigated how H3K79me2, a modification catalyzed by DOT1L and previously considered a general transcriptional activation mark, regulates gene expression during cardiogenesis. Embryonic cardiomyocyte ablation of Dot1l revealed that H3K79me2 does not act as a general transcriptional activator, but rather regulates highly specific transcriptional networks at two critical cardiogenic junctures: embryonic cardiogenesis, where it was particularly important for left ventricle-specific genes, and postnatal cardiomyocyte cell cycle withdrawal, with Dot1L mutants having more mononuclear cardiomyocytes and prolonged cardiomyocyte cell cycle activity. Mechanistic analyses revealed that H3K79me2 in two distinct domains, gene bodies and regulatory elements, synergized to promote expression of genes activated by DOT1L. Surprisingly, H3K79me2 in specific regulatory elements also contributed to silencing genes usually not expressed in cardiomyocytes. These results reveal mechanisms by which DOT1L successively regulates left ventricle specification and cardiomyocyte cell cycle withdrawal.\n
\n\n\n
\n\n\n
\n \n\n \n \n Matthias S. Leisegang, Jasleen Kaur Bains, Sandra Seredinski, James A. Oo, Nina M. Krause, Chao-Chung Kuo, Stefan Günther, Nevcin Sentürk Cetin, Timothy Warwick, Can Cao, Frederike Boos, Judit Izquierdo Ponce, Shaza Haydar, Rebecca Bednarz, Chanil Valasarajan, Dominik C. Fuhrmann, Jens Preussner, Mario Looso, Soni S. Pullamsetti, Marcel H. Schulz, Hendrik R. A. Jonker, Christian Richter, Flávia Rezende, Ralf Gilsbach, Beatrice Pflüger-Müller, Ilka Wittig, Ingrid Grummt, Teodora Ribarska, Ivan G. Costa, Harald Schwalbe, & Ralf P. Brandes.\n\n\n \n \n \n \n HIF1α-AS1 is a DNA:DNA:RNA triplex-forming lncRNA interacting with the HUSH complex.\n \n \n \n\n\n \n\n\n\n Nature Communications, 13(1): 6563. November 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{leisegang_hif1-as1_2022,\n\ttitle = {{HIF1α}-{AS1} is a {DNA}:{DNA}:{RNA} triplex-forming {lncRNA} interacting with the {HUSH} complex},\n\tvolume = {13},\n\tissn = {2041-1723},\n\tshorttitle = {{HIF1α}-{AS1} is a {DNA}},\n\tdoi = {10.1038/s41467-022-34252-2},\n\tabstract = {DNA:DNA:RNA triplexes that are formed through Hoogsteen base-pairing of the RNA in the major groove of the DNA duplex have been observed in vitro, but the extent to which these interactions occur in cells and how they impact cellular functions remains elusive. Using a combination of bioinformatic techniques, RNA/DNA pulldown and biophysical studies, we set out to identify functionally important DNA:DNA:RNA triplex-forming long non-coding RNAs (lncRNA) in human endothelial cells. The lncRNA HIF1α-AS1 was retrieved as a top hit. Endogenous HIF1α-AS1 reduces the expression of numerous genes, including EPH Receptor A2 and Adrenomedullin through DNA:DNA:RNA triplex formation by acting as an adapter for the repressive human silencing hub complex (HUSH). Moreover, the oxygen-sensitive HIF1α-AS1 is down-regulated in pulmonary hypertension and loss-of-function approaches not only result in gene de-repression but also enhance angiogenic capacity. As exemplified here with HIF1α-AS1, DNA:DNA:RNA triplex formation is a functionally important mechanism of trans-acting gene expression control.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Nature Communications},\n\tauthor = {Leisegang, Matthias S. and Bains, Jasleen Kaur and Seredinski, Sandra and Oo, James A. and Krause, Nina M. and Kuo, Chao-Chung and Günther, Stefan and Sentürk Cetin, Nevcin and Warwick, Timothy and Cao, Can and Boos, Frederike and Izquierdo Ponce, Judit and Haydar, Shaza and Bednarz, Rebecca and Valasarajan, Chanil and Fuhrmann, Dominik C. and Preussner, Jens and Looso, Mario and Pullamsetti, Soni S. and Schulz, Marcel H. and Jonker, Hendrik R. A. and Richter, Christian and Rezende, Flávia and Gilsbach, Ralf and Pflüger-Müller, Beatrice and Wittig, Ilka and Grummt, Ingrid and Ribarska, Teodora and Costa, Ivan G. and Schwalbe, Harald and Brandes, Ralf P.},\n\tmonth = nov,\n\tyear = {2022},\n\tpmid = {36323673},\n\tpmcid = {PMC9630315},\n\tkeywords = {Base Pairing, DNA, Endothelial Cells, Gene Expression Regulation, Neoplastic, Humans, Oligonucleotides, RNA, Long Noncoding},\n\tpages = {6563},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/IUDM4VBV/Leisegang et al. - 2022 - HIF1α-AS1 is a DNADNARNA triplex-forming lncRNA .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n DNA:DNA:RNA triplexes that are formed through Hoogsteen base-pairing of the RNA in the major groove of the DNA duplex have been observed in vitro, but the extent to which these interactions occur in cells and how they impact cellular functions remains elusive. Using a combination of bioinformatic techniques, RNA/DNA pulldown and biophysical studies, we set out to identify functionally important DNA:DNA:RNA triplex-forming long non-coding RNAs (lncRNA) in human endothelial cells. The lncRNA HIF1α-AS1 was retrieved as a top hit. Endogenous HIF1α-AS1 reduces the expression of numerous genes, including EPH Receptor A2 and Adrenomedullin through DNA:DNA:RNA triplex formation by acting as an adapter for the repressive human silencing hub complex (HUSH). Moreover, the oxygen-sensitive HIF1α-AS1 is down-regulated in pulmonary hypertension and loss-of-function approaches not only result in gene de-repression but also enhance angiogenic capacity. As exemplified here with HIF1α-AS1, DNA:DNA:RNA triplex formation is a functionally important mechanism of trans-acting gene expression control.\n
\n\n\n
\n\n\n
\n \n\n \n \n Timothy Warwick, Sandra Seredinski, Nina M. Krause, Jasleen Kaur Bains, Lara Althaus, James A. Oo, Alessandro Bonetti, Anne Dueck, Stefan Engelhardt, Harald Schwalbe, Matthias S. Leisegang, Marcel H. Schulz, & Ralf P. Brandes.\n\n\n \n \n \n \n A universal model of RNA.DNA:DNA triplex formation accurately predicts genome-wide RNA-DNA interactions.\n \n \n \n\n\n \n\n\n\n Briefings in Bioinformatics, 23(6): bbac445. November 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{warwick_universal_2022,\n\ttitle = {A universal model of {RNA}.{DNA}:{DNA} triplex formation accurately predicts genome-wide {RNA}-{DNA} interactions},\n\tvolume = {23},\n\tissn = {1477-4054},\n\tshorttitle = {A universal model of {RNA}.{DNA}},\n\tdoi = {10.1093/bib/bbac445},\n\tabstract = {RNA.DNA:DNA triple helix (triplex) formation is a form of RNA-DNA interaction which regulates gene expression but is difficult to study experimentally in vivo. This makes accurate computational prediction of such interactions highly important in the field of RNA research. Current predictive methods use canonical Hoogsteen base pairing rules, which whilst biophysically valid, may not reflect the plastic nature of cell biology. Here, we present the first optimization approach to learn a probabilistic model describing RNA-DNA interactions directly from motifs derived from triplex sequencing data. We find that there are several stable interaction codes, including Hoogsteen base pairing and novel RNA-DNA base pairings, which agree with in vitro measurements. We implemented these findings in TriplexAligner, a program that uses the determined interaction codes to predict triplex binding. TriplexAligner predicts RNA-DNA interactions identified in all-to-all sequencing data more accurately than all previously published tools in human and mouse and also predicts previously studied triplex interactions with known regulatory functions. We further validated a novel triplex interaction using biophysical experiments. Our work is an important step towards better understanding of triplex formation and allows genome-wide analyses of RNA-DNA interactions.},\n\tlanguage = {eng},\n\tnumber = {6},\n\tjournal = {Briefings in Bioinformatics},\n\tauthor = {Warwick, Timothy and Seredinski, Sandra and Krause, Nina M. and Bains, Jasleen Kaur and Althaus, Lara and Oo, James A. and Bonetti, Alessandro and Dueck, Anne and Engelhardt, Stefan and Schwalbe, Harald and Leisegang, Matthias S. and Schulz, Marcel H. and Brandes, Ralf P.},\n\tmonth = nov,\n\tyear = {2022},\n\tpmid = {36239395},\n\tpmcid = {PMC9677506},\n\tkeywords = {Animals, DNA, DNA Replication, Genome-Wide Association Study, Humans, machine learning, Mice, Nucleic Acid Conformation, RNA, RNA–DNA interaction, Triplex},\n\tpages = {bbac445},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/Q5W3SC4I/Warwick et al. - 2022 - A universal model of RNA.DNADNA triplex formation.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n RNA.DNA:DNA triple helix (triplex) formation is a form of RNA-DNA interaction which regulates gene expression but is difficult to study experimentally in vivo. This makes accurate computational prediction of such interactions highly important in the field of RNA research. Current predictive methods use canonical Hoogsteen base pairing rules, which whilst biophysically valid, may not reflect the plastic nature of cell biology. Here, we present the first optimization approach to learn a probabilistic model describing RNA-DNA interactions directly from motifs derived from triplex sequencing data. We find that there are several stable interaction codes, including Hoogsteen base pairing and novel RNA-DNA base pairings, which agree with in vitro measurements. We implemented these findings in TriplexAligner, a program that uses the determined interaction codes to predict triplex binding. TriplexAligner predicts RNA-DNA interactions identified in all-to-all sequencing data more accurately than all previously published tools in human and mouse and also predicts previously studied triplex interactions with known regulatory functions. We further validated a novel triplex interaction using biophysical experiments. Our work is an important step towards better understanding of triplex formation and allows genome-wide analyses of RNA-DNA interactions.\n
\n\n\n
\n\n\n
\n \n\n \n \n Timothy Warwick, Marcel H. Schulz, Ralf Gilsbach, Ralf P. Brandes, & Sabine Seuter.\n\n\n \n \n \n \n Nuclear receptor activation shapes spatial genome organization essential for gene expression control: lessons learned from the vitamin D receptor.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 50(7): 3745–3763. April 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{warwick_nuclear_2022,\n\ttitle = {Nuclear receptor activation shapes spatial genome organization essential for gene expression control: lessons learned from the vitamin {D} receptor},\n\tvolume = {50},\n\tissn = {1362-4962},\n\tshorttitle = {Nuclear receptor activation shapes spatial genome organization essential for gene expression control},\n\tdoi = {10.1093/nar/gkac178},\n\tabstract = {Spatial genome organization is tightly controlled by several regulatory mechanisms and is essential for gene expression control. Nuclear receptors are ligand-activated transcription factors that modulate physiological and pathophysiological processes and are primary pharmacological targets. DNA binding of the important loop-forming insulator protein CCCTC-binding factor (CTCF) was modulated by 1α,25-dihydroxyvitamin D3 (1,25(OH)2D3). We performed CTCF HiChIP assays to produce the first genome-wide dataset of CTCF long-range interactions in 1,25(OH)2D3-treated cells, and to determine whether dynamic changes of spatial chromatin interactions are essential for fine-tuning of nuclear receptor signaling. We detected changes in 3D chromatin organization upon vitamin D receptor (VDR) activation at 3.1\\% of all observed CTCF interactions. VDR binding was enriched at both differential loop anchors and within differential loops. Differential loops were observed in several putative functional roles including TAD border formation, promoter-enhancer looping, and establishment of VDR-responsive insulated neighborhoods. Vitamin D target genes were enriched in differential loops and at their anchors. Secondary vitamin D effects related to dynamic chromatin domain changes were linked to location of downstream transcription factors in differential loops. CRISPR interference and loop anchor deletion experiments confirmed the functional relevance of nuclear receptor ligand-induced adjustments of the chromatin 3D structure for gene expression regulation.},\n\tlanguage = {eng},\n\tnumber = {7},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Warwick, Timothy and Schulz, Marcel H. and Gilsbach, Ralf and Brandes, Ralf P. and Seuter, Sabine},\n\tmonth = apr,\n\tyear = {2022},\n\tpmid = {35325193},\n\tpmcid = {PMC9023275},\n\tkeywords = {Chromatin, Gene Expression, Ligands, Receptors, Calcitriol, Receptors, Cytoplasmic and Nuclear, Transcription Factors, Vitamin D},\n\tpages = {3745--3763},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/LFSWGXSP/Warwick et al. - 2022 - Nuclear receptor activation shapes spatial genome .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Spatial genome organization is tightly controlled by several regulatory mechanisms and is essential for gene expression control. Nuclear receptors are ligand-activated transcription factors that modulate physiological and pathophysiological processes and are primary pharmacological targets. DNA binding of the important loop-forming insulator protein CCCTC-binding factor (CTCF) was modulated by 1α,25-dihydroxyvitamin D3 (1,25(OH)2D3). We performed CTCF HiChIP assays to produce the first genome-wide dataset of CTCF long-range interactions in 1,25(OH)2D3-treated cells, and to determine whether dynamic changes of spatial chromatin interactions are essential for fine-tuning of nuclear receptor signaling. We detected changes in 3D chromatin organization upon vitamin D receptor (VDR) activation at 3.1% of all observed CTCF interactions. VDR binding was enriched at both differential loop anchors and within differential loops. Differential loops were observed in several putative functional roles including TAD border formation, promoter-enhancer looping, and establishment of VDR-responsive insulated neighborhoods. Vitamin D target genes were enriched in differential loops and at their anchors. Secondary vitamin D effects related to dynamic chromatin domain changes were linked to location of downstream transcription factors in differential loops. CRISPR interference and loop anchor deletion experiments confirmed the functional relevance of nuclear receptor ligand-induced adjustments of the chromatin 3D structure for gene expression regulation.\n
\n\n\n
\n\n\n
\n \n\n \n \n Franziska Drews, Abdulrahman Salhab, Sivarajan Karunanithi, Miriam Cheaib, Martin Jung, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Broad domains of histone marks in the highly compact Paramecium macronuclear genome.\n \n \n \n\n\n \n\n\n\n Genome Research, 32(4): 710–725. April 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{drews_broad_2022,\n\ttitle = {Broad domains of histone marks in the highly compact {Paramecium} macronuclear genome},\n\tvolume = {32},\n\tissn = {1549-5469},\n\tdoi = {10.1101/gr.276126.121},\n\tabstract = {The unicellular ciliate Paramecium contains a large vegetative macronucleus with several unusual characteristics, including an extremely high coding density and high polyploidy. As macronculear chromatin is devoid of heterochromatin, our study characterizes the functional epigenomic organization necessary for gene regulation and proper Pol II activity. Histone marks (H3K4me3, H3K9ac, H3K27me3) reveal no narrow peaks but broad domains along gene bodies, whereas intergenic regions are devoid of nucleosomes. Our data implicate H3K4me3 levels inside ORFs to be the main factor associated with gene expression, and H3K27me3 appears in association with H3K4me3 in plastic genes. Silent and lowly expressed genes show low nucleosome occupancy, suggesting that gene inactivation does not involve increased nucleosome occupancy and chromatin condensation. Because of a high occupancy of Pol II along highly expressed ORFs, transcriptional elongation appears to be quite different from that of other species. This is supported by missing heptameric repeats in the C-terminal domain of Pol II and a divergent elongation system. Our data imply that unoccupied DNA is the default state, whereas gene activation requires nucleosome recruitment together with broad domains of H3K4me3. In summary, gene activation and silencing in Paramecium run counter to the current understanding of chromatin biology.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {Genome Research},\n\tauthor = {Drews, Franziska and Salhab, Abdulrahman and Karunanithi, Sivarajan and Cheaib, Miriam and Jung, Martin and Schulz, Marcel H. and Simon, Martin},\n\tmonth = apr,\n\tyear = {2022},\n\tpmid = {35264449},\n\tpmcid = {PMC8997361},\n\tkeywords = {Chromatin, Histone Code, Histones, Nucleosomes, Paramecium, RNA Polymerase II},\n\tpages = {710--725},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/3BJ4YQII/Drews et al. - 2022 - Broad domains of histone marks in the highly compa.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The unicellular ciliate Paramecium contains a large vegetative macronucleus with several unusual characteristics, including an extremely high coding density and high polyploidy. As macronculear chromatin is devoid of heterochromatin, our study characterizes the functional epigenomic organization necessary for gene regulation and proper Pol II activity. Histone marks (H3K4me3, H3K9ac, H3K27me3) reveal no narrow peaks but broad domains along gene bodies, whereas intergenic regions are devoid of nucleosomes. Our data implicate H3K4me3 levels inside ORFs to be the main factor associated with gene expression, and H3K27me3 appears in association with H3K4me3 in plastic genes. Silent and lowly expressed genes show low nucleosome occupancy, suggesting that gene inactivation does not involve increased nucleosome occupancy and chromatin condensation. Because of a high occupancy of Pol II along highly expressed ORFs, transcriptional elongation appears to be quite different from that of other species. This is supported by missing heptameric repeats in the C-terminal domain of Pol II and a divergent elongation system. Our data imply that unoccupied DNA is the default state, whereas gene activation requires nucleosome recruitment together with broad domains of H3K4me3. In summary, gene activation and silencing in Paramecium run counter to the current understanding of chromatin biology.\n
\n\n\n
\n\n\n
\n \n\n \n \n Ralf Schulze Brüning, Lukas Tombor, Marcel H. Schulz, Stefanie Dimmeler, & David John.\n\n\n \n \n \n \n Comparative analysis of common alignment tools for single-cell RNA sequencing.\n \n \n \n\n\n \n\n\n\n GigaScience, 11: giac001. January 2022.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{bruning_comparative_2022,\n\ttitle = {Comparative analysis of common alignment tools for single-cell {RNA} sequencing},\n\tvolume = {11},\n\tissn = {2047-217X},\n\tdoi = {10.1093/gigascience/giac001},\n\tabstract = {BACKGROUND: With the rise of single-cell RNA sequencing new bioinformatic tools have been developed to handle specific demands, such as quantifying unique molecular identifiers and correcting cell barcodes. Here, we benchmarked several datasets with the most common alignment tools for single-cell RNA sequencing data. We evaluated differences in the whitelisting, gene quantification, overall performance, and potential variations in clustering or detection of differentially expressed genes. We compared the tools Cell Ranger version 6, STARsolo, Kallisto, Alevin, and Alevin-fry on 3 published datasets for human and mouse, sequenced with different versions of the 10X sequencing protocol.\nRESULTS: Striking differences were observed in the overall runtime of the mappers. Besides that, Kallisto and Alevin showed variances in the number of valid cells and detected genes per cell. Kallisto reported the highest number of cells; however, we observed an overrepresentation of cells with low gene content and unknown cell type. Conversely, Alevin rarely reported such low-content cells. Further variations were detected in the set of expressed genes. While STARsolo, Cell Ranger 6, Alevin-fry, and Alevin produced similar gene sets, Kallisto detected additional genes from the Vmn and Olfr gene family, which are likely mapping artefacts. We also observed differences in the mitochondrial content of the resulting cells when comparing a prefiltered annotation set to the full annotation set that includes pseudogenes and other biotypes.\nCONCLUSION: Overall, this study provides a detailed comparison of common single-cell RNA sequencing mappers and shows their specific properties on 10X Genomics data.},\n\tlanguage = {eng},\n\tjournal = {GigaScience},\n\tauthor = {Brüning, Ralf Schulze and Tombor, Lukas and Schulz, Marcel H. and Dimmeler, Stefanie and John, David},\n\tmonth = jan,\n\tyear = {2022},\n\tpmid = {35084033},\n\tpmcid = {PMC8848315},\n\tkeywords = {aligners, Animals, benchmarking, Cluster Analysis, Computational Biology, Genomics, mappers, mapping-algorithms, Mice, RNA, Sequence Analysis, RNA, Single-Cell Analysis, single-cell RNA sequencing, Software, transcriptomics},\n\tpages = {giac001},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/KYLRS32F/Brüning et al. - 2022 - Comparative analysis of common alignment tools for.pdf:application/pdf},\n}\n
\n
\n\n\n
\n BACKGROUND: With the rise of single-cell RNA sequencing new bioinformatic tools have been developed to handle specific demands, such as quantifying unique molecular identifiers and correcting cell barcodes. Here, we benchmarked several datasets with the most common alignment tools for single-cell RNA sequencing data. We evaluated differences in the whitelisting, gene quantification, overall performance, and potential variations in clustering or detection of differentially expressed genes. We compared the tools Cell Ranger version 6, STARsolo, Kallisto, Alevin, and Alevin-fry on 3 published datasets for human and mouse, sequenced with different versions of the 10X sequencing protocol. RESULTS: Striking differences were observed in the overall runtime of the mappers. Besides that, Kallisto and Alevin showed variances in the number of valid cells and detected genes per cell. Kallisto reported the highest number of cells; however, we observed an overrepresentation of cells with low gene content and unknown cell type. Conversely, Alevin rarely reported such low-content cells. Further variations were detected in the set of expressed genes. While STARsolo, Cell Ranger 6, Alevin-fry, and Alevin produced similar gene sets, Kallisto detected additional genes from the Vmn and Olfr gene family, which are likely mapping artefacts. We also observed differences in the mitochondrial content of the resulting cells when comparing a prefiltered annotation set to the full annotation set that includes pseudogenes and other biotypes. CONCLUSION: Overall, this study provides a detailed comparison of common single-cell RNA sequencing mappers and shows their specific properties on 10X Genomics data.\n
\n\n\n
\n\n\n
\n \n\n \n \n Dennis Hecker, Fatemeh Behjati Ardakani, Alexander Karollus, Julien Gagneur, & Marcel H. Schulz.\n\n\n \n \n \n \n \n The adapted Activity-By-Contact model for enhancer-gene assignment and its application to single-cell data.\n \n \n \n \n\n\n \n\n\n\n Technical Report Bioinformatics, January 2022.\n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@techreport{hecker_adapted_2022,\n\ttype = {preprint},\n\ttitle = {The adapted {Activity}-{By}-{Contact} model for enhancer-gene assignment and its application to single-cell data},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2022.01.28.478202},\n\tabstract = {Abstract\n          \n            Identifying regulatory regions in the genome is of great interest for understanding the epigenomic landscape in cells. One fundamental challenge in this context is to find the target genes whose expression is affected by the regulatory regions. A recent successful method is the Activity-By-Contact (ABC) model (Fulco et al., 2019) which scores enhancer-gene interactions based on enhancer activity and the contact frequency of an enhancer to its target gene. However, it describes regulatory interactions entirely from a gene’s perspective, and does not account for all the candidate target genes of an enhancer. In addition, the ABC-model requires two types of assays to measure enhancer activity, which limits the applicability. Moreover, there is no implementation available that could allow for an integration with transcription factor (TF) binding information nor an efficient analysis of single-cell data. We demonstrate that the ABC-score can yield a higher accuracy by adapting the enhancer activity according to the number of contacts the enhancer has to its candidate target genes and also by considering all annotated transcription start sites of a gene. Further, we show that the model is comparably accurate with only one assay to measure enhancer activity. We combined our generalised ABC-model (gABC) with TF binding information and illustrate an analysis of a single-cell ATAC-seq data set of the human heart, where we were able to characterise cell type-specific regulatory interactions and predict gene expression based on transcription factor affinities. All executed processing steps are incorporated into our new computational pipeline STARE. The software is available at\n            https://github.com/schulzlab/STARE\n            .},\n\tlanguage = {en},\n\turldate = {2023-01-09},\n\tinstitution = {Bioinformatics},\n\tauthor = {Hecker, Dennis and Ardakani, Fatemeh Behjati and Karollus, Alexander and Gagneur, Julien and Schulz, Marcel H.},\n\tmonth = jan,\n\tyear = {2022},\n\tdoi = {10.1101/2022.01.28.478202},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/6VQQBL9X/Hecker et al. - 2022 - The adapted Activity-By-Contact model for enhancer.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Abstract Identifying regulatory regions in the genome is of great interest for understanding the epigenomic landscape in cells. One fundamental challenge in this context is to find the target genes whose expression is affected by the regulatory regions. A recent successful method is the Activity-By-Contact (ABC) model (Fulco et al., 2019) which scores enhancer-gene interactions based on enhancer activity and the contact frequency of an enhancer to its target gene. However, it describes regulatory interactions entirely from a gene’s perspective, and does not account for all the candidate target genes of an enhancer. In addition, the ABC-model requires two types of assays to measure enhancer activity, which limits the applicability. Moreover, there is no implementation available that could allow for an integration with transcription factor (TF) binding information nor an efficient analysis of single-cell data. We demonstrate that the ABC-score can yield a higher accuracy by adapting the enhancer activity according to the number of contacts the enhancer has to its candidate target genes and also by considering all annotated transcription start sites of a gene. Further, we show that the model is comparably accurate with only one assay to measure enhancer activity. We combined our generalised ABC-model (gABC) with TF binding information and illustrate an analysis of a single-cell ATAC-seq data set of the human heart, where we were able to characterise cell type-specific regulatory interactions and predict gene expression based on transcription factor affinities. All executed processing steps are incorporated into our new computational pipeline STARE. The software is available at https://github.com/schulzlab/STARE .\n
\n\n\n
\n\n\n
\n \n\n \n \n Nikoletta Katsaouni, Florian Aul, Lukas Krischker, Sascha Schmalhofer, Lars Hedrich, & Marcel H. Schulz.\n\n\n \n \n \n \n \n Energy efficient convolutional neural networks for arrhythmia detection.\n \n \n \n \n\n\n \n\n\n\n Array, 13: 100127. March 2022.\n \n\n\n\n
\n\n\n\n \n \n \"EnergyPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{katsaouni_energy_2022,\n\ttitle = {Energy efficient convolutional neural networks for arrhythmia detection},\n\tvolume = {13},\n\tissn = {25900056},\n\turl = {https://linkinghub.elsevier.com/retrieve/pii/S2590005622000017},\n\tdoi = {10.1016/j.array.2022.100127},\n\tlanguage = {en},\n\turldate = {2023-01-09},\n\tjournal = {Array},\n\tauthor = {Katsaouni, Nikoletta and Aul, Florian and Krischker, Lukas and Schmalhofer, Sascha and Hedrich, Lars and Schulz, Marcel H.},\n\tmonth = mar,\n\tyear = {2022},\n\tpages = {100127},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/5Z4VA8DS/Katsaouni et al. - 2022 - Energy efficient convolutional neural networks for.pdf:application/pdf},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Simone Franziska Glaser, Andre Brezski, Nina Baumgarten, Marius Klangwart, Andreas W. Heumüller, Ranjan Kumar Maji, Matthias S. Leisegang, Stefan Guenther, Christoph M. Zehendner, David John, Marcel H. Schulz, Kathi Zarnack, & Stefanie Dimmeler.\n\n\n \n \n \n \n \n Circular RNA circPLOD2 regulates pericyte function by targeting the transcription factor KLF4.\n \n \n \n \n\n\n \n\n\n\n Technical Report Molecular Biology, December 2022.\n \n\n\n\n
\n\n\n\n \n \n \"CircularPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@techreport{glaser_circular_2022,\n\ttype = {preprint},\n\ttitle = {Circular {RNA} {circPLOD2} regulates pericyte function by targeting the transcription factor {KLF4}},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2022.12.04.519017},\n\tabstract = {Abstract\n          \n            Circular RNAs (circRNAs) are generated by back-splicing and control cellular signaling and phenotypes. Pericytes stabilize the capillary structure and play an important role in the formation and maintenance of new blood vessels. Here, we characterized hypoxia-regulated circRNAs in human pericytes and showed that circPLOD2 is induced by hypoxia and regulates pericyte function. Silencing of circPLOD2 increased pericyte proliferation, endothelial-pericyte interaction and tube formation. Transcriptional profiling of circPLOD2-depleted cells and epigenomic analyses revealed widespread changes in gene expression and identified the circPLOD2-dependent regulation of the transcription factor KLF4 as a key effector of these changes. Importantly, overexpression of\n            KLF4\n            was sufficient to reverse the effects on pericyte proliferation and endothelial-pericyte interactions observed after circPLOD2 depletion. Together, these data revealed a novel function of circPLOD2 in the control of pericyte proliferation and capillary formation and showed that circPLOD2-mediated regulation of KLF4 significantly contributes to the transcriptional response to hypoxia.\n          \n          \n            Highlights\n            \n              \n                circPLOD2 is upregulated in hypoxia in human vascular pericytes\n              \n              \n                \n                  Selective depletion of circPLOD2, but not linear\n                  PLOD2\n                  mRNA, changes pericyte migration and endothelial-pericyte interaction\n                \n              \n              \n                circPLOD2 depletion triggers widespread changes in gene expression that are mirrored in the transcriptional hypoxia response\n              \n              \n                Epigenomic analyses pinpoint the transcription factor KLF4 as a central player in circPLOD2-mediated expression changes\n              \n              \n                \n                  KLF4\n                  overexpression is sufficient to rescue the changes in pericyte function caused by circPLOD2 depletion},\n\tlanguage = {en},\n\turldate = {2023-01-10},\n\tinstitution = {Molecular Biology},\n\tauthor = {Glaser, Simone Franziska and Brezski, Andre and Baumgarten, Nina and Klangwart, Marius and Heumüller, Andreas W. and Maji, Ranjan Kumar and Leisegang, Matthias S. and Guenther, Stefan and Zehendner, Christoph M. and John, David and Schulz, Marcel H. and Zarnack, Kathi and Dimmeler, Stefanie},\n\tmonth = dec,\n\tyear = {2022},\n\tdoi = {10.1101/2022.12.04.519017},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/EM7YME4F/Glaser et al. - 2022 - Circular RNA circPLOD2 regulates pericyte function.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Abstract Circular RNAs (circRNAs) are generated by back-splicing and control cellular signaling and phenotypes. Pericytes stabilize the capillary structure and play an important role in the formation and maintenance of new blood vessels. Here, we characterized hypoxia-regulated circRNAs in human pericytes and showed that circPLOD2 is induced by hypoxia and regulates pericyte function. Silencing of circPLOD2 increased pericyte proliferation, endothelial-pericyte interaction and tube formation. Transcriptional profiling of circPLOD2-depleted cells and epigenomic analyses revealed widespread changes in gene expression and identified the circPLOD2-dependent regulation of the transcription factor KLF4 as a key effector of these changes. Importantly, overexpression of KLF4 was sufficient to reverse the effects on pericyte proliferation and endothelial-pericyte interactions observed after circPLOD2 depletion. Together, these data revealed a novel function of circPLOD2 in the control of pericyte proliferation and capillary formation and showed that circPLOD2-mediated regulation of KLF4 significantly contributes to the transcriptional response to hypoxia. Highlights circPLOD2 is upregulated in hypoxia in human vascular pericytes Selective depletion of circPLOD2, but not linear PLOD2 mRNA, changes pericyte migration and endothelial-pericyte interaction circPLOD2 depletion triggers widespread changes in gene expression that are mirrored in the transcriptional hypoxia response Epigenomic analyses pinpoint the transcription factor KLF4 as a central player in circPLOD2-mediated expression changes KLF4 overexpression is sufficient to rescue the changes in pericyte function caused by circPLOD2 depletion\n
\n\n\n
\n\n\n
\n \n\n \n \n Markus Hoffmann, Nico Trummer, Jakub Jankowski, Hye Kyung Lee, Lina-Liv Willruth, Olga Lazareva, Kevin Yuan, Nina Baumgarten, Florian Schmidt, Jan Baumbach, Marcel H. Schulz, David B. Blumenthal, Lothar Hennighausen, & Markus List.\n\n\n \n \n \n \n \n TF-Prioritizer: a java pipeline to prioritize condition-specific transcription factors.\n \n \n \n \n\n\n \n\n\n\n Technical Report Bioinformatics, October 2022.\n \n\n\n\n
\n\n\n\n \n \n \"TF-Prioritizer:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@techreport{hoffmann_tf-prioritizer_2022,\n\ttype = {preprint},\n\ttitle = {{TF}-{Prioritizer}: a java pipeline to prioritize condition-specific transcription factors},\n\tshorttitle = {{TF}-{Prioritizer}},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2022.10.19.512881},\n\tabstract = {ABSTRACT\n          \n            Background\n            Eukaryotic gene expression is controlled by cis-regulatory elements (CREs) including promoters and enhancers which are bound by transcription factors (TFs). Differential expression of TFs and their putative binding sites on CREs cause tissue and developmental-specific transcriptional activity. Consolidating genomic data sets can offer further insights into the accessibility of CREs, TF activity, and thus gene regulation. However, the integration and analysis of multi-modal data sets are hampered by considerable technical challenges. While methods for highlighting differential TF activity from combined ChIP-seq and RNA-seq data exist, they do not offer good usability, have limited support for large-scale data processing, and provide only minimal functionality for visual result interpretation.\n          \n          \n            Results\n            \n              We developed TF-Prioritizer, an automated java pipeline to prioritize condition-specific TFs derived from multi-modal data. TF-Prioritizer creates an interactive, feature-rich, and user-friendly web report of its results. To showcase the potential of TF-Prioritizer, we identified known active TFs (e.g.,\n              Stat5, Elf5, Nfib, Esr1\n              ), their target genes (e.g., milk proteins and cell-cycle genes), and newly classified lactating mammary gland TFs (e.g.,\n              Creb1, Arnt\n              ).\n            \n          \n          \n            Conclusion\n            TF-Prioritizer accepts ChIP-seq and RNA-seq data, as input and suggests TFs with differential activity, thus offering an understanding of genome-wide gene regulation, potential pathogenesis, and therapeutic targets in biomedical research.},\n\tlanguage = {en},\n\turldate = {2023-01-10},\n\tinstitution = {Bioinformatics},\n\tauthor = {Hoffmann, Markus and Trummer, Nico and Jankowski, Jakub and Lee, Hye Kyung and Willruth, Lina-Liv and Lazareva, Olga and Yuan, Kevin and Baumgarten, Nina and Schmidt, Florian and Baumbach, Jan and Schulz, Marcel H. and Blumenthal, David B. and Hennighausen, Lothar and List, Markus},\n\tmonth = oct,\n\tyear = {2022},\n\tdoi = {10.1101/2022.10.19.512881},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/594VCTUY/Hoffmann et al. - 2022 - TF-Prioritizer a java pipeline to prioritize cond.pdf:application/pdf},\n}\n\n\n
\n
\n\n\n
\n ABSTRACT Background Eukaryotic gene expression is controlled by cis-regulatory elements (CREs) including promoters and enhancers which are bound by transcription factors (TFs). Differential expression of TFs and their putative binding sites on CREs cause tissue and developmental-specific transcriptional activity. Consolidating genomic data sets can offer further insights into the accessibility of CREs, TF activity, and thus gene regulation. However, the integration and analysis of multi-modal data sets are hampered by considerable technical challenges. While methods for highlighting differential TF activity from combined ChIP-seq and RNA-seq data exist, they do not offer good usability, have limited support for large-scale data processing, and provide only minimal functionality for visual result interpretation. Results We developed TF-Prioritizer, an automated java pipeline to prioritize condition-specific TFs derived from multi-modal data. TF-Prioritizer creates an interactive, feature-rich, and user-friendly web report of its results. To showcase the potential of TF-Prioritizer, we identified known active TFs (e.g., Stat5, Elf5, Nfib, Esr1 ), their target genes (e.g., milk proteins and cell-cycle genes), and newly classified lactating mammary gland TFs (e.g., Creb1, Arnt ). Conclusion TF-Prioritizer accepts ChIP-seq and RNA-seq data, as input and suggests TFs with differential activity, thus offering an understanding of genome-wide gene regulation, potential pathogenesis, and therapeutic targets in biomedical research.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (12)\n \n \n
\n
\n \n \n
\n \n\n \n \n Michael Scherer, Florian Schmidt, Olga Lazareva, Jörn Walter, Jan Baumbach, Marcel H. Schulz, & Markus List.\n\n\n \n \n \n \n \n Machine learning for deciphering cell heterogeneity and gene regulation.\n \n \n \n \n\n\n \n\n\n\n Nature Computational Science, 1(3): 183–191. March 2021.\n \n\n\n\n
\n\n\n\n \n \n \"MachinePaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{scherer_machine_2021,\n\ttitle = {Machine learning for deciphering cell heterogeneity and gene regulation},\n\tvolume = {1},\n\tissn = {2662-8457},\n\turl = {http://www.nature.com/articles/s43588-021-00038-7},\n\tdoi = {10.1038/s43588-021-00038-7},\n\tlanguage = {en},\n\tnumber = {3},\n\turldate = {2022-11-22},\n\tjournal = {Nature Computational Science},\n\tauthor = {Scherer, Michael and Schmidt, Florian and Lazareva, Olga and Walter, Jörn and Baumbach, Jan and Schulz, Marcel H. and List, Markus},\n\tmonth = mar,\n\tyear = {2021},\n\tpages = {183--191},\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n Franziska Drews, Sivarajan Karunanithi, Ulrike Götz, Simone Marker, Raphael, Marcello Pirritano, Angela M. Rodrigues-Viana, Martin Jung, Gilles Gasparoni, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Two Piwis with Ago-like functions silence somatic genes at the chromatin level.\n \n \n \n\n\n \n\n\n\n RNA biology, 18(sup2): 757–769. November 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{drews_two_2021,\n\ttitle = {Two {Piwis} with {Ago}-like functions silence somatic genes at the chromatin level},\n\tvolume = {18},\n\tissn = {1555-8584},\n\tdoi = {10.1080/15476286.2021.1991114},\n\tabstract = {Most sRNA biogenesis mechanisms involve either RNAse III cleavage or ping-pong amplification by different Piwi proteins harbouring slicer activity. Here, we follow the question why the mechanism of transgene-induced silencing in the ciliate Paramecium needs both Dicer activity and two Ptiwi proteins. This pathway involves primary siRNAs produced from non-translatable transgenes and secondary siRNAs from targeted endogenous loci. Our data does not indicate any signatures from ping-pong amplification but Dicer cleavage of long dsRNA. Ptiwi13 and 14 prefer different sub-cellular localizations and different preferences for primary and secondary siRNAs but do not load them mutually exclusive. Both Piwis enrich for antisense RNAs and show a general preference for uridine-rich sRNAs along the entire sRNA length. In addition, Ptiwi14-loaded siRNAs show a 5´-U signature. Our data indicates both Ptiwis and 2´-O-methylation contributing to strand selection of Dicer cleaved siRNAs. This unexpected function of the two distinct vegetative Piwis extends the increasing knowledge of the diversity of Piwi functions in diverse silencing pathways. We describe an unusual mode of action of Piwi proteins extending not only the great variety of Piwi-associated RNAi pathways but moreover raising the question whether this could have been the primordial one.},\n\tlanguage = {eng},\n\tnumber = {sup2},\n\tjournal = {RNA biology},\n\tauthor = {Drews, Franziska and Karunanithi, Sivarajan and Götz, Ulrike and Marker, Simone and deWijn, Raphael and Pirritano, Marcello and Rodrigues-Viana, Angela M. and Jung, Martin and Gasparoni, Gilles and Schulz, Marcel H. and Simon, Martin},\n\tmonth = nov,\n\tyear = {2021},\n\tpmid = {34663180},\n\tpmcid = {PMC8782163},\n\tkeywords = {Argonaute, Argonaute Proteins, Chromatin, dicer, Gene Expression Profiling, Gene Silencing, High-Throughput Nucleotide Sequencing, Paramecium tetraurelia, piwi, Protein Binding, Protozoan Proteins, Ribonuclease III, RNA interference, RNA Interference, RNA, Small Interfering, secondary siRNAs, siRNA, sRNA loading, transgene-induced silencing, Transgenes},\n\tpages = {757--769},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/QS5VRMRJ/Drews et al. - 2021 - Two Piwis with Ago-like functions silence somatic .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Most sRNA biogenesis mechanisms involve either RNAse III cleavage or ping-pong amplification by different Piwi proteins harbouring slicer activity. Here, we follow the question why the mechanism of transgene-induced silencing in the ciliate Paramecium needs both Dicer activity and two Ptiwi proteins. This pathway involves primary siRNAs produced from non-translatable transgenes and secondary siRNAs from targeted endogenous loci. Our data does not indicate any signatures from ping-pong amplification but Dicer cleavage of long dsRNA. Ptiwi13 and 14 prefer different sub-cellular localizations and different preferences for primary and secondary siRNAs but do not load them mutually exclusive. Both Piwis enrich for antisense RNAs and show a general preference for uridine-rich sRNAs along the entire sRNA length. In addition, Ptiwi14-loaded siRNAs show a 5´-U signature. Our data indicates both Ptiwis and 2´-O-methylation contributing to strand selection of Dicer cleaved siRNAs. This unexpected function of the two distinct vegetative Piwis extends the increasing knowledge of the diversity of Piwi functions in diverse silencing pathways. We describe an unusual mode of action of Piwi proteins extending not only the great variety of Piwi-associated RNAi pathways but moreover raising the question whether this could have been the primordial one.\n
\n\n\n
\n\n\n
\n \n\n \n \n Jessica Hoppstädter, Anna Dembek, Marcus Höring, Hanna S. Schymik, Charlotte Dahlem, Afnan Sultan, Natalie Wirth, Salma Al-Fityan, Britta Diesel, Gilles Gasparoni, Jörn Walter, Volkhard Helms, Hanno Huwer, Martin Simon, Gerhard Liebisch, Marcel H. Schulz, & Alexandra K. Kiemer.\n\n\n \n \n \n \n Dysregulation of cholesterol homeostasis in human lung cancer tissue and tumour-associated macrophages.\n \n \n \n\n\n \n\n\n\n EBioMedicine, 72: 103578. October 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{hoppstadter_dysregulation_2021,\n\ttitle = {Dysregulation of cholesterol homeostasis in human lung cancer tissue and tumour-associated macrophages},\n\tvolume = {72},\n\tissn = {2352-3964},\n\tdoi = {10.1016/j.ebiom.2021.103578},\n\tabstract = {BACKGROUND: Based on reports on elevated cholesterol levels in cancer cells, strategies to lower cholesterol synthesis have been suggested as an antitumour strategy. However, cholesterol depletion has also been shown to induce tumour-promoting actions in tumour-associated macrophages (TAMs).\nMETHODS: We performed lipidomic and transcriptomic analyses of human lung cancer material. To assess whether the TAM phenotype is shaped by secreted factors produced by tumour cells, primary human monocyte-derived macrophages were polarized towards a TAM-like phenotype using tumour cell-conditioned medium.\nFINDINGS: Lipidomic analysis of lung adenocarcinoma (n=29) and adjacent non-tumour tissues (n=22) revealed a significant accumulation of free cholesterol and cholesteryl esters within the tumour tissue. In contrast, cholesterol levels were reduced in TAMs isolated from lung adenocarcinoma tissues when compared with alveolar macrophages (AMs) obtained from adjacent non-tumour tissues. Bulk-RNA-Seq revealed that genes involved in cholesterol biosynthesis and metabolism were downregulated in TAMs, while cholesterol efflux transporters were upregulated. In vitro polarized TAM-like macrophages showed an attenuated lipogenic gene expression signature and exhibited lower cholesterol levels compared with non-polarized macrophages. A genome-wide comparison by bulk RNA-Seq confirmed a high similarity of ex vivo TAMs and in vitro TAM-like macrophages. Modulation of intracellular cholesterol levels by either starving, cholesterol depletion, or efflux transporter inhibition indicated that cholesterol distinctly shapes macrophage gene expression.\nINTERPRETATION: Our data show an opposite dysregulation of cholesterol homeostasis in tumour tissue vs. TAMs. Polarization of in vitro differentiated macrophages by tumour cell-conditioned medium recapitulates key features of ex vivo TAMs.\nFUNDING: Deutsche Forschungsgemeinschaft (DFG), Landesforschungsf €orderungsprogramm Saarland (LFPP).},\n\tlanguage = {eng},\n\tjournal = {EBioMedicine},\n\tauthor = {Hoppstädter, Jessica and Dembek, Anna and Höring, Marcus and Schymik, Hanna S. and Dahlem, Charlotte and Sultan, Afnan and Wirth, Natalie and Al-Fityan, Salma and Diesel, Britta and Gasparoni, Gilles and Walter, Jörn and Helms, Volkhard and Huwer, Hanno and Simon, Martin and Liebisch, Gerhard and Schulz, Marcel H. and Kiemer, Alexandra K.},\n\tmonth = oct,\n\tyear = {2021},\n\tpmid = {34571364},\n\tpmcid = {PMC8479395},\n\tkeywords = {ABCA1, ABCG1, Adenocarcinoma, ATR-101, Cell Line, Tumor, Cholesterol, Gene Expression, Homeostasis, Humans, innate immune response, Lung Neoplasms, Non-small cell lung cancer, Tumor Microenvironment, Tumor-Associated Macrophages},\n\tpages = {103578},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/5IQGPBTG/Hoppstädter et al. - 2021 - Dysregulation of cholesterol homeostasis in human .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Based on reports on elevated cholesterol levels in cancer cells, strategies to lower cholesterol synthesis have been suggested as an antitumour strategy. However, cholesterol depletion has also been shown to induce tumour-promoting actions in tumour-associated macrophages (TAMs). METHODS: We performed lipidomic and transcriptomic analyses of human lung cancer material. To assess whether the TAM phenotype is shaped by secreted factors produced by tumour cells, primary human monocyte-derived macrophages were polarized towards a TAM-like phenotype using tumour cell-conditioned medium. FINDINGS: Lipidomic analysis of lung adenocarcinoma (n=29) and adjacent non-tumour tissues (n=22) revealed a significant accumulation of free cholesterol and cholesteryl esters within the tumour tissue. In contrast, cholesterol levels were reduced in TAMs isolated from lung adenocarcinoma tissues when compared with alveolar macrophages (AMs) obtained from adjacent non-tumour tissues. Bulk-RNA-Seq revealed that genes involved in cholesterol biosynthesis and metabolism were downregulated in TAMs, while cholesterol efflux transporters were upregulated. In vitro polarized TAM-like macrophages showed an attenuated lipogenic gene expression signature and exhibited lower cholesterol levels compared with non-polarized macrophages. A genome-wide comparison by bulk RNA-Seq confirmed a high similarity of ex vivo TAMs and in vitro TAM-like macrophages. Modulation of intracellular cholesterol levels by either starving, cholesterol depletion, or efflux transporter inhibition indicated that cholesterol distinctly shapes macrophage gene expression. INTERPRETATION: Our data show an opposite dysregulation of cholesterol homeostasis in tumour tissue vs. TAMs. Polarization of in vitro differentiated macrophages by tumour cell-conditioned medium recapitulates key features of ex vivo TAMs. FUNDING: Deutsche Forschungsgemeinschaft (DFG), Landesforschungsf €orderungsprogramm Saarland (LFPP).\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, Alexander Marx, Nina Baumgarten, Marie Hebel, Martin Wegner, Manuel Kaulich, Matthias S. Leisegang, Ralf P. Brandes, Jonathan Göke, Jilles Vreeken, & Marcel H. Schulz.\n\n\n \n \n \n \n Integrative analysis of epigenetics data identifies gene-specific regulatory elements.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 49(18): 10397–10418. October 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_integrative_2021,\n\ttitle = {Integrative analysis of epigenetics data identifies gene-specific regulatory elements},\n\tvolume = {49},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkab798},\n\tabstract = {Understanding how epigenetic variation in non-coding regions is involved in distal gene-expression regulation is an important problem. Regulatory regions can be associated to genes using large-scale datasets of epigenetic and expression data. However, for regions of complex epigenomic signals and enhancers that regulate many genes, it is difficult to understand these associations. We present StitchIt, an approach to dissect epigenetic variation in a gene-specific manner for the detection of regulatory elements (REMs) without relying on peak calls in individual samples. StitchIt segments epigenetic signal tracks over many samples to generate the location and the target genes of a REM simultaneously. We show that this approach leads to a more accurate and refined REM detection compared to standard methods even on heterogeneous datasets, which are challenging to model. Also, StitchIt REMs are highly enriched in experimentally determined chromatin interactions and expression quantitative trait loci. We validated several newly predicted REMs using CRISPR-Cas9 experiments, thereby demonstrating the reliability of StitchIt. StitchIt is able to dissect regulation in superenhancers and predicts thousands of putative REMs that go unnoticed using peak-based approaches suggesting that a large part of the regulome might be uncharted water.},\n\tlanguage = {eng},\n\tnumber = {18},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Schmidt, Florian and Marx, Alexander and Baumgarten, Nina and Hebel, Marie and Wegner, Martin and Kaulich, Manuel and Leisegang, Matthias S. and Brandes, Ralf P. and Göke, Jonathan and Vreeken, Jilles and Schulz, Marcel H.},\n\tmonth = oct,\n\tyear = {2021},\n\tpmid = {34508352},\n\tpmcid = {PMC8501997},\n\tkeywords = {Chromatin, Data Analysis, Enhancer Elements, Genetic, Epigenesis, Genetic, Gene Expression Regulation, Human Umbilical Vein Endothelial Cells, Humans},\n\tpages = {10397--10418},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/SDIH56BU/Schmidt et al. - 2021 - Integrative analysis of epigenetics data identifie.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Understanding how epigenetic variation in non-coding regions is involved in distal gene-expression regulation is an important problem. Regulatory regions can be associated to genes using large-scale datasets of epigenetic and expression data. However, for regions of complex epigenomic signals and enhancers that regulate many genes, it is difficult to understand these associations. We present StitchIt, an approach to dissect epigenetic variation in a gene-specific manner for the detection of regulatory elements (REMs) without relying on peak calls in individual samples. StitchIt segments epigenetic signal tracks over many samples to generate the location and the target genes of a REM simultaneously. We show that this approach leads to a more accurate and refined REM detection compared to standard methods even on heterogeneous datasets, which are challenging to model. Also, StitchIt REMs are highly enriched in experimentally determined chromatin interactions and expression quantitative trait loci. We validated several newly predicted REMs using CRISPR-Cas9 experiments, thereby demonstrating the reliability of StitchIt. StitchIt is able to dissect regulation in superenhancers and predicts thousands of putative REMs that go unnoticed using peak-based approaches suggesting that a large part of the regulome might be uncharted water.\n
\n\n\n
\n\n\n
\n \n\n \n \n Markus Hoffmann, Elisabeth Pachl, Michael Hartung, Veronika Stiegler, Jan Baumbach, Marcel H. Schulz, & Markus List.\n\n\n \n \n \n \n SPONGEdb: a pan-cancer resource for competing endogenous RNA interactions.\n \n \n \n\n\n \n\n\n\n NAR cancer, 3(1): zcaa042. March 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{hoffmann_spongedb_2021,\n\ttitle = {{SPONGEdb}: a pan-cancer resource for competing endogenous {RNA} interactions},\n\tvolume = {3},\n\tissn = {2632-8674},\n\tshorttitle = {{SPONGEdb}},\n\tdoi = {10.1093/narcan/zcaa042},\n\tabstract = {microRNAs (miRNAs) are post-transcriptional regulators involved in many biological processes and human diseases, including cancer. The majority of transcripts compete over a limited pool of miRNAs, giving rise to a complex network of competing endogenous RNA (ceRNA) interactions. Currently, gene-regulatory networks focus mostly on transcription factor-mediated regulation, and dedicated efforts for charting ceRNA regulatory networks are scarce. Recently, it became possible to infer ceRNA interactions genome-wide from matched gene and miRNA expression data. Here, we inferred ceRNA regulatory networks for 22 cancer types and a pan-cancer ceRNA network based on data from The Cancer Genome Atlas. To make these networks accessible to the biomedical community, we present SPONGEdb, a database offering a user-friendly web interface to browse and visualize ceRNA interactions and an application programming interface accessible by accompanying R and Python packages. SPONGEdb allows researchers to identify potent ceRNA regulators via network centrality measures and to assess their potential as cancer biomarkers through survival, cancer hallmark and gene set enrichment analysis. In summary, SPONGEdb is a feature-rich web resource supporting the community in studying ceRNA regulation within and across cancer types.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {NAR cancer},\n\tauthor = {Hoffmann, Markus and Pachl, Elisabeth and Hartung, Michael and Stiegler, Veronika and Baumbach, Jan and Schulz, Marcel H. and List, Markus},\n\tmonth = mar,\n\tyear = {2021},\n\tpmid = {34316695},\n\tpmcid = {PMC8210024},\n\tpages = {zcaa042},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/ELK69GUA/Hoffmann et al. - 2021 - SPONGEdb a pan-cancer resource for competing endo.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n microRNAs (miRNAs) are post-transcriptional regulators involved in many biological processes and human diseases, including cancer. The majority of transcripts compete over a limited pool of miRNAs, giving rise to a complex network of competing endogenous RNA (ceRNA) interactions. Currently, gene-regulatory networks focus mostly on transcription factor-mediated regulation, and dedicated efforts for charting ceRNA regulatory networks are scarce. Recently, it became possible to infer ceRNA interactions genome-wide from matched gene and miRNA expression data. Here, we inferred ceRNA regulatory networks for 22 cancer types and a pan-cancer ceRNA network based on data from The Cancer Genome Atlas. To make these networks accessible to the biomedical community, we present SPONGEdb, a database offering a user-friendly web interface to browse and visualize ceRNA interactions and an application programming interface accessible by accompanying R and Python packages. SPONGEdb allows researchers to identify potent ceRNA regulators via network centrality measures and to assess their potential as cancer biomarkers through survival, cancer hallmark and gene set enrichment analysis. In summary, SPONGEdb is a feature-rich web resource supporting the community in studying ceRNA regulation within and across cancer types.\n
\n\n\n
\n\n\n
\n \n\n \n \n Nikoletta Katsaouni, Araek Tashkandi, Lena Wiese, & Marcel H. Schulz.\n\n\n \n \n \n \n Machine learning based disease prediction from genotype data.\n \n \n \n\n\n \n\n\n\n Biological Chemistry, 402(8): 871–885. July 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{katsaouni_machine_2021,\n\ttitle = {Machine learning based disease prediction from genotype data},\n\tvolume = {402},\n\tissn = {1437-4315},\n\tdoi = {10.1515/hsz-2021-0109},\n\tabstract = {Using results from genome-wide association studies for understanding complex traits is a current challenge. Here we review how genotype data can be used with different machine learning (ML) methods to predict phenotype occurrence and severity from genotype data. We discuss common feature encoding schemes and how studies handle the often small number of samples compared to the huge number of variants. We compare which ML methods are being applied, including recent results using deep neural networks. Further, we review the application of methods for feature explanation and interpretation.},\n\tlanguage = {eng},\n\tnumber = {8},\n\tjournal = {Biological Chemistry},\n\tauthor = {Katsaouni, Nikoletta and Tashkandi, Araek and Wiese, Lena and Schulz, Marcel H.},\n\tmonth = jul,\n\tyear = {2021},\n\tpmid = {34218544},\n\tkeywords = {deep neural networks, disease prediction, Genome-Wide Association Study, Genotype, Humans, machine learning, Machine Learning},\n\tpages = {871--885},\n}\n\n
\n
\n\n\n
\n Using results from genome-wide association studies for understanding complex traits is a current challenge. Here we review how genotype data can be used with different machine learning (ML) methods to predict phenotype occurrence and severity from genotype data. We discuss common feature encoding schemes and how studies handle the often small number of samples compared to the huge number of variants. We compare which ML methods are being applied, including recent results using deep neural networks. Further, we review the application of methods for feature explanation and interpretation.\n
\n\n\n
\n\n\n
\n \n\n \n \n Beatriz Serrano-Solano, Melanie C. Föll, Cristóbal Gallardo-Alba, Anika Erxleben, Helena Rasche, Saskia Hiltemann, Matthias Fahrner, Mark J. Dunning, Marcel H. Schulz, Beáta Scholtz, Dave Clements, Anton Nekrutenko, Bérénice Batut, & Björn A. Grüning.\n\n\n \n \n \n \n Fostering accessible online education using Galaxy as an e-learning platform.\n \n \n \n\n\n \n\n\n\n PLoS computational biology, 17(5): e1008923. May 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{serrano-solano_fostering_2021,\n\ttitle = {Fostering accessible online education using {Galaxy} as an e-learning platform},\n\tvolume = {17},\n\tissn = {1553-7358},\n\tdoi = {10.1371/journal.pcbi.1008923},\n\tabstract = {The COVID-19 pandemic is shifting teaching to an online setting all over the world. The Galaxy framework facilitates the online learning process and makes it accessible by providing a library of high-quality community-curated training materials, enabling easy access to data and tools, and facilitates sharing achievements and progress between students and instructors. By combining Galaxy with robust communication channels, effective instruction can be designed inclusively, regardless of the students' environments.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {PLoS computational biology},\n\tauthor = {Serrano-Solano, Beatriz and Föll, Melanie C. and Gallardo-Alba, Cristóbal and Erxleben, Anika and Rasche, Helena and Hiltemann, Saskia and Fahrner, Matthias and Dunning, Mark J. and Schulz, Marcel H. and Scholtz, Beáta and Clements, Dave and Nekrutenko, Anton and Batut, Bérénice and Grüning, Björn A.},\n\tmonth = may,\n\tyear = {2021},\n\tpmid = {33983944},\n\tpmcid = {PMC8118283},\n\tkeywords = {Computational Biology, Computer-Assisted Instruction, COVID-19, Education, Distance, Humans, Information Dissemination, Pandemics, SARS-CoV-2},\n\tpages = {e1008923},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/3W7DM8ZL/Serrano-Solano et al. - 2021 - Fostering accessible online education using Galaxy.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The COVID-19 pandemic is shifting teaching to an online setting all over the world. The Galaxy framework facilitates the online learning process and makes it accessible by providing a library of high-quality community-curated training materials, enabling easy access to data and tools, and facilitates sharing achievements and progress between students and instructors. By combining Galaxy with robust communication channels, effective instruction can be designed inclusively, regardless of the students' environments.\n
\n\n\n
\n\n\n
\n \n\n \n \n Jonas Fischer, Fatemeh Behjati Ardakani, Kathrin Kattler, Jörn Walter, & Marcel H. Schulz.\n\n\n \n \n \n \n CpG content-dependent associations between transcription factors and histone modifications.\n \n \n \n\n\n \n\n\n\n PloS One, 16(4): e0249985. 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{fischer_cpg_2021,\n\ttitle = {{CpG} content-dependent associations between transcription factors and histone modifications},\n\tvolume = {16},\n\tissn = {1932-6203},\n\tdoi = {10.1371/journal.pone.0249985},\n\tabstract = {Understanding the factors that underlie the epigenetic regulation of genes is crucial to understand the gene regulatory machinery as a whole. Several experimental and computational studies examined the relationship between different factors involved. Here we investigate the relationship between transcription factors (TFs) and histone modifications (HMs), based on ChIP-seq data in cell lines. As it was shown that gene regulation by TFs differs depending on the CpG class of a promoter, we study the impact of the CpG content in promoters on the associations between TFs and HMs. We suggest an approach based on sparse linear regression models to infer associations between TFs and HMs with respect to CpG content. A study of the partial correlation of HMs for the two classes of high and low CpG content reveals possible CpG dependence and potential candidates for confounding factors in our models. We show that the models are accurate, inferred associations reflect known biological relationships, and we give new insight into associations with respect to CpG content. Moreover, analysis of a ChIP-seq dataset in HepG2 cells of the HM H3K122ac, an HM about little is known, reveals novel TF associations and supports a previously established link to active transcription.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {PloS One},\n\tauthor = {Fischer, Jonas and Ardakani, Fatemeh Behjati and Kattler, Kathrin and Walter, Jörn and Schulz, Marcel H.},\n\tyear = {2021},\n\tpmid = {33857234},\n\tpmcid = {PMC8049299},\n\tkeywords = {Cell Line, Tumor, Chromatin Immunoprecipitation Sequencing, CpG Islands, Gene Expression Regulation, Histones, Humans, Models, Biological, Protein Processing, Post-Translational, Transcription Factors},\n\tpages = {e0249985},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/QN66X9ET/Fischer et al. - 2021 - CpG content-dependent associations between transcr.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Understanding the factors that underlie the epigenetic regulation of genes is crucial to understand the gene regulatory machinery as a whole. Several experimental and computational studies examined the relationship between different factors involved. Here we investigate the relationship between transcription factors (TFs) and histone modifications (HMs), based on ChIP-seq data in cell lines. As it was shown that gene regulation by TFs differs depending on the CpG class of a promoter, we study the impact of the CpG content in promoters on the associations between TFs and HMs. We suggest an approach based on sparse linear regression models to infer associations between TFs and HMs with respect to CpG content. A study of the partial correlation of HMs for the two classes of high and low CpG content reveals possible CpG dependence and potential candidates for confounding factors in our models. We show that the models are accurate, inferred associations reflect known biological relationships, and we give new insight into associations with respect to CpG content. Moreover, analysis of a ChIP-seq dataset in HepG2 cells of the HM H3K122ac, an HM about little is known, reveals novel TF associations and supports a previously established link to active transcription.\n
\n\n\n
\n\n\n
\n \n\n \n \n Timothy Warwick, Marcel H. Schulz, Stefan Günther, Ralf Gilsbach, Antonio Neme, Carsten Carlberg, Ralf P. Brandes, & Sabine Seuter.\n\n\n \n \n \n \n A hierarchical regulatory network analysis of the vitamin D induced transcriptome reveals novel regulators and complete VDR dependency in monocytes.\n \n \n \n\n\n \n\n\n\n Scientific Reports, 11(1): 6518. March 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{warwick_hierarchical_2021,\n\ttitle = {A hierarchical regulatory network analysis of the vitamin {D} induced transcriptome reveals novel regulators and complete {VDR} dependency in monocytes},\n\tvolume = {11},\n\tissn = {2045-2322},\n\tdoi = {10.1038/s41598-021-86032-5},\n\tabstract = {The transcription factor vitamin D receptor (VDR) is the high affinity nuclear target of the biologically active form of vitamin D3 (1,25(OH)2D3). In order to identify pure genomic transcriptional effects of 1,25(OH)2D3, we used VDR cistrome, transcriptome and open chromatin data, obtained from the human monocytic cell line THP-1, for a novel hierarchical analysis applying three bioinformatics approaches. We predicted 75.6\\% of all early 1,25(OH)2D3-responding (2.5 or 4 h) and 57.4\\% of the late differentially expressed genes (24 h) to be primary VDR target genes. VDR knockout led to a complete loss of 1,25(OH)2D3-induced genome-wide gene regulation. Thus, there was no indication of any VDR-independent non-genomic actions of 1,25(OH)2D3 modulating its transcriptional response. Among the predicted primary VDR target genes, 47 were coding for transcription factors and thus may mediate secondary 1,25(OH)2D3 responses. CEBPA and ETS1 ChIP-seq data and RNA-seq following CEBPA knockdown were used to validate the predicted regulation of secondary vitamin D target genes by both transcription factors. In conclusion, a directional network containing 47 partly novel primary VDR target transcription factors describes secondary responses in a highly complex vitamin D signaling cascade. The central transcription factor VDR is indispensable for all transcriptome-wide effects of the nuclear hormone.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Scientific Reports},\n\tauthor = {Warwick, Timothy and Schulz, Marcel H. and Günther, Stefan and Gilsbach, Ralf and Neme, Antonio and Carlberg, Carsten and Brandes, Ralf P. and Seuter, Sabine},\n\tmonth = mar,\n\tyear = {2021},\n\tpmid = {33753848},\n\tpmcid = {PMC7985518},\n\tkeywords = {CCAAT-Enhancer-Binding Proteins, Cholecalciferol, CRISPR-Cas Systems, Gene Expression Regulation, Gene Knockout Techniques, Gene Regulatory Networks, Genome, Human, Humans, Monocytes, Proto-Oncogene Protein c-ets-1, Receptors, Calcitriol, RNA-Seq, Transcriptome, Vitamin D},\n\tpages = {6518},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/ZIDENXMM/Warwick et al. - 2021 - A hierarchical regulatory network analysis of the .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The transcription factor vitamin D receptor (VDR) is the high affinity nuclear target of the biologically active form of vitamin D3 (1,25(OH)2D3). In order to identify pure genomic transcriptional effects of 1,25(OH)2D3, we used VDR cistrome, transcriptome and open chromatin data, obtained from the human monocytic cell line THP-1, for a novel hierarchical analysis applying three bioinformatics approaches. We predicted 75.6% of all early 1,25(OH)2D3-responding (2.5 or 4 h) and 57.4% of the late differentially expressed genes (24 h) to be primary VDR target genes. VDR knockout led to a complete loss of 1,25(OH)2D3-induced genome-wide gene regulation. Thus, there was no indication of any VDR-independent non-genomic actions of 1,25(OH)2D3 modulating its transcriptional response. Among the predicted primary VDR target genes, 47 were coding for transcription factors and thus may mediate secondary 1,25(OH)2D3 responses. CEBPA and ETS1 ChIP-seq data and RNA-seq following CEBPA knockdown were used to validate the predicted regulation of secondary vitamin D target genes by both transcription factors. In conclusion, a directional network containing 47 partly novel primary VDR target transcription factors describes secondary responses in a highly complex vitamin D signaling cascade. The central transcription factor VDR is indispensable for all transcriptome-wide effects of the nuclear hormone.\n
\n\n\n
\n\n\n
\n \n\n \n \n Nina Baumgarten, Florian Schmidt, Martin Wegner, Marie Hebel, Manuel Kaulich, & Marcel H. Schulz.\n\n\n \n \n \n \n Computational prediction of CRISPR-impaired non-coding regulatory regions.\n \n \n \n\n\n \n\n\n\n Biological Chemistry, 402(8): 973–982. July 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{baumgarten_computational_2021,\n\ttitle = {Computational prediction of {CRISPR}-impaired non-coding regulatory regions},\n\tvolume = {402},\n\tissn = {1437-4315},\n\tdoi = {10.1515/hsz-2020-0392},\n\tabstract = {Genome-wide CRISPR screens are becoming more widespread and allow the simultaneous interrogation of thousands of genomic regions. Although recent progress has been made in the analysis of CRISPR screens, it is still an open problem how to interpret CRISPR mutations in non-coding regions of the genome. Most of the tools concentrate on the interpretation of mutations introduced in gene coding regions. We introduce a computational pipeline that uses epigenomic information about regulatory elements for the interpretation of CRISPR mutations in non-coding regions. We illustrate our analysis protocol on the analysis of a genome-wide CRISPR screen in hTERT-RPE1 cells and reveal novel regulatory elements that mediate chemoresistance against doxorubicin in these cells. We infer links to established and to novel chemoresistance genes. Our analysis protocol is general and can be applied on any cell type and with different CRISPR enzymes.},\n\tlanguage = {eng},\n\tnumber = {8},\n\tjournal = {Biological Chemistry},\n\tauthor = {Baumgarten, Nina and Schmidt, Florian and Wegner, Martin and Hebel, Marie and Kaulich, Manuel and Schulz, Marcel H.},\n\tmonth = jul,\n\tyear = {2021},\n\tpmid = {33660495},\n\tkeywords = {chemoresistance, Clustered Regularly Interspaced Short Palindromic Repeats, CRISPR-Cas9 screen, gene regulation, Genomics, mutations, non-coding genome},\n\tpages = {973--982},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/B3U43CY6/Baumgarten et al. - 2021 - Computational prediction of CRISPR-impaired non-co.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Genome-wide CRISPR screens are becoming more widespread and allow the simultaneous interrogation of thousands of genomic regions. Although recent progress has been made in the analysis of CRISPR screens, it is still an open problem how to interpret CRISPR mutations in non-coding regions of the genome. Most of the tools concentrate on the interpretation of mutations introduced in gene coding regions. We introduce a computational pipeline that uses epigenomic information about regulatory elements for the interpretation of CRISPR mutations in non-coding regions. We illustrate our analysis protocol on the analysis of a genome-wide CRISPR screen in hTERT-RPE1 cells and reveal novel regulatory elements that mediate chemoresistance against doxorubicin in these cells. We infer links to established and to novel chemoresistance genes. Our analysis protocol is general and can be applied on any cell type and with different CRISPR enzymes.\n
\n\n\n
\n\n\n
\n \n\n \n \n Lukas S. Tombor, David John, Simone F. Glaser, Guillermo Luxán, Elvira Forte, Milena Furtado, Nadia Rosenthal, Nina Baumgarten, Marcel H. Schulz, Janina Wittig, Eva-Maria Rogg, Yosif Manavski, Ariane Fischer, Marion Muhly-Reinholz, Kathrin Klee, Mario Looso, Carmen Selignow, Till Acker, Sofia-Iris Bibli, Ingrid Fleming, Ralph Patrick, Richard P. Harvey, Wesley T. Abplanalp, & Stefanie Dimmeler.\n\n\n \n \n \n \n Single cell sequencing reveals endothelial plasticity with transient mesenchymal activation after myocardial infarction.\n \n \n \n\n\n \n\n\n\n Nature Communications, 12(1): 681. January 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{tombor_single_2021,\n\ttitle = {Single cell sequencing reveals endothelial plasticity with transient mesenchymal activation after myocardial infarction},\n\tvolume = {12},\n\tissn = {2041-1723},\n\tdoi = {10.1038/s41467-021-20905-1},\n\tabstract = {Endothelial cells play a critical role in the adaptation of tissues to injury. Tissue ischemia induced by infarction leads to profound changes in endothelial cell functions and can induce transition to a mesenchymal state. Here we explore the kinetics and individual cellular responses of endothelial cells after myocardial infarction by using single cell RNA sequencing. This study demonstrates a time dependent switch in endothelial cell proliferation and inflammation associated with transient changes in metabolic gene signatures. Trajectory analysis reveals that the majority of endothelial cells 3 to 7 days after myocardial infarction acquire a transient state, characterized by mesenchymal gene expression, which returns to baseline 14 days after injury. Lineage tracing, using the Cdh5-CreERT2;mT/mG mice followed by single cell RNA sequencing, confirms the transient mesenchymal transition and reveals additional hypoxic and inflammatory signatures of endothelial cells during early and late states after injury. These data suggest that endothelial cells undergo a transient mes-enchymal activation concomitant with a metabolic adaptation within the first days after myocardial infarction but do not acquire a long-term mesenchymal fate. This mesenchymal activation may facilitate endothelial cell migration and clonal expansion to regenerate the vascular network.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Nature Communications},\n\tauthor = {Tombor, Lukas S. and John, David and Glaser, Simone F. and Luxán, Guillermo and Forte, Elvira and Furtado, Milena and Rosenthal, Nadia and Baumgarten, Nina and Schulz, Marcel H. and Wittig, Janina and Rogg, Eva-Maria and Manavski, Yosif and Fischer, Ariane and Muhly-Reinholz, Marion and Klee, Kathrin and Looso, Mario and Selignow, Carmen and Acker, Till and Bibli, Sofia-Iris and Fleming, Ingrid and Patrick, Ralph and Harvey, Richard P. and Abplanalp, Wesley T. and Dimmeler, Stefanie},\n\tmonth = jan,\n\tyear = {2021},\n\tpmid = {33514719},\n\tpmcid = {PMC7846794},\n\tkeywords = {Animals, Cell Movement, Cell Plasticity, Cell Proliferation, Cells, Cultured, Disease Models, Animal, Endothelial Cells, Endothelium, Epithelial-Mesenchymal Transition, Genes, Reporter, Human Umbilical Vein Endothelial Cells, Humans, Luminescent Proteins, Male, Mice, Mice, Transgenic, Myocardial Infarction, Myocardium, RNA-Seq, Single-Cell Analysis},\n\tpages = {681},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/S3N3PNAI/Tombor et al. - 2021 - Single cell sequencing reveals endothelial plastic.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Endothelial cells play a critical role in the adaptation of tissues to injury. Tissue ischemia induced by infarction leads to profound changes in endothelial cell functions and can induce transition to a mesenchymal state. Here we explore the kinetics and individual cellular responses of endothelial cells after myocardial infarction by using single cell RNA sequencing. This study demonstrates a time dependent switch in endothelial cell proliferation and inflammation associated with transient changes in metabolic gene signatures. Trajectory analysis reveals that the majority of endothelial cells 3 to 7 days after myocardial infarction acquire a transient state, characterized by mesenchymal gene expression, which returns to baseline 14 days after injury. Lineage tracing, using the Cdh5-CreERT2;mT/mG mice followed by single cell RNA sequencing, confirms the transient mesenchymal transition and reveals additional hypoxic and inflammatory signatures of endothelial cells during early and late states after injury. These data suggest that endothelial cells undergo a transient mes-enchymal activation concomitant with a metabolic adaptation within the first days after myocardial infarction but do not acquire a long-term mesenchymal fate. This mesenchymal activation may facilitate endothelial cell migration and clonal expansion to regenerate the vascular network.\n
\n\n\n
\n\n\n
\n \n\n \n \n Peter Ebert, & Marcel H. Schulz.\n\n\n \n \n \n \n Fast detection of differential chromatin domains with SCIDDO.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 37(9): 1198–1205. June 2021.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{ebert_fast_2021,\n\ttitle = {Fast detection of differential chromatin domains with {SCIDDO}},\n\tvolume = {37},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/btaa960},\n\tabstract = {MOTIVATION: The generation of genome-wide maps of histone modifications using chromatin immunoprecipitation sequencing is a standard approach to dissect the complexity of the epigenome. Interpretation and differential analysis of histone datasets remains challenging due to regulatory meaningful co-occurrences of histone marks and their difference in genomic spread. To ease interpretation, chromatin state segmentation maps are a commonly employed abstraction combining individual histone marks. We developed the tool SCIDDO as a fast, flexible and statistically sound method for the differential analysis of chromatin state segmentation maps.\nRESULTS: We demonstrate the utility of SCIDDO in a comparative analysis that identifies differential chromatin domains (DCD) in various regulatory contexts and with only moderate computational resources. We show that the identified DCDs correlate well with observed changes in gene expression and can recover a substantial number of differentially expressed genes (DEGs). We showcase SCIDDO's ability to directly interrogate chromatin dynamics, such as enhancer switches in downstream analysis, which simplifies exploring specific questions about regulatory changes in chromatin. By comparing SCIDDO to competing methods, we provide evidence that SCIDDO's performance in identifying DEGs via differential chromatin marking is more stable across a range of cell-type comparisons and parameter cut-offs.\nAVAILABILITY AND IMPLEMENTATION: The SCIDDO source code is openly available under github.com/ptrebert/sciddo.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {9},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Ebert, Peter and Schulz, Marcel H.},\n\tmonth = jun,\n\tyear = {2021},\n\tpmid = {33232443},\n\tpmcid = {PMC8189691},\n\tkeywords = {Chromatin, Chromatin Immunoprecipitation, Chromosomes, Genome, Histone Code},\n\tpages = {1198--1205},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/MQBEE8II/Ebert und Schulz - 2021 - Fast detection of differential chromatin domains w.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: The generation of genome-wide maps of histone modifications using chromatin immunoprecipitation sequencing is a standard approach to dissect the complexity of the epigenome. Interpretation and differential analysis of histone datasets remains challenging due to regulatory meaningful co-occurrences of histone marks and their difference in genomic spread. To ease interpretation, chromatin state segmentation maps are a commonly employed abstraction combining individual histone marks. We developed the tool SCIDDO as a fast, flexible and statistically sound method for the differential analysis of chromatin state segmentation maps. RESULTS: We demonstrate the utility of SCIDDO in a comparative analysis that identifies differential chromatin domains (DCD) in various regulatory contexts and with only moderate computational resources. We show that the identified DCDs correlate well with observed changes in gene expression and can recover a substantial number of differentially expressed genes (DEGs). We showcase SCIDDO's ability to directly interrogate chromatin dynamics, such as enhancer switches in downstream analysis, which simplifies exploring specific questions about regulatory changes in chromatin. By comparing SCIDDO to competing methods, we provide evidence that SCIDDO's performance in identifying DEGs via differential chromatin marking is more stable across a range of cell-type comparisons and parameter cut-offs. AVAILABILITY AND IMPLEMENTATION: The SCIDDO source code is openly available under github.com/ptrebert/sciddo. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2020\n \n \n (14)\n \n \n
\n
\n \n \n
\n \n\n \n \n Fatemeh Behjati Ardakani, Kathrin Kattler, Tobias Heinen, Florian Schmidt, David Feuerborn, Gilles Gasparoni, Konstantin Lepikhov, Patrick Nell, Jan Hengstler, Jörn Walter, & Marcel H. Schulz.\n\n\n \n \n \n \n Prediction of single-cell gene expression for transcription factor analysis.\n \n \n \n\n\n \n\n\n\n GigaScience, 9(11): giaa113. October 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{behjati_ardakani_prediction_2020,\n\ttitle = {Prediction of single-cell gene expression for transcription factor analysis},\n\tvolume = {9},\n\tissn = {2047-217X},\n\tdoi = {10.1093/gigascience/giaa113},\n\tabstract = {BACKGROUND: Single-cell RNA sequencing is a powerful technology to discover new cell types and study biological processes in complex biological samples. A current challenge is to predict transcription factor (TF) regulation from single-cell RNA data.\nRESULTS: Here, we propose a novel approach for predicting gene expression at the single-cell level using cis-regulatory motifs, as well as epigenetic features. We designed a tree-guided multi-task learning framework that considers each cell as a task. Through this framework we were able to explain the single-cell gene expression values using either TF binding affinities or TF ChIP-seq data measured at specific genomic regions. TFs identified using these models could be validated by the literature.\nCONCLUSION: Our proposed method allows us to identify distinct TFs that show cell type-specific regulation. This approach is not limited to TFs but can use any type of data that can potentially be used in explaining gene expression at the single-cell level to study factors that drive differentiation or show abnormal regulation in disease. The implementation of our workflow can be accessed under an MIT license via https://github.com/SchulzLab/Triangulate.},\n\tlanguage = {eng},\n\tnumber = {11},\n\tjournal = {GigaScience},\n\tauthor = {Behjati Ardakani, Fatemeh and Kattler, Kathrin and Heinen, Tobias and Schmidt, Florian and Feuerborn, David and Gasparoni, Gilles and Lepikhov, Konstantin and Nell, Patrick and Hengstler, Jan and Walter, Jörn and Schulz, Marcel H.},\n\tmonth = oct,\n\tyear = {2020},\n\tpmid = {33124660},\n\tpmcid = {PMC7596801},\n\tkeywords = {Binding Sites, Gene Expression, Gene Expression Regulation, Protein Binding, Transcription Factors},\n\tpages = {giaa113},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/2T4DN4WA/Behjati Ardakani et al. - 2020 - Prediction of single-cell gene expression for tran.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Single-cell RNA sequencing is a powerful technology to discover new cell types and study biological processes in complex biological samples. A current challenge is to predict transcription factor (TF) regulation from single-cell RNA data. RESULTS: Here, we propose a novel approach for predicting gene expression at the single-cell level using cis-regulatory motifs, as well as epigenetic features. We designed a tree-guided multi-task learning framework that considers each cell as a task. Through this framework we were able to explain the single-cell gene expression values using either TF binding affinities or TF ChIP-seq data measured at specific genomic regions. TFs identified using these models could be validated by the literature. CONCLUSION: Our proposed method allows us to identify distinct TFs that show cell type-specific regulation. This approach is not limited to TFs but can use any type of data that can potentially be used in explaining gene expression at the single-cell level to study factors that drive differentiation or show abnormal regulation in disease. The implementation of our workflow can be accessed under an MIT license via https://github.com/SchulzLab/Triangulate.\n
\n\n\n
\n\n\n
\n \n\n \n \n Giulia K. Buchmann, Christoph Schürmann, Tim Warwick, Marcel H. Schulz, Manuela Spaeth, Oliver J. Müller, Katrin Schröder, Hanjoong Jo, Norbert Weissmann, & Ralf P. Brandes.\n\n\n \n \n \n \n Deletion of NoxO1 limits atherosclerosis development in female mice.\n \n \n \n\n\n \n\n\n\n Redox Biology, 37: 101713. October 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{buchmann_deletion_2020,\n\ttitle = {Deletion of {NoxO1} limits atherosclerosis development in female mice},\n\tvolume = {37},\n\tissn = {2213-2317},\n\tdoi = {10.1016/j.redox.2020.101713},\n\tabstract = {OBJECTIVE: Oxidative stress is a risk factor for atherosclerosis. NADPH oxidases of the Nox family produce ROS but their contribution to atherosclerosis development is less clear. Nox2 promotes and Nox4 rather limits atherosclerosis. Although Nox1 with its cytosolic co-factors are largely expressed in epithelial cells, a role for Nox1 for atherosclerosis development was suggested. To further define the role of this homologue, the role of its essential cytosolic cofactor, NoxO1, was determined for atherosclerosis development with the aid of knockout mice.\nMETHODS AND RESULTS: Wildtype (WT) and NoxO1 knockout mice were treated with high fat diet and adeno-associated virus (AAV) overexpressing pro-protein convertase subtilisin/kexin type 9 (PCSK9) to induce hepatic low-density lipoprotein (LDL) receptor loss. As a result, massive hypercholesterolemia was induced and spontaneous atherosclerosis developed within three month. Deletion of NoxO1 reduced atherosclerosis formation in brachiocephalic artery and aortic arch in female but not male NoxO1-/- mice as compared to WT littermates. This was associated with a reduced pro-inflammatory cytokine signature in the plasma of female but not male NoxO1-/- mice. MACE-RNAseq of the vessel did not reveal this signature and the expression of the Nox1/NoxO1 system was low to not detectable.\nCONCLUSIONS: The scaffolding protein NoxO1 plays some role in atherosclerosis development in female mice probably by attenuating the global inflammatory burden.},\n\tlanguage = {eng},\n\tjournal = {Redox Biology},\n\tauthor = {Buchmann, Giulia K. and Schürmann, Christoph and Warwick, Tim and Schulz, Marcel H. and Spaeth, Manuela and Müller, Oliver J. and Schröder, Katrin and Jo, Hanjoong and Weissmann, Norbert and Brandes, Ralf P.},\n\tmonth = oct,\n\tyear = {2020},\n\tpmid = {32949971},\n\tpmcid = {PMC7502371},\n\tkeywords = {Adaptor Proteins, Signal Transducing, Animals, Atherosclerosis, Female, Gender differences, Mice, Mice, Knockout, NADPH oxidase, NoxO1, PCSK9, Proprotein Convertase 9, Reactive oxygen species, Reactive Oxygen Species},\n\tpages = {101713},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/2QFNM2HT/Buchmann et al. - 2020 - Deletion of NoxO1 limits atherosclerosis developme.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n OBJECTIVE: Oxidative stress is a risk factor for atherosclerosis. NADPH oxidases of the Nox family produce ROS but their contribution to atherosclerosis development is less clear. Nox2 promotes and Nox4 rather limits atherosclerosis. Although Nox1 with its cytosolic co-factors are largely expressed in epithelial cells, a role for Nox1 for atherosclerosis development was suggested. To further define the role of this homologue, the role of its essential cytosolic cofactor, NoxO1, was determined for atherosclerosis development with the aid of knockout mice. METHODS AND RESULTS: Wildtype (WT) and NoxO1 knockout mice were treated with high fat diet and adeno-associated virus (AAV) overexpressing pro-protein convertase subtilisin/kexin type 9 (PCSK9) to induce hepatic low-density lipoprotein (LDL) receptor loss. As a result, massive hypercholesterolemia was induced and spontaneous atherosclerosis developed within three month. Deletion of NoxO1 reduced atherosclerosis formation in brachiocephalic artery and aortic arch in female but not male NoxO1-/- mice as compared to WT littermates. This was associated with a reduced pro-inflammatory cytokine signature in the plasma of female but not male NoxO1-/- mice. MACE-RNAseq of the vessel did not reveal this signature and the expression of the Nox1/NoxO1 system was low to not detectable. CONCLUSIONS: The scaffolding protein NoxO1 plays some role in atherosclerosis development in female mice probably by attenuating the global inflammatory burden.\n
\n\n\n
\n\n\n
\n \n\n \n \n Jenny Vanessa Valbuena Perez, Rebecca Linnenberger, Anna Dembek, Stefano Bruscoli, Carlo Riccardi, Marcel H. Schulz, Markus R. Meyer, Alexandra K. Kiemer, & Jessica Hoppstädter.\n\n\n \n \n \n \n Altered glucocorticoid metabolism represents a feature of macroph-aging.\n \n \n \n\n\n \n\n\n\n Aging Cell, 19(6): e13156. June 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{valbuena_perez_altered_2020,\n\ttitle = {Altered glucocorticoid metabolism represents a feature of macroph-aging},\n\tvolume = {19},\n\tissn = {1474-9726},\n\tdoi = {10.1111/acel.13156},\n\tabstract = {The aging process is characterized by a chronic, low-grade inflammatory state, termed "inflammaging." It has been suggested that macrophage activation plays a key role in the induction and maintenance of this state. In the present study, we aimed to elucidate the mechanisms responsible for aging-associated changes in the myeloid compartment of mice. The aging phenotype, characterized by elevated cytokine production, was associated with a dysfunction of the hypothalamic-pituitary-adrenal (HPA) axis and diminished serum corticosteroid levels. In particular, the concentration of corticosterone, the major active glucocorticoid in rodents, was decreased. This could be explained by an impaired expression and activity of 11β-hydroxysteroid dehydrogenase type 1 (11β-HSD1), an enzyme that determines the extent of cellular glucocorticoid responses by reducing the corticosteroids cortisone/11-dehydrocorticosterone to their active forms cortisol/corticosterone, in aged macrophages and peripheral leukocytes. These changes were accompanied by a downregulation of the glucocorticoid receptor target gene glucocorticoid-induced leucine zipper (GILZ) in vitro and in vivo. Since GILZ plays a central role in macrophage activation, we hypothesized that the loss of GILZ contributed to the process of macroph-aging. The phenotype of macrophages from aged mice was indeed mimicked in young GILZ knockout mice. In summary, the current study provides insight into the role of glucocorticoid metabolism and GILZ regulation during aging.},\n\tlanguage = {eng},\n\tnumber = {6},\n\tjournal = {Aging Cell},\n\tauthor = {Valbuena Perez, Jenny Vanessa and Linnenberger, Rebecca and Dembek, Anna and Bruscoli, Stefano and Riccardi, Carlo and Schulz, Marcel H. and Meyer, Markus R. and Kiemer, Alexandra K. and Hoppstädter, Jessica},\n\tmonth = jun,\n\tyear = {2020},\n\tpmid = {32463582},\n\tpmcid = {PMC7294787},\n\tkeywords = {Age Factors, Animals, cellular immunology, cytokines, Cytokines, Disease Models, Animal, Glucocorticoids, inflammation, Inflammation, Macrophage Activation, Macrophages, Peritoneal, Mice, Mice, Inbred C57BL, Mice, Knockout, mononuclear cell, mouse models, reactive oxygen species, Reactive Oxygen Species, steroid control of aging, TSC22D3},\n\tpages = {e13156},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/5RQQ6X7Q/Valbuena Perez et al. - 2020 - Altered glucocorticoid metabolism represents a fea.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The aging process is characterized by a chronic, low-grade inflammatory state, termed \"inflammaging.\" It has been suggested that macrophage activation plays a key role in the induction and maintenance of this state. In the present study, we aimed to elucidate the mechanisms responsible for aging-associated changes in the myeloid compartment of mice. The aging phenotype, characterized by elevated cytokine production, was associated with a dysfunction of the hypothalamic-pituitary-adrenal (HPA) axis and diminished serum corticosteroid levels. In particular, the concentration of corticosterone, the major active glucocorticoid in rodents, was decreased. This could be explained by an impaired expression and activity of 11β-hydroxysteroid dehydrogenase type 1 (11β-HSD1), an enzyme that determines the extent of cellular glucocorticoid responses by reducing the corticosteroids cortisone/11-dehydrocorticosterone to their active forms cortisol/corticosterone, in aged macrophages and peripheral leukocytes. These changes were accompanied by a downregulation of the glucocorticoid receptor target gene glucocorticoid-induced leucine zipper (GILZ) in vitro and in vivo. Since GILZ plays a central role in macrophage activation, we hypothesized that the loss of GILZ contributed to the process of macroph-aging. The phenotype of macrophages from aged mice was indeed mimicked in young GILZ knockout mice. In summary, the current study provides insight into the role of glucocorticoid metabolism and GILZ regulation during aging.\n
\n\n\n
\n\n\n
\n \n\n \n \n Nina Baumgarten, Dennis Hecker, Sivarajan Karunanithi, Florian Schmidt, Markus List, & Marcel H. Schulz.\n\n\n \n \n \n \n EpiRegio: analysis and retrieval of regulatory elements linked to genes.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 48(W1): W193–W199. July 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{baumgarten_epiregio_2020,\n\ttitle = {{EpiRegio}: analysis and retrieval of regulatory elements linked to genes},\n\tvolume = {48},\n\tissn = {1362-4962},\n\tshorttitle = {{EpiRegio}},\n\tdoi = {10.1093/nar/gkaa382},\n\tabstract = {A current challenge in genomics is to interpret non-coding regions and their role in transcriptional regulation of possibly distant target genes. Genome-wide association studies show that a large part of genomic variants are found in those non-coding regions, but their mechanisms of gene regulation are often unknown. An additional challenge is to reliably identify the target genes of the regulatory regions, which is an essential step in understanding their impact on gene expression. Here we present the EpiRegio web server, a resource of regulatory elements (REMs). REMs are genomic regions that exhibit variations in their chromatin accessibility profile associated with changes in expression of their target genes. EpiRegio incorporates both epigenomic and gene expression data for various human primary cell types and tissues, providing an integrated view of REMs in the genome. Our web server allows the analysis of genes and their associated REMs, including the REM's activity and its estimated cell type-specific contribution to its target gene's expression. Further, it is possible to explore genomic regions for their regulatory potential, investigate overlapping REMs and by that the dissection of regions of large epigenomic complexity. EpiRegio allows programmatic access through a REST API and is freely available at https://epiregio.de/.},\n\tlanguage = {eng},\n\tnumber = {W1},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Baumgarten, Nina and Hecker, Dennis and Karunanithi, Sivarajan and Schmidt, Florian and List, Markus and Schulz, Marcel H.},\n\tmonth = jul,\n\tyear = {2020},\n\tpmid = {32459338},\n\tpmcid = {PMC7319550},\n\tkeywords = {Chromatin Immunoprecipitation Sequencing, Disease, Gene Expression Regulation, Humans, Regulatory Elements, Transcriptional, Software, Transcription Factors},\n\tpages = {W193--W199},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/MZLWLINU/Baumgarten et al. - 2020 - EpiRegio analysis and retrieval of regulatory ele.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n A current challenge in genomics is to interpret non-coding regions and their role in transcriptional regulation of possibly distant target genes. Genome-wide association studies show that a large part of genomic variants are found in those non-coding regions, but their mechanisms of gene regulation are often unknown. An additional challenge is to reliably identify the target genes of the regulatory regions, which is an essential step in understanding their impact on gene expression. Here we present the EpiRegio web server, a resource of regulatory elements (REMs). REMs are genomic regions that exhibit variations in their chromatin accessibility profile associated with changes in expression of their target genes. EpiRegio incorporates both epigenomic and gene expression data for various human primary cell types and tissues, providing an integrated view of REMs in the genome. Our web server allows the analysis of genes and their associated REMs, including the REM's activity and its estimated cell type-specific contribution to its target gene's expression. Further, it is possible to explore genomic regions for their regulatory potential, investigate overlapping REMs and by that the dissection of regions of large epigenomic complexity. EpiRegio allows programmatic access through a REST API and is freely available at https://epiregio.de/.\n
\n\n\n
\n\n\n
\n \n\n \n \n Sivarajan Karunanithi, Vidya Oruganti, Raphael Wijn, Franziska Drews, Miriam Cheaib, Karl Nordström, Martin Simon, & Marcel H. Schulz.\n\n\n \n \n \n \n Feeding exogenous dsRNA interferes with endogenous sRNA accumulation in Paramecium.\n \n \n \n\n\n \n\n\n\n DNA research: an international journal for rapid publication of reports on genes and genomes, 27(1): dsaa005. February 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{karunanithi_feeding_2020,\n\ttitle = {Feeding exogenous {dsRNA} interferes with endogenous {sRNA} accumulation in {Paramecium}},\n\tvolume = {27},\n\tissn = {1756-1663},\n\tdoi = {10.1093/dnares/dsaa005},\n\tabstract = {Supply of exogenous dsRNA (exo-dsRNA), either by injection or by feeding, is a fast and powerful alternative to classical knockout studies. The biotechnical potential of feeding techniques is evident from the numerous studies focusing on oral administration of dsRNA to control pests and viral infection in crops/animal farming. We aimed to dissect the direct and indirect effects of exo-dsRNA feeding on the endogenous short interfering RNA (endo-siRNA) populations of the free-living ciliate Paramecium. We introduced dsRNA fragments against Dicer1 (DCR1), involved in RNA interference (RNAi) against exo- and few endo-siRNAs, and an RNAi unrelated gene, ND169. Any feeding, even the control dsRNA, diminishes genome wide the accumulation of endo-siRNAs and mRNAs. This cannot be explained by direct off-target effects and suggests mechanistic overlaps of the exo- and endo-RNAi mechanisms. Nevertheless, we observe a stronger down-regulation of mRNAs in DCR1 feeding compared with ND169 knockdown. This is likely due to the direct involvement of DCR1 in endo-siRNA accumulation. We further observed a cis-regulatory effect on mRNAs that overlap with phased endo-siRNAs. This interference of exo-dsRNA with endo-siRNAs warrants further investigations into secondary effects in target species/consumers, risk assessment of dsRNA feeding applications, and environmental pollution with dsRNA.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {DNA research: an international journal for rapid publication of reports on genes and genomes},\n\tauthor = {Karunanithi, Sivarajan and Oruganti, Vidya and de Wijn, Raphael and Drews, Franziska and Cheaib, Miriam and Nordström, Karl and Simon, Martin and Schulz, Marcel H.},\n\tmonth = feb,\n\tyear = {2020},\n\tpmid = {32339224},\n\tpmcid = {PMC7315353},\n\tkeywords = {dsRNA feeding, environmental RNAi, off-target, Paramecium, Ribonuclease III, RNA Interference, RNA, Double-Stranded, RNA, Messenger, RNA, Small Interfering, siRNA},\n\tpages = {dsaa005},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/5WD2DENY/Karunanithi et al. - 2020 - Feeding exogenous dsRNA interferes with endogenous.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Supply of exogenous dsRNA (exo-dsRNA), either by injection or by feeding, is a fast and powerful alternative to classical knockout studies. The biotechnical potential of feeding techniques is evident from the numerous studies focusing on oral administration of dsRNA to control pests and viral infection in crops/animal farming. We aimed to dissect the direct and indirect effects of exo-dsRNA feeding on the endogenous short interfering RNA (endo-siRNA) populations of the free-living ciliate Paramecium. We introduced dsRNA fragments against Dicer1 (DCR1), involved in RNA interference (RNAi) against exo- and few endo-siRNAs, and an RNAi unrelated gene, ND169. Any feeding, even the control dsRNA, diminishes genome wide the accumulation of endo-siRNAs and mRNAs. This cannot be explained by direct off-target effects and suggests mechanistic overlaps of the exo- and endo-RNAi mechanisms. Nevertheless, we observe a stronger down-regulation of mRNAs in DCR1 feeding compared with ND169 knockdown. This is likely due to the direct involvement of DCR1 in endo-siRNA accumulation. We further observed a cis-regulatory effect on mRNAs that overlap with phased endo-siRNAs. This interference of exo-dsRNA with endo-siRNAs warrants further investigations into secondary effects in target species/consumers, risk assessment of dsRNA feeding applications, and environmental pollution with dsRNA.\n
\n\n\n
\n\n\n
\n \n\n \n \n Beatrice Pflüger-Müller, James A. Oo, Jan Heering, Timothy Warwick, Ewgenij Proschak, Stefan Günther, Mario Looso, Flávia Rezende, Christian Fork, Gerd Geisslinger, Dominique Thomas, Robert Gurke, Dieter Steinhilber, Marcel Schulz, Matthias S. Leisegang, & Ralf P. Brandes.\n\n\n \n \n \n \n The endocannabinoid anandamide has an anti-inflammatory effect on CCL2 expression in vascular smooth muscle cells.\n \n \n \n\n\n \n\n\n\n Basic Research in Cardiology, 115(3): 34. April 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{pfluger-muller_endocannabinoid_2020,\n\ttitle = {The endocannabinoid anandamide has an anti-inflammatory effect on {CCL2} expression in vascular smooth muscle cells},\n\tvolume = {115},\n\tissn = {1435-1803},\n\tdoi = {10.1007/s00395-020-0793-3},\n\tabstract = {Endocannabinoids are important lipid-signaling mediators. Both protective and deleterious effects of endocannabinoids in the cardiovascular system have been reported but the mechanistic basis for these contradicting observations is unclear. We set out to identify anti-inflammatory mechanisms of endocannabinoids in the murine aorta and in human vascular smooth muscle cells (hVSMC). In response to combined stimulation with cytokines, IL-1β and TNFα, the murine aorta released several endocannabinoids, with anandamide (AEA) levels being the most significantly increased. AEA pretreatment had profound effects on cytokine-induced gene expression in hVSMC and murine aorta. As revealed by RNA-Seq analysis, the induction of a subset of 21 inflammatory target genes, including the important cytokine CCL2 was blocked by AEA. This effect was not mediated through AEA-dependent interference of the AP-1 or NF-κB pathways but rather through an epigenetic mechanism. In the presence of AEA, ATAC-Seq analysis and chromatin-immunoprecipitations revealed that CCL2 induction was blocked due to increased levels of H3K27me3 and a decrease of H3K27ac leading to compacted chromatin structure in the CCL2 promoter. These effects were mediated by recruitment of HDAC4 and the nuclear corepressor NCoR1 to the CCL2 promoter. This study therefore establishes a novel anti-inflammatory mechanism for the endogenous endocannabinoid AEA in vascular smooth muscle cells. Furthermore, this work provides a link between endogenous endocannabinoid signaling and epigenetic regulation.},\n\tlanguage = {eng},\n\tnumber = {3},\n\tjournal = {Basic Research in Cardiology},\n\tauthor = {Pflüger-Müller, Beatrice and Oo, James A. and Heering, Jan and Warwick, Timothy and Proschak, Ewgenij and Günther, Stefan and Looso, Mario and Rezende, Flávia and Fork, Christian and Geisslinger, Gerd and Thomas, Dominique and Gurke, Robert and Steinhilber, Dieter and Schulz, Marcel and Leisegang, Matthias S. and Brandes, Ralf P.},\n\tmonth = apr,\n\tyear = {2020},\n\tpmid = {32323032},\n\tpmcid = {PMC7176595},\n\tkeywords = {Anandamide, Animals, Anti-Inflammatory Agents, Arachidonic Acids, CCL2, Chemokine CCL2, Endocannabinoids, Epigenesis, Genetic, HDAC4, Humans, Inflammation, Mice, Muscle, Smooth, Vascular, NCoR1, Polyunsaturated Alkamides, Signal Transduction},\n\tpages = {34},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/WZ5FF4UY/Pflüger-Müller et al. - 2020 - The endocannabinoid anandamide has an anti-inflamm.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Endocannabinoids are important lipid-signaling mediators. Both protective and deleterious effects of endocannabinoids in the cardiovascular system have been reported but the mechanistic basis for these contradicting observations is unclear. We set out to identify anti-inflammatory mechanisms of endocannabinoids in the murine aorta and in human vascular smooth muscle cells (hVSMC). In response to combined stimulation with cytokines, IL-1β and TNFα, the murine aorta released several endocannabinoids, with anandamide (AEA) levels being the most significantly increased. AEA pretreatment had profound effects on cytokine-induced gene expression in hVSMC and murine aorta. As revealed by RNA-Seq analysis, the induction of a subset of 21 inflammatory target genes, including the important cytokine CCL2 was blocked by AEA. This effect was not mediated through AEA-dependent interference of the AP-1 or NF-κB pathways but rather through an epigenetic mechanism. In the presence of AEA, ATAC-Seq analysis and chromatin-immunoprecipitations revealed that CCL2 induction was blocked due to increased levels of H3K27me3 and a decrease of H3K27ac leading to compacted chromatin structure in the CCL2 promoter. These effects were mediated by recruitment of HDAC4 and the nuclear corepressor NCoR1 to the CCL2 promoter. This study therefore establishes a novel anti-inflammatory mechanism for the endogenous endocannabinoid AEA in vascular smooth muscle cells. Furthermore, this work provides a link between endogenous endocannabinoid signaling and epigenetic regulation.\n
\n\n\n
\n\n\n
\n \n\n \n \n Shounak Chakraborty, Stefan Canzar, Tobias Marschall, & Marcel H. Schulz.\n\n\n \n \n \n \n Chromatyping: Reconstructing Nucleosome Profiles from NOMe Sequencing Data.\n \n \n \n\n\n \n\n\n\n Journal of Computational Biology: A Journal of Computational Molecular Cell Biology, 27(3): 330–341. March 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{chakraborty_chromatyping_2020,\n\ttitle = {Chromatyping: {Reconstructing} {Nucleosome} {Profiles} from {NOMe} {Sequencing} {Data}},\n\tvolume = {27},\n\tissn = {1557-8666},\n\tshorttitle = {Chromatyping},\n\tdoi = {10.1089/cmb.2019.0457},\n\tabstract = {Measuring nucleosome positioning in cells is crucial for the analysis of epigenetic gene regulation. Reconstruction of nucleosome profiles of individual cells or subpopulations of cells remains challenging because most genome-wide assays measure nucleosome positioning and DNA accessibility for thousands of cells using bulk sequencing. In this study we use characteristics of the NOMe (nucleosome occupancy and methylation)-sequencing assay to derive a new approach, called ChromaClique, for deconvolution of different nucleosome profiles (chromatypes) from cell subpopulations of one NOMe-seq measurement. ChromaClique uses a maximal clique enumeration algorithm on a newly defined NOMe read graph that is able to group reads according to their nucleosome profiles. We show that the edge probabilities of that graph can be efficiently computed using hidden Markov models. We demonstrate using simulated data that ChromaClique is more accurate than a related method and scales favorably, allowing genome-wide analyses of chromatypes in cell subpopulations.},\n\tlanguage = {eng},\n\tnumber = {3},\n\tjournal = {Journal of Computational Biology: A Journal of Computational Molecular Cell Biology},\n\tauthor = {Chakraborty, Shounak and Canzar, Stefan and Marschall, Tobias and Schulz, Marcel H.},\n\tmonth = mar,\n\tyear = {2020},\n\tpmid = {32160036},\n\tkeywords = {Algorithms, Computational Biology, CpG Islands, DNA Methylation, Epigenesis, Genetic, epigenetics, Gene Expression Regulation, HMMs, Humans, Markov Chains, max clique enumeration, NOMe-seq, Nucleosomes, Promoter Regions, Genetic, Sequence Analysis, DNA},\n\tpages = {330--341},\n}\n\n
\n
\n\n\n
\n Measuring nucleosome positioning in cells is crucial for the analysis of epigenetic gene regulation. Reconstruction of nucleosome profiles of individual cells or subpopulations of cells remains challenging because most genome-wide assays measure nucleosome positioning and DNA accessibility for thousands of cells using bulk sequencing. In this study we use characteristics of the NOMe (nucleosome occupancy and methylation)-sequencing assay to derive a new approach, called ChromaClique, for deconvolution of different nucleosome profiles (chromatypes) from cell subpopulations of one NOMe-seq measurement. ChromaClique uses a maximal clique enumeration algorithm on a newly defined NOMe read graph that is able to group reads according to their nucleosome profiles. We show that the edge probabilities of that graph can be efficiently computed using hidden Markov models. We demonstrate using simulated data that ChromaClique is more accurate than a related method and scales favorably, allowing genome-wide analyses of chromatypes in cell subpopulations.\n
\n\n\n
\n\n\n
\n \n\n \n \n Vanessa Königs, Camila Oliveira Freitas Machado, Benjamin Arnold, Nicole Blümel, Anfisa Solovyeva, Sinah Löbbert, Michal Schafranek, Igor Ruiz De Los Mozos, Ilka Wittig, Francois McNicoll, Marcel H. Schulz, & Michaela Müller-McNicoll.\n\n\n \n \n \n \n SRSF7 maintains its homeostasis through the expression of Split-ORFs and nuclear body assembly.\n \n \n \n\n\n \n\n\n\n Nature Structural & Molecular Biology, 27(3): 260–273. March 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{konigs_srsf7_2020,\n\ttitle = {{SRSF7} maintains its homeostasis through the expression of {Split}-{ORFs} and nuclear body assembly},\n\tvolume = {27},\n\tissn = {1545-9985},\n\tdoi = {10.1038/s41594-020-0385-9},\n\tabstract = {SRSF7 is an essential RNA-binding protein whose misexpression promotes cancer. Here, we describe how SRSF7 maintains its protein homeostasis in murine P19 cells using an intricate negative feedback mechanism. SRSF7 binding to its premessenger RNA promotes inclusion of a poison cassette exon and transcript degradation via nonsense-mediated decay (NMD). However, elevated SRSF7 levels inhibit NMD and promote translation of two protein halves, termed Split-ORFs, from the bicistronic SRSF7-PCE transcript. The first half acts as dominant-negative isoform suppressing poison cassette exon inclusion and instead promoting the retention of flanking introns containing repeated SRSF7 binding sites. Massive SRSF7 binding to these sites and its oligomerization promote the assembly of large nuclear bodies, which sequester SRSF7 transcripts at their transcription site, preventing their export and restoring normal SRSF7 protein levels. We further show that hundreds of human and mouse NMD targets, especially RNA-binding proteins, encode potential Split-ORFs, some of which are expressed under specific cellular conditions.},\n\tlanguage = {eng},\n\tnumber = {3},\n\tjournal = {Nature Structural \\& Molecular Biology},\n\tauthor = {Königs, Vanessa and de Oliveira Freitas Machado, Camila and Arnold, Benjamin and Blümel, Nicole and Solovyeva, Anfisa and Löbbert, Sinah and Schafranek, Michal and Ruiz De Los Mozos, Igor and Wittig, Ilka and McNicoll, Francois and Schulz, Marcel H. and Müller-McNicoll, Michaela},\n\tmonth = mar,\n\tyear = {2020},\n\tpmid = {32123389},\n\tpmcid = {PMC7096898},\n\tkeywords = {Amino Acid Sequence, Animals, Base Sequence, Binding Sites, Cell Line, Tumor, Cell Nucleus, Exons, Gene Expression Regulation, Homeostasis, Mice, Mouse Embryonic Stem Cells, Neoplasm Proteins, Nonsense Mediated mRNA Decay, Open Reading Frames, Protein Binding, Protein Biosynthesis, RNA Precursors, RNA-Binding Proteins, Serine-Arginine Splicing Factors, Transcription, Genetic},\n\tpages = {260--273},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/B3M4P4UM/Königs et al. - 2020 - SRSF7 maintains its homeostasis through the expres.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n SRSF7 is an essential RNA-binding protein whose misexpression promotes cancer. Here, we describe how SRSF7 maintains its protein homeostasis in murine P19 cells using an intricate negative feedback mechanism. SRSF7 binding to its premessenger RNA promotes inclusion of a poison cassette exon and transcript degradation via nonsense-mediated decay (NMD). However, elevated SRSF7 levels inhibit NMD and promote translation of two protein halves, termed Split-ORFs, from the bicistronic SRSF7-PCE transcript. The first half acts as dominant-negative isoform suppressing poison cassette exon inclusion and instead promoting the retention of flanking introns containing repeated SRSF7 binding sites. Massive SRSF7 binding to these sites and its oligomerization promote the assembly of large nuclear bodies, which sequester SRSF7 transcripts at their transcription site, preventing their export and restoring normal SRSF7 protein levels. We further show that hundreds of human and mouse NMD targets, especially RNA-binding proteins, encode potential Split-ORFs, some of which are expressed under specific cellular conditions.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, Fabian Kern, & Marcel H. Schulz.\n\n\n \n \n \n \n Integrative prediction of gene expression with chromatin accessibility and conformation data.\n \n \n \n\n\n \n\n\n\n Epigenetics & Chromatin, 13(1): 4. February 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_integrative_2020,\n\ttitle = {Integrative prediction of gene expression with chromatin accessibility and conformation data},\n\tvolume = {13},\n\tissn = {1756-8935},\n\tdoi = {10.1186/s13072-020-0327-0},\n\tabstract = {BACKGROUND: Enhancers play a fundamental role in orchestrating cell state and development. Although several methods have been developed to identify enhancers, linking them to their target genes is still an open problem. Several theories have been proposed on the functional mechanisms of enhancers, which triggered the development of various methods to infer promoter-enhancer interactions (PEIs). The advancement of high-throughput techniques describing the three-dimensional organization of the chromatin, paved the way to pinpoint long-range PEIs. Here we investigated whether including PEIs in computational models for the prediction of gene expression improves performance and interpretability.\nRESULTS: We have extended our [Formula: see text] framework to include DNA contacts deduced from chromatin conformation capture experiments and compared various methods to determine PEIs using predictive modelling of gene expression from chromatin accessibility data and predicted transcription factor (TF) motif data. We designed a novel machine learning approach that allows the prioritization of TFs binding to distal loop and promoter regions with respect to their importance for gene expression regulation. Our analysis revealed a set of core TFs that are part of enhancer-promoter loops involving YY1 in different cell lines.\nCONCLUSION: We present a novel approach that can be used to prioritize TFs involved in distal and promoter-proximal regulatory events by integrating chromatin accessibility, conformation, and gene expression data. We show that the integration of chromatin conformation data can improve gene expression prediction and aids model interpretability.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Epigenetics \\& Chromatin},\n\tauthor = {Schmidt, Florian and Kern, Fabian and Schulz, Marcel H.},\n\tmonth = feb,\n\tyear = {2020},\n\tpmid = {32029002},\n\tpmcid = {PMC7003490},\n\tkeywords = {Binding Sites, Chromatin, Chromatin accessibility, Chromatin Assembly and Disassembly, Chromatin conformation, DNase1-seq, Enhancer Elements, Genetic, Gene expression prediction, Gene regulation, Genomics, HCT116 Cells, HeLa Cells, HiC, HiChIP, Human Umbilical Vein Endothelial Cells, Humans, Jurkat Cells, K562 Cells, Machine learning, Machine Learning, Protein Binding, Transcription Factors},\n\tpages = {4},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/AB9CX5IG/Schmidt et al. - 2020 - Integrative prediction of gene expression with chr.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Enhancers play a fundamental role in orchestrating cell state and development. Although several methods have been developed to identify enhancers, linking them to their target genes is still an open problem. Several theories have been proposed on the functional mechanisms of enhancers, which triggered the development of various methods to infer promoter-enhancer interactions (PEIs). The advancement of high-throughput techniques describing the three-dimensional organization of the chromatin, paved the way to pinpoint long-range PEIs. Here we investigated whether including PEIs in computational models for the prediction of gene expression improves performance and interpretability. RESULTS: We have extended our [Formula: see text] framework to include DNA contacts deduced from chromatin conformation capture experiments and compared various methods to determine PEIs using predictive modelling of gene expression from chromatin accessibility data and predicted transcription factor (TF) motif data. We designed a novel machine learning approach that allows the prioritization of TFs binding to distal loop and promoter regions with respect to their importance for gene expression regulation. Our analysis revealed a set of core TFs that are part of enhancer-promoter loops involving YY1 in different cell lines. CONCLUSION: We present a novel approach that can be used to prioritize TFs involved in distal and promoter-proximal regulatory events by integrating chromatin accessibility, conformation, and gene expression data. We show that the integration of chromatin conformation data can improve gene expression prediction and aids model interpretability.\n
\n\n\n
\n\n\n
\n \n\n \n \n Stefanie Gier, Martin Simon, Gilles Gasparoni, Salem Khalifa, Marcel H. Schulz, Manfred J. Schmitt, & Frank Breinig.\n\n\n \n \n \n \n Yeast Viral Killer Toxin K1 Induces Specific Host Cell Adaptions via Intrinsic Selection Pressure.\n \n \n \n\n\n \n\n\n\n Applied and Environmental Microbiology, 86(4): e02446–19. February 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{gier_yeast_2020,\n\ttitle = {Yeast {Viral} {Killer} {Toxin} {K1} {Induces} {Specific} {Host} {Cell} {Adaptions} via {Intrinsic} {Selection} {Pressure}},\n\tvolume = {86},\n\tissn = {1098-5336},\n\tdoi = {10.1128/AEM.02446-19},\n\tabstract = {The killer phenomenon in yeast (Saccharomyces cerevisiae) not only provides the opportunity to study host-virus interactions in a eukaryotic model but also represents a powerful tool to analyze potential coadaptional events and the role of killer yeast in biological diversity. Although undoubtedly having a crucial impact on the abundance and expression of the killer phenotype in killer-yeast harboring communities, the influence of a particular toxin on its producing host cell has not been addressed sufficiently. In this study, we describe a model system of two K1 killer yeast strains with distinct phenotypical differences pointing to substantial selection pressure in response to the toxin secretion level. Transcriptome and lipidome analyses revealed specific and intrinsic host cell adaptions dependent on the amount of K1 toxin produced. High basal expression of genes coding for osmoprotectants and stress-responsive proteins in a killer yeast strain secreting larger amounts of active K1 toxin implies a generally increased stress tolerance. Moreover, the data suggest that immunity of the host cell against its own toxin is essential for the balanced virus-host interplay providing valuable hints to elucidate the molecular mechanisms underlying K1 immunity and implicating an evolutionarily conserved role for toxin immunity in natural yeast populations.IMPORTANCE The killer phenotype in Saccharomyces cerevisiae relies on the cytoplasmic persistence of two RNA viruses. In contrast to bacterial toxin producers, killer yeasts necessitate a specific immunity mechanism against their own toxin because they bear the same receptor populations as sensitive cells. Although the killer phenomenon is highly abundant and has a crucial impact on the structure of yeast communities, the influence of a particular toxin on its host cell has been barely addressed. In our study, we used two derivatives secreting different amount of the killer toxin K1 to analyze potential coadaptional events in this particular host/virus system. Our data underline the dependency of the host cell's ability to cope with extracellular toxin molecules and intracellular K1 molecules provided by the virus. Therefore, this research significantly advances the current understanding of the evolutionarily conserved role of this molecular machinery as an intrinsic selection pressure in yeast populations.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {Applied and Environmental Microbiology},\n\tauthor = {Gier, Stefanie and Simon, Martin and Gasparoni, Gilles and Khalifa, Salem and Schulz, Marcel H. and Schmitt, Manfred J. and Breinig, Frank},\n\tmonth = feb,\n\tyear = {2020},\n\tpmid = {31811035},\n\tpmcid = {PMC6997729},\n\tkeywords = {Host Microbial Interactions, K1, Killer Factors, Yeast, killer toxin, Phenotype, RNA Viruses, Saccharomyces cerevisiae, Selection, Genetic, transcriptome, yeast viral toxin},\n\tpages = {e02446--19},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/R7ML5R6S/Gier et al. - 2020 - Yeast Viral Killer Toxin K1 Induces Specific Host .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The killer phenomenon in yeast (Saccharomyces cerevisiae) not only provides the opportunity to study host-virus interactions in a eukaryotic model but also represents a powerful tool to analyze potential coadaptional events and the role of killer yeast in biological diversity. Although undoubtedly having a crucial impact on the abundance and expression of the killer phenotype in killer-yeast harboring communities, the influence of a particular toxin on its producing host cell has not been addressed sufficiently. In this study, we describe a model system of two K1 killer yeast strains with distinct phenotypical differences pointing to substantial selection pressure in response to the toxin secretion level. Transcriptome and lipidome analyses revealed specific and intrinsic host cell adaptions dependent on the amount of K1 toxin produced. High basal expression of genes coding for osmoprotectants and stress-responsive proteins in a killer yeast strain secreting larger amounts of active K1 toxin implies a generally increased stress tolerance. Moreover, the data suggest that immunity of the host cell against its own toxin is essential for the balanced virus-host interplay providing valuable hints to elucidate the molecular mechanisms underlying K1 immunity and implicating an evolutionarily conserved role for toxin immunity in natural yeast populations.IMPORTANCE The killer phenotype in Saccharomyces cerevisiae relies on the cytoplasmic persistence of two RNA viruses. In contrast to bacterial toxin producers, killer yeasts necessitate a specific immunity mechanism against their own toxin because they bear the same receptor populations as sensitive cells. Although the killer phenomenon is highly abundant and has a crucial impact on the structure of yeast communities, the influence of a particular toxin on its host cell has been barely addressed. In our study, we used two derivatives secreting different amount of the killer toxin K1 to analyze potential coadaptional events in this particular host/virus system. Our data underline the dependency of the host cell's ability to cope with extracellular toxin molecules and intracellular K1 molecules provided by the virus. Therefore, this research significantly advances the current understanding of the evolutionarily conserved role of this molecular machinery as an intrinsic selection pressure in yeast populations.\n
\n\n\n
\n\n\n
\n \n\n \n \n Nina Baumgarten, Florian Schmidt, & Marcel H. Schulz.\n\n\n \n \n \n \n Improved linking of motifs to their TFs using domain information.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 36(6): 1655–1662. March 2020.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{baumgarten_improved_2020,\n\ttitle = {Improved linking of motifs to their {TFs} using domain information},\n\tvolume = {36},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/btz855},\n\tabstract = {MOTIVATION: A central aim of molecular biology is to identify mechanisms of transcriptional regulation. Transcription factors (TFs), which are DNA-binding proteins, are highly involved in these processes, thus a crucial information is to know where TFs interact with DNA and to be aware of the TFs' DNA-binding motifs. For that reason, computational tools exist that link DNA-binding motifs to TFs either without sequence information or based on TF-associated sequences, e.g. identified via a chromatin immunoprecipitation followed by sequencing (ChIP-seq) experiment.In this paper, we present MASSIF, a novel method to improve the performance of existing tools that link motifs to TFs relying on TF-associated sequences. MASSIF is based on the idea that a DNA-binding motif, which is correctly linked to a TF, should be assigned to a DNA-binding domain (DBD) similar to that of the mapped TF. Because DNA-binding motifs are in general not linked to DBDs, it is not possible to compare the DBD of a TF and the motif directly. Instead we created a DBD collection, which consist of TFs with a known DBD and an associated motif. This collection enables us to evaluate how likely it is that a linked motif and a TF of interest are associated to the same DBD. We named this similarity measure domain score, and represent it as a P-value. We developed two different ways to improve the performance of existing tools that link motifs to TFs based on TF-associated sequences: (i) using meta-analysis to combine P-values from one or several of these tools with the P-value of the domain score and (ii) filter unlikely motifs based on the domain score.\nRESULTS: We demonstrate the functionality of MASSIF on several human ChIP-seq datasets, using either motifs from the HOCOMOCO database or de novo identified ones as input motifs. In addition, we show that both variants of our method improve the performance of tools that link motifs to TFs based on TF-associated sequences significantly independent of the considered DBD type.\nAVAILABILITY AND IMPLEMENTATION: MASSIF is freely available online at https://github.com/SchulzLab/MASSIF.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {6},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Baumgarten, Nina and Schmidt, Florian and Schulz, Marcel H.},\n\tmonth = mar,\n\tyear = {2020},\n\tpmid = {31742324},\n\tpmcid = {PMC7703792},\n\tkeywords = {Binding Sites, Chromatin Immunoprecipitation, Computational Biology, DNA-Binding Proteins, Nucleotide Motifs, Protein Binding, Sequence Analysis, DNA, Transcription Factors},\n\tpages = {1655--1662},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/5HVC29YI/Baumgarten et al. - 2020 - Improved linking of motifs to their TFs using doma.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: A central aim of molecular biology is to identify mechanisms of transcriptional regulation. Transcription factors (TFs), which are DNA-binding proteins, are highly involved in these processes, thus a crucial information is to know where TFs interact with DNA and to be aware of the TFs' DNA-binding motifs. For that reason, computational tools exist that link DNA-binding motifs to TFs either without sequence information or based on TF-associated sequences, e.g. identified via a chromatin immunoprecipitation followed by sequencing (ChIP-seq) experiment.In this paper, we present MASSIF, a novel method to improve the performance of existing tools that link motifs to TFs relying on TF-associated sequences. MASSIF is based on the idea that a DNA-binding motif, which is correctly linked to a TF, should be assigned to a DNA-binding domain (DBD) similar to that of the mapped TF. Because DNA-binding motifs are in general not linked to DBDs, it is not possible to compare the DBD of a TF and the motif directly. Instead we created a DBD collection, which consist of TFs with a known DBD and an associated motif. This collection enables us to evaluate how likely it is that a linked motif and a TF of interest are associated to the same DBD. We named this similarity measure domain score, and represent it as a P-value. We developed two different ways to improve the performance of existing tools that link motifs to TFs based on TF-associated sequences: (i) using meta-analysis to combine P-values from one or several of these tools with the P-value of the domain score and (ii) filter unlikely motifs based on the domain score. RESULTS: We demonstrate the functionality of MASSIF on several human ChIP-seq datasets, using either motifs from the HOCOMOCO database or de novo identified ones as input motifs. In addition, we show that both variants of our method improve the performance of tools that link motifs to TFs based on TF-associated sequences significantly independent of the considered DBD type. AVAILABILITY AND IMPLEMENTATION: MASSIF is freely available online at https://github.com/SchulzLab/MASSIF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Mikko Rautiainen, Dilip A Durai, Ying Chen, Lixia Xin, Hwee Meng Low, Jonathan Göke, Tobias Marschall, & Marcel H. Schulz.\n\n\n \n \n \n \n \n AERON: Transcript quantification and gene-fusion detection using long reads.\n \n \n \n \n\n\n \n\n\n\n Preprint. January 2020.\n \n\n\n\n
\n\n\n\n \n \n \"AERON:Paper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{rautiainen_aeron_2020,\n\tjournal = {Preprint},\n\ttitle = {{AERON}: {Transcript} quantification and gene-fusion detection using long reads},\n\tshorttitle = {{AERON}},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2020.01.27.921338},\n\tabstract = {Abstract\n          Single-molecule sequencing technologies have the potential to improve measurement and analysis of long RNA molecules expressed in cells. However, analysis of error-prone long RNA reads is a current challenge. We present AERON for the estimation of transcript expression and prediction of gene-fusion events. AERON uses an efficient read-to-graph alignment algorithm to obtain accurate estimates for noisy reads. We demonstrate AERON to yield accurate expression estimates on simulated and real datasets. It is the first method to reliably call gene-fusion events from long RNA reads. Sequencing the K562 transcriptome, we used AERON and found known as well as novel gene-fusion events.},\n\tlanguage = {en},\n\turldate = {2023-01-09},\n\tinstitution = {Bioinformatics},\n\tauthor = {Rautiainen, Mikko and Durai, Dilip A and Chen, Ying and Xin, Lixia and Low, Hwee Meng and Göke, Jonathan and Marschall, Tobias and Schulz, Marcel H.},\n\tmonth = jan,\n\tyear = {2020},\n\tdoi = {10.1101/2020.01.27.921338},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/DRTEMPI7/Rautiainen et al. - 2020 - AERON Transcript quantification and gene-fusion d.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Abstract Single-molecule sequencing technologies have the potential to improve measurement and analysis of long RNA molecules expressed in cells. However, analysis of error-prone long RNA reads is a current challenge. We present AERON for the estimation of transcript expression and prediction of gene-fusion events. AERON uses an efficient read-to-graph alignment algorithm to obtain accurate estimates for noisy reads. We demonstrate AERON to yield accurate expression estimates on simulated and real datasets. It is the first method to reliably call gene-fusion events from long RNA reads. Sequencing the K562 transcriptome, we used AERON and found known as well as novel gene-fusion events.\n
\n\n\n
\n\n\n
\n \n\n \n \n Jan Grau, Florian Schmidt, & Marcel H. Schulz.\n\n\n \n \n \n \n \n Widespread effects of DNA methylation and intra-motif dependencies revealed by novel transcription factor binding models.\n \n \n \n \n\n\n \n\n\n\n Technical Report Bioinformatics, October 2020.\n \n\n\n\n
\n\n\n\n \n \n \"WidespreadPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@techreport{grau_widespread_2020,\n\ttype = {preprint},\n\ttitle = {Widespread effects of {DNA} methylation and intra-motif dependencies revealed by novel transcription factor binding models},\n\turl = {http://biorxiv.org/lookup/doi/10.1101/2020.10.21.348193},\n\tabstract = {Abstract\n          \n            Several studies suggested that transcription factor (TF) binding to DNA may be impaired or enhanced by DNA methylation. We present M\n            e\n            D\n            e\n            M\n            o\n            , a toolbox for TF motif analysis that combines information about DNA methylation with models capturing intra-motif dependencies. In a large-scale study using ChIP-seq data for 335 TFs, we identify novel TFs that are affected by DNA methylation. Overall, we find that CpG methylation decreases the likelihood of binding for the majority of TFs. For a considerable subset of TFs, we show that intra-motif dependencies are pivotal for accurately modelling the impact of DNA methylation on TF binding.},\n\tlanguage = {en},\n\turldate = {2023-01-09},\n\tinstitution = {Bioinformatics},\n\tauthor = {Grau, Jan and Schmidt, Florian and Schulz, Marcel H.},\n\tmonth = oct,\n\tyear = {2020},\n\tdoi = {10.1101/2020.10.21.348193},\n\tfile = {Eingereichte Version:/Users/mschulz/Zotero/storage/DYJGZ3HP/Grau et al. - 2020 - Widespread effects of DNA methylation and intra-mo.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Abstract Several studies suggested that transcription factor (TF) binding to DNA may be impaired or enhanced by DNA methylation. We present M e D e M o , a toolbox for TF motif analysis that combines information about DNA methylation with models capturing intra-motif dependencies. In a large-scale study using ChIP-seq data for 335 TFs, we identify novel TFs that are affected by DNA methylation. Overall, we find that CpG methylation decreases the likelihood of binding for the majority of TFs. For a considerable subset of TFs, we show that intra-motif dependencies are pivotal for accurately modelling the impact of DNA methylation on TF binding.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Aul, Nikoletta Katsaouni, Marcel H. Schulz, & Lars Hedrich.\n\n\n \n \n \n \n Synthesis of Power-Efficient Analog Neural Networks for Signal Processing.\n \n \n \n\n\n \n\n\n\n IEEE Xplore. November 2020.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{florian_aul_synthesis_2020,\n\tjournal = {{IEEE} {Xplore}},\n\ttitle = {Synthesis of {Power}-{Efficient} {Analog} {Neural} {Networks} for {Signal} {Processing}},\n\tauthor = {{Florian Aul} and {Nikoletta Katsaouni} and {Marcel H. Schulz} and {Lars Hedrich}},\n\tmonth = nov,\n\tyear = {2020},\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (15)\n \n \n
\n
\n \n \n
\n \n\n \n \n Tarek Kröhler, Sonja M. Kessler, Kevan Hosseini, Markus List, Ahmad Barghash, Sonika Patial, Stephan Laggai, Katja Gemperlein, Johannes Haybaeck, Rolf Müller, Volkhard Helms, Marcel H. Schulz, Jessica Hoppstädter, Perry J. Blackshear, & Alexandra K. Kiemer.\n\n\n \n \n \n \n The mRNA-binding Protein TTP/ZFP36 in Hepatocarcinogenesis and Hepatocellular Carcinoma.\n \n \n \n\n\n \n\n\n\n Cancers, 11(11): 1754. November 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{krohler_mrna-binding_2019,\n\ttitle = {The {mRNA}-binding {Protein} {TTP}/{ZFP36} in {Hepatocarcinogenesis} and {Hepatocellular} {Carcinoma}},\n\tvolume = {11},\n\tissn = {2072-6694},\n\tdoi = {10.3390/cancers11111754},\n\tabstract = {Hepatic lipid deposition and inflammation represent risk factors for hepatocellular carcinoma (HCC). The mRNA-binding protein tristetraprolin (TTP, gene name ZFP36) has been suggested as a tumor suppressor in several malignancies, but it increases insulin resistance. The aim of this study was to elucidate the role of TTP in hepatocarcinogenesis and HCC progression. Employing liver-specific TTP-knockout (lsTtp-KO) mice in the diethylnitrosamine (DEN) hepatocarcinogenesis model, we observed a significantly reduced tumor burden compared to wild-type animals. Upon short-term DEN treatment, modelling early inflammatory processes in hepatocarcinogenesis, lsTtp-KO mice exhibited a reduced monocyte/macrophage ratio as compared to wild-type mice. While short-term DEN strongly induced an abundance of saturated and poly-unsaturated hepatic fatty acids, lsTtp-KO mice did not show these changes. These findings suggested anti-carcinogenic actions of TTP deletion due to effects on inflammation and metabolism. Interestingly, though, investigating effects of TTP on different hallmarks of cancer suggested tumor-suppressing actions: TTP inhibited proliferation, attenuated migration, and slightly increased chemosensitivity. In line with a tumor-suppressing activity, we observed a reduced expression of several oncogenes in TTP-overexpressing cells. Accordingly, ZFP36 expression was downregulated in tumor tissues in three large human data sets. Taken together, this study suggests that hepatocytic TTP promotes hepatocarcinogenesis, while it shows tumor-suppressive actions during hepatic tumor progression.},\n\tlanguage = {eng},\n\tnumber = {11},\n\tjournal = {Cancers},\n\tauthor = {Kröhler, Tarek and Kessler, Sonja M. and Hosseini, Kevan and List, Markus and Barghash, Ahmad and Patial, Sonika and Laggai, Stephan and Gemperlein, Katja and Haybaeck, Johannes and Müller, Rolf and Helms, Volkhard and Schulz, Marcel H. and Hoppstädter, Jessica and Blackshear, Perry J. and Kiemer, Alexandra K.},\n\tmonth = nov,\n\tyear = {2019},\n\tpmid = {31717307},\n\tpmcid = {PMC6896064},\n\tkeywords = {BCL2, chemoresistance, flow cytometry, HepG2, Huh7, liver cancer, MYC, NASH, NEAT1, VEGFA},\n\tpages = {1754},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/M8ZIET3Y/Kröhler et al. - 2019 - The mRNA-binding Protein TTPZFP36 in Hepatocarcin.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Hepatic lipid deposition and inflammation represent risk factors for hepatocellular carcinoma (HCC). The mRNA-binding protein tristetraprolin (TTP, gene name ZFP36) has been suggested as a tumor suppressor in several malignancies, but it increases insulin resistance. The aim of this study was to elucidate the role of TTP in hepatocarcinogenesis and HCC progression. Employing liver-specific TTP-knockout (lsTtp-KO) mice in the diethylnitrosamine (DEN) hepatocarcinogenesis model, we observed a significantly reduced tumor burden compared to wild-type animals. Upon short-term DEN treatment, modelling early inflammatory processes in hepatocarcinogenesis, lsTtp-KO mice exhibited a reduced monocyte/macrophage ratio as compared to wild-type mice. While short-term DEN strongly induced an abundance of saturated and poly-unsaturated hepatic fatty acids, lsTtp-KO mice did not show these changes. These findings suggested anti-carcinogenic actions of TTP deletion due to effects on inflammation and metabolism. Interestingly, though, investigating effects of TTP on different hallmarks of cancer suggested tumor-suppressing actions: TTP inhibited proliferation, attenuated migration, and slightly increased chemosensitivity. In line with a tumor-suppressing activity, we observed a reduced expression of several oncogenes in TTP-overexpressing cells. Accordingly, ZFP36 expression was downregulated in tumor tissues in three large human data sets. Taken together, this study suggests that hepatocytic TTP promotes hepatocarcinogenesis, while it shows tumor-suppressive actions during hepatic tumor progression.\n
\n\n\n
\n\n\n
\n \n\n \n \n Karl J. V. Nordström, Florian Schmidt, Nina Gasparoni, Abdulrahman Salhab, Gilles Gasparoni, Kathrin Kattler, Fabian Müller, Peter Ebert, Ivan G. Costa, DEEP consortium, Nico Pfeifer, Thomas Lengauer, Marcel H. Schulz, & Jörn Walter.\n\n\n \n \n \n \n Unique and assay specific features of NOMe-, ATAC- and DNase I-seq data.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 47(20): 10580–10596. November 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{nordstrom_unique_2019,\n\ttitle = {Unique and assay specific features of {NOMe}-, {ATAC}- and {DNase} {I}-seq data},\n\tvolume = {47},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkz799},\n\tabstract = {Chromatin accessibility maps are important for the functional interpretation of the genome. Here, we systematically analysed assay specific differences between DNase I-seq, ATAC-seq and NOMe-seq in a side by side experimental and bioinformatic setup. We observe that most prominent nucleosome depleted regions (NDRs, e.g. in promoters) are roboustly called by all three or at least two assays. However, we also find a high proportion of assay specific NDRs that are often 'called' by only one of the assays. We show evidence that these assay specific NDRs are indeed genuine open chromatin sites and contribute important information for accurate gene expression prediction. While technically ATAC-seq and DNase I-seq provide a superb high NDR calling rate for relatively low sequencing costs in comparison to NOMe-seq, NOMe-seq singles out for its genome-wide coverage allowing to not only detect NDRs but also endogenous DNA methylation and as we show here genome wide segmentation into heterochromatic B domains and local phasing of nucleosomes outside of NDRs. In summary, our comparisons strongly suggest to consider assay specific differences for the experimental design and for generalized and comparative functional interpretations.},\n\tlanguage = {eng},\n\tnumber = {20},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Nordström, Karl J. V. and Schmidt, Florian and Gasparoni, Nina and Salhab, Abdulrahman and Gasparoni, Gilles and Kattler, Kathrin and Müller, Fabian and Ebert, Peter and Costa, Ivan G. and {DEEP consortium} and Pfeifer, Nico and Lengauer, Thomas and Schulz, Marcel H. and Walter, Jörn},\n\tmonth = nov,\n\tyear = {2019},\n\tpmid = {31584093},\n\tpmcid = {PMC6847574},\n\tkeywords = {Chromatin Immunoprecipitation Sequencing, Hep G2 Cells, Humans, Nucleosomes, Promoter Regions, Genetic},\n\tpages = {10580--10596},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/CHJS57XE/Nordström et al. - 2019 - Unique and assay specific features of NOMe-, ATAC-.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Chromatin accessibility maps are important for the functional interpretation of the genome. Here, we systematically analysed assay specific differences between DNase I-seq, ATAC-seq and NOMe-seq in a side by side experimental and bioinformatic setup. We observe that most prominent nucleosome depleted regions (NDRs, e.g. in promoters) are roboustly called by all three or at least two assays. However, we also find a high proportion of assay specific NDRs that are often 'called' by only one of the assays. We show evidence that these assay specific NDRs are indeed genuine open chromatin sites and contribute important information for accurate gene expression prediction. While technically ATAC-seq and DNase I-seq provide a superb high NDR calling rate for relatively low sequencing costs in comparison to NOMe-seq, NOMe-seq singles out for its genome-wide coverage allowing to not only detect NDRs but also endogenous DNA methylation and as we show here genome wide segmentation into heterochromatic B domains and local phasing of nucleosomes outside of NDRs. In summary, our comparisons strongly suggest to consider assay specific differences for the experimental design and for generalized and comparative functional interpretations.\n
\n\n\n
\n\n\n
\n \n\n \n \n Markus List, Azim Dehghani Amirabad, Dennis Kostka, & Marcel H. Schulz.\n\n\n \n \n \n \n Large-scale inference of competing endogenous RNA networks with sparse partial correlation.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 35(14): i596–i604. July 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{list_large-scale_2019,\n\ttitle = {Large-scale inference of competing endogenous {RNA} networks with sparse partial correlation},\n\tvolume = {35},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/btz314},\n\tabstract = {MOTIVATION: MicroRNAs (miRNAs) are important non-coding post-transcriptional regulators that are involved in many biological processes and human diseases. Individual miRNAs may regulate hundreds of genes, giving rise to a complex gene regulatory network in which transcripts carrying miRNA binding sites act as competing endogenous RNAs (ceRNAs). Several methods for the analysis of ceRNA interactions exist, but these do often not adjust for statistical confounders or address the problem that more than one miRNA interacts with a target transcript.\nRESULTS: We present SPONGE, a method for the fast construction of ceRNA networks. SPONGE uses 'multiple sensitivity correlation', a newly defined measure for which we can estimate a distribution under a null hypothesis. SPONGE can accurately quantify the contribution of multiple miRNAs to a ceRNA interaction with a probabilistic model that addresses previously neglected confounding factors and allows fast P-value calculation, thus outperforming existing approaches. We applied SPONGE to paired miRNA and gene expression data from The Cancer Genome Atlas for studying global effects of miRNA-mediated cross-talk. Our results highlight already established and novel protein-coding and non-coding ceRNAs which could serve as biomarkers in cancer.\nAVAILABILITY AND IMPLEMENTATION: SPONGE is available as an R/Bioconductor package (doi: 10.18129/B9.bioc.SPONGE).\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {14},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {List, Markus and Dehghani Amirabad, Azim and Kostka, Dennis and Schulz, Marcel H.},\n\tmonth = jul,\n\tyear = {2019},\n\tpmid = {31510670},\n\tpmcid = {PMC6612827},\n\tkeywords = {Gene Regulatory Networks, Humans, Neoplasms, RNA},\n\tpages = {i596--i604},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/F7LNTE99/List et al. - 2019 - Large-scale inference of competing endogenous RNA .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: MicroRNAs (miRNAs) are important non-coding post-transcriptional regulators that are involved in many biological processes and human diseases. Individual miRNAs may regulate hundreds of genes, giving rise to a complex gene regulatory network in which transcripts carrying miRNA binding sites act as competing endogenous RNAs (ceRNAs). Several methods for the analysis of ceRNA interactions exist, but these do often not adjust for statistical confounders or address the problem that more than one miRNA interacts with a target transcript. RESULTS: We present SPONGE, a method for the fast construction of ceRNA networks. SPONGE uses 'multiple sensitivity correlation', a newly defined measure for which we can estimate a distribution under a null hypothesis. SPONGE can accurately quantify the contribution of multiple miRNAs to a ceRNA interaction with a probabilistic model that addresses previously neglected confounding factors and allows fast P-value calculation, thus outperforming existing approaches. We applied SPONGE to paired miRNA and gene expression data from The Cancer Genome Atlas for studying global effects of miRNA-mediated cross-talk. Our results highlight already established and novel protein-coding and non-coding ceRNAs which could serve as biomarkers in cancer. AVAILABILITY AND IMPLEMENTATION: SPONGE is available as an R/Bioconductor package (doi: 10.18129/B9.bioc.SPONGE). SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Eiman Elwakeel, Mirko Brüggemann, Annika F. Fink, Marcel H. Schulz, Tobias Schmid, Rajkumar Savai, Bernhard Brüne, Kathi Zarnack, & Andreas Weigert.\n\n\n \n \n \n \n Phenotypic Plasticity of Fibroblasts during Mammary Carcinoma Development.\n \n \n \n\n\n \n\n\n\n International Journal of Molecular Sciences, 20(18): 4438. September 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{elwakeel_phenotypic_2019,\n\ttitle = {Phenotypic {Plasticity} of {Fibroblasts} during {Mammary} {Carcinoma} {Development}},\n\tvolume = {20},\n\tissn = {1422-0067},\n\tdoi = {10.3390/ijms20184438},\n\tabstract = {: Cancer-associated fibroblasts (CAFs) in the tumor microenvironment contribute to all stages of tumorigenesis and are usually considered to be tumor-promoting cells. CAFs show a remarkable degree of heterogeneity, which is attributed to developmental origin or to local environmental niches, resulting in distinct CAF subsets within individual tumors. While CAF heterogeneity is frequently investigated in late-stage tumors, data on longitudinal CAF development in tumors are lacking. To this end, we used the transgenic polyoma middle T oncogene-induced mouse mammary carcinoma model and performed whole transcriptome analysis in FACS-sorted fibroblasts from early- and late-stage tumors. We observed a shift in fibroblast populations over time towards a subset previously shown to negatively correlate with patient survival, which was confirmed by multispectral immunofluorescence analysis. Moreover, we identified a transcriptomic signature distinguishing CAFs from early- and late-stage tumors. Importantly, the signature of early-stage CAFs correlated well with tumor stage and survival in human mammary carcinoma patients. A random forest analysis suggested predictive value of the complete set of differentially expressed genes between early- and late-stage CAFs on bulk tumor patient samples, supporting the clinical relevance of our findings. In conclusion, our data show transcriptome alterations in CAFs during tumorigenesis in the mammary gland, which suggest that CAFs are educated by the tumor over time to promote tumor development. Moreover, we show that murine CAF gene signatures can harbor predictive value for human cancer.},\n\tlanguage = {eng},\n\tnumber = {18},\n\tjournal = {International Journal of Molecular Sciences},\n\tauthor = {Elwakeel, Eiman and Brüggemann, Mirko and Fink, Annika F. and Schulz, Marcel H. and Schmid, Tobias and Savai, Rajkumar and Brüne, Bernhard and Zarnack, Kathi and Weigert, Andreas},\n\tmonth = sep,\n\tyear = {2019},\n\tpmid = {31505876},\n\tpmcid = {PMC6769951},\n\tkeywords = {Animals, cancer, cancer-associated fibroblasts, Female, Fibroblasts, Gene Expression Regulation, Neoplastic, gene signature, mammary carcinoma, Mammary Glands, Animal, Mammary Neoplasms, Animal, Mice, Mice, Transgenic, Transcription, Genetic, transcriptional profiling},\n\tpages = {4438},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/K6NBQSI2/Elwakeel et al. - 2019 - Phenotypic Plasticity of Fibroblasts during Mammar.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n : Cancer-associated fibroblasts (CAFs) in the tumor microenvironment contribute to all stages of tumorigenesis and are usually considered to be tumor-promoting cells. CAFs show a remarkable degree of heterogeneity, which is attributed to developmental origin or to local environmental niches, resulting in distinct CAF subsets within individual tumors. While CAF heterogeneity is frequently investigated in late-stage tumors, data on longitudinal CAF development in tumors are lacking. To this end, we used the transgenic polyoma middle T oncogene-induced mouse mammary carcinoma model and performed whole transcriptome analysis in FACS-sorted fibroblasts from early- and late-stage tumors. We observed a shift in fibroblast populations over time towards a subset previously shown to negatively correlate with patient survival, which was confirmed by multispectral immunofluorescence analysis. Moreover, we identified a transcriptomic signature distinguishing CAFs from early- and late-stage tumors. Importantly, the signature of early-stage CAFs correlated well with tumor stage and survival in human mammary carcinoma patients. A random forest analysis suggested predictive value of the complete set of differentially expressed genes between early- and late-stage CAFs on bulk tumor patient samples, supporting the clinical relevance of our findings. In conclusion, our data show transcriptome alterations in CAFs during tumorigenesis in the mammary gland, which suggest that CAFs are educated by the tumor over time to promote tumor development. Moreover, we show that murine CAF gene signatures can harbor predictive value for human cancer.\n
\n\n\n
\n\n\n
\n \n\n \n \n Nicole Ritter, Tamer Ali, Nina Kopitchinski, Peggy Schuster, Arica Beisaw, David A. Hendrix, Marcel H. Schulz, Michaela Müller-McNicoll, Stefanie Dimmeler, & Phillip Grote.\n\n\n \n \n \n \n The lncRNA Locus Handsdown Regulates Cardiac Gene Programs and Is Essential for Early Mouse Development.\n \n \n \n\n\n \n\n\n\n Developmental Cell, 50(5): 644–657.e8. September 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{ritter_lncrna_2019,\n\ttitle = {The {lncRNA} {Locus} {Handsdown} {Regulates} {Cardiac} {Gene} {Programs} and {Is} {Essential} for {Early} {Mouse} {Development}},\n\tvolume = {50},\n\tissn = {1878-1551},\n\tdoi = {10.1016/j.devcel.2019.07.013},\n\tabstract = {Precisely controlled gene regulatory networks are required during embryonic development to give rise to various structures, including those of the cardiovascular system. Long non-coding RNA (lncRNA) loci are known to be important regulators of these genetic programs. We have identified a novel and essential lncRNA locus Handsdown (Hdn), active in early heart cells, and show by genetic inactivation that it is essential for murine development. Hdn displays haploinsufficiency for cardiac development as Hdn-heterozygous adult mice exhibit hyperplasia in the right ventricular wall. Transcriptional activity of the Hdn locus, independent of its RNA, suppresses its neighboring gene Hand2. We reveal a switch in a topologically associated domain in differentiation of the cardiac lineage, allowing the Hdn locus to directly interact with regulatory elements of the Hand2 locus.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Developmental Cell},\n\tauthor = {Ritter, Nicole and Ali, Tamer and Kopitchinski, Nina and Schuster, Peggy and Beisaw, Arica and Hendrix, David A. and Schulz, Marcel H. and Müller-McNicoll, Michaela and Dimmeler, Stefanie and Grote, Phillip},\n\tmonth = sep,\n\tyear = {2019},\n\tpmid = {31422919},\n\tkeywords = {Animals, cardiac development, Cell Differentiation, Cells, Cultured, Gene Expression Regulation, Developmental, Hand2, haploinsufficiency, Haploinsufficiency, Heart, LncRNA, Mice, Mice, Inbred C57BL, Mouse Embryonic Stem Cells, Myocytes, Cardiac, RNA, Long Noncoding, TAD},\n\tpages = {644--657.e8},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/XJ9ZCCRK/Ritter et al. - 2019 - The lncRNA Locus Handsdown Regulates Cardiac Gene .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Precisely controlled gene regulatory networks are required during embryonic development to give rise to various structures, including those of the cardiovascular system. Long non-coding RNA (lncRNA) loci are known to be important regulators of these genetic programs. We have identified a novel and essential lncRNA locus Handsdown (Hdn), active in early heart cells, and show by genetic inactivation that it is essential for murine development. Hdn displays haploinsufficiency for cardiac development as Hdn-heterozygous adult mice exhibit hyperplasia in the right ventricular wall. Transcriptional activity of the Hdn locus, independent of its RNA, suppresses its neighboring gene Hand2. We reveal a switch in a topologically associated domain in differentiation of the cardiac lineage, allowing the Hdn locus to directly interact with regulatory elements of the Hand2 locus.\n
\n\n\n
\n\n\n
\n \n\n \n \n Andrea Blum, Saleem Khalifa, Karl Nordström, Martin Simon, Marcel H. Schulz, & Manfred J. Schmitt.\n\n\n \n \n \n \n Transcriptomics of a KDELR1 knockout cell line reveals modulated cell adhesion properties.\n \n \n \n\n\n \n\n\n\n Scientific Reports, 9(1): 10611. July 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{blum_transcriptomics_2019,\n\ttitle = {Transcriptomics of a {KDELR1} knockout cell line reveals modulated cell adhesion properties},\n\tvolume = {9},\n\tissn = {2045-2322},\n\tdoi = {10.1038/s41598-019-47027-5},\n\tabstract = {KDEL receptors (KDELRs) represent transmembrane proteins of the secretory pathway which regulate the retention of soluble ER-residents as well as retrograde and anterograde vesicle trafficking. In addition, KDELRs are involved in the regulation of cellular stress response and ECM degradation. For a deeper insight into KDELR1 specific functions, we characterised a KDELR1-KO cell line (HAP1) through whole transcriptome analysis by comparing KDELR1-KO cells with its respective HAP1 wild-type. Our data indicate more than 300 significantly and differentially expressed genes whose gene products are mainly involved in developmental processes such as cell adhesion and ECM composition, pointing out to severe cellular disorders due to a loss of KDELR1. Impaired adhesion capacity of KDELR1-KO cells was further demonstrated through in vitro adhesion assays, while collagen- and/or laminin-coating nearly doubled the adhesion property of KDELR1-KO cells compared to wild-type, confirming a transcriptional adaptation to improve or restore the cellular adhesion capability. Perturbations within the secretory pathway were verified by an increased secretion of ER-resident PDI and decreased cell viability under ER stress conditions, suggesting KDELR1-KO cells to be severely impaired in maintaining cellular homeostasis.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Scientific Reports},\n\tauthor = {Blum, Andrea and Khalifa, Saleem and Nordström, Karl and Simon, Martin and Schulz, Marcel H. and Schmitt, Manfred J.},\n\tmonth = jul,\n\tyear = {2019},\n\tpmid = {31337861},\n\tpmcid = {PMC6650600},\n\tkeywords = {Cell Adhesion, Cell Line, Cell Movement, Gene Expression Profiling, Gene Knockout Techniques, Humans, Receptors, Peptide, Sequence Analysis, DNA},\n\tpages = {10611},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/JB3IP5AW/Blum et al. - 2019 - Transcriptomics of a KDELR1 knockout cell line rev.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n KDEL receptors (KDELRs) represent transmembrane proteins of the secretory pathway which regulate the retention of soluble ER-residents as well as retrograde and anterograde vesicle trafficking. In addition, KDELRs are involved in the regulation of cellular stress response and ECM degradation. For a deeper insight into KDELR1 specific functions, we characterised a KDELR1-KO cell line (HAP1) through whole transcriptome analysis by comparing KDELR1-KO cells with its respective HAP1 wild-type. Our data indicate more than 300 significantly and differentially expressed genes whose gene products are mainly involved in developmental processes such as cell adhesion and ECM composition, pointing out to severe cellular disorders due to a loss of KDELR1. Impaired adhesion capacity of KDELR1-KO cells was further demonstrated through in vitro adhesion assays, while collagen- and/or laminin-coating nearly doubled the adhesion property of KDELR1-KO cells compared to wild-type, confirming a transcriptional adaptation to improve or restore the cellular adhesion capability. Perturbations within the secretory pathway were verified by an increased secretion of ER-resident PDI and decreased cell viability under ER stress conditions, suggesting KDELR1-KO cells to be severely impaired in maintaining cellular homeostasis.\n
\n\n\n
\n\n\n
\n \n\n \n \n Sivarajan Karunanithi, Vidya Oruganti, Simone Marker, Angela M. Rodriguez-Viana, Franziska Drews, Marcello Pirritano, Karl Nordström, Martin Simon, & Marcel H. Schulz.\n\n\n \n \n \n \n Exogenous RNAi mechanisms contribute to transcriptome adaptation by phased siRNA clusters in Paramecium.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 47(15): 8036–8049. September 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{karunanithi_exogenous_2019,\n\ttitle = {Exogenous {RNAi} mechanisms contribute to transcriptome adaptation by phased {siRNA} clusters in {Paramecium}},\n\tvolume = {47},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkz553},\n\tabstract = {Extensive research has characterized distinct exogenous RNAi pathways interfering in gene expression during vegetative growth of the unicellular model ciliate Paramecium. However, role of RNAi in endogenous transcriptome regulation, and environmental adaptation is unknown. Here, we describe the first genome-wide profiling of endogenous sRNAs in context of different transcriptomic states (serotypes). We developed a pipeline to identify, and characterize 2602 siRNA producing clusters (SRCs). Our data show no evidence that SRCs produce miRNAs, and in contrast to other species, no preference for strand specificity of siRNAs. Interestingly, most SRCs overlap coding genes and a separate group show siRNA phasing along the entire open reading frame, suggesting that the mRNA transcript serves as a source for siRNAs. Integrative analysis of siRNA abundance and gene expression levels revealed surprisingly that mRNA and siRNA show negative as well as positive associations. Two RNA-dependent RNA Polymerase mutants, RDR1 and RDR2, show a drastic loss of siRNAs especially in phased SRCs accompanied with increased mRNA levels. Importantly, most SRCs depend on both RDRs, reminiscent to primary siRNAs in the RNAi against exogenous RNA, indicating mechanistic overlaps between exogenous and endogenous RNAi contributing to flexible transcriptome adaptation.},\n\tlanguage = {eng},\n\tnumber = {15},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Karunanithi, Sivarajan and Oruganti, Vidya and Marker, Simone and Rodriguez-Viana, Angela M. and Drews, Franziska and Pirritano, Marcello and Nordström, Karl and Simon, Martin and Schulz, Marcel H.},\n\tmonth = sep,\n\tyear = {2019},\n\tpmid = {31251800},\n\tpmcid = {PMC6735861},\n\tkeywords = {Adaptation, Physiological, Gene Expression Profiling, Gene Ontology, Genome, Protozoan, MicroRNAs, Paramecium, RNA Interference, RNA, Messenger, RNA, Small Interfering, Transcriptome},\n\tpages = {8036--8049},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/NHST4WSW/Karunanithi et al. - 2019 - Exogenous RNAi mechanisms contribute to transcript.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Extensive research has characterized distinct exogenous RNAi pathways interfering in gene expression during vegetative growth of the unicellular model ciliate Paramecium. However, role of RNAi in endogenous transcriptome regulation, and environmental adaptation is unknown. Here, we describe the first genome-wide profiling of endogenous sRNAs in context of different transcriptomic states (serotypes). We developed a pipeline to identify, and characterize 2602 siRNA producing clusters (SRCs). Our data show no evidence that SRCs produce miRNAs, and in contrast to other species, no preference for strand specificity of siRNAs. Interestingly, most SRCs overlap coding genes and a separate group show siRNA phasing along the entire open reading frame, suggesting that the mRNA transcript serves as a source for siRNAs. Integrative analysis of siRNA abundance and gene expression levels revealed surprisingly that mRNA and siRNA show negative as well as positive associations. Two RNA-dependent RNA Polymerase mutants, RDR1 and RDR2, show a drastic loss of siRNAs especially in phased SRCs accompanied with increased mRNA levels. Importantly, most SRCs depend on both RDRs, reminiscent to primary siRNAs in the RNAi against exogenous RNA, indicating mechanistic overlaps between exogenous and endogenous RNAi contributing to flexible transcriptome adaptation.\n
\n\n\n
\n\n\n
\n \n\n \n \n Stefanie Gier, Martin Simon, Karl Nordström, Salem Khalifa, Marcel H. Schulz, Manfred J. Schmitt, & Frank Breinig.\n\n\n \n \n \n \n Transcriptome Kinetics of Saccharomyces cerevisiae in Response to Viral Killer Toxin K1.\n \n \n \n\n\n \n\n\n\n Frontiers in Microbiology, 10: 1102. 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{gier_transcriptome_2019,\n\ttitle = {Transcriptome {Kinetics} of {Saccharomyces} cerevisiae in {Response} to {Viral} {Killer} {Toxin} {K1}},\n\tvolume = {10},\n\tissn = {1664-302X},\n\tdoi = {10.3389/fmicb.2019.01102},\n\tabstract = {The K1 A/B toxin secreted by virus-infected Saccharomyces cerevisiae strains kills sensitive cells via disturbance of cytoplasmic membrane functions. Despite decades of research, the mechanisms underlying K1 toxicity and immunity have not been elucidated yet. In a novel approach, this study aimed to characterize transcriptome changes in K1-treated sensitive yeast cells in a time-dependent manner. Global transcriptional profiling revealed substantial cellular adaptations in target cells resulting in 1,189 differentially expressed genes in total. Killer toxin K1 induced oxidative, cell wall and hyperosmotic stress responses as well as rapid down-regulation of transcription and translation. Essential pathways regulating energy metabolism were also significantly affected by the toxin. Remarkably, a futile cycle of the osmolytes trehalose and glycogen was identified probably representing a critical feature of K1 intoxication. In silico analysis suggested several transcription factors involved in toxin-triggered signal transduction. The identified transcriptome changes provide valuable hints to illuminate the still unknown molecular events leading to K1 toxicity and immunity implicating an evolutionarily conserved response at least initially counteracting ionophoric toxin action.},\n\tlanguage = {eng},\n\tjournal = {Frontiers in Microbiology},\n\tauthor = {Gier, Stefanie and Simon, Martin and Nordström, Karl and Khalifa, Salem and Schulz, Marcel H. and Schmitt, Manfred J. and Breinig, Frank},\n\tyear = {2019},\n\tpmid = {31156606},\n\tpmcid = {PMC6531845},\n\tkeywords = {K1, killer toxin, Saccharomyces cerevisiae, transcriptome, yeast viral toxin},\n\tpages = {1102},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/KJNUD5RH/Gier et al. - 2019 - Transcriptome Kinetics of Saccharomyces cerevisiae.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The K1 A/B toxin secreted by virus-infected Saccharomyces cerevisiae strains kills sensitive cells via disturbance of cytoplasmic membrane functions. Despite decades of research, the mechanisms underlying K1 toxicity and immunity have not been elucidated yet. In a novel approach, this study aimed to characterize transcriptome changes in K1-treated sensitive yeast cells in a time-dependent manner. Global transcriptional profiling revealed substantial cellular adaptations in target cells resulting in 1,189 differentially expressed genes in total. Killer toxin K1 induced oxidative, cell wall and hyperosmotic stress responses as well as rapid down-regulation of transcription and translation. Essential pathways regulating energy metabolism were also significantly affected by the toxin. Remarkably, a futile cycle of the osmolytes trehalose and glycogen was identified probably representing a critical feature of K1 intoxication. In silico analysis suggested several transcription factors involved in toxin-triggered signal transduction. The identified transcriptome changes provide valuable hints to illuminate the still unknown molecular events leading to K1 toxicity and immunity implicating an evolutionarily conserved response at least initially counteracting ionophoric toxin action.\n
\n\n\n
\n\n\n
\n \n\n \n \n Sivarajan Karunanithi, Martin Simon, & Marcel H. Schulz.\n\n\n \n \n \n \n Automated analysis of small RNA datasets with RAPID.\n \n \n \n\n\n \n\n\n\n PeerJ, 7: e6710. 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{karunanithi_automated_2019,\n\ttitle = {Automated analysis of small {RNA} datasets with {RAPID}},\n\tvolume = {7},\n\tissn = {2167-8359},\n\tdoi = {10.7717/peerj.6710},\n\tabstract = {Understanding the role of short-interfering RNA (siRNA) in diverse biological processes is of current interest and often approached through small RNA sequencing. However, analysis of these datasets is difficult due to the complexity of biological RNA processing pathways, which differ between species. Several properties like strand specificity, length distribution, and distribution of soft-clipped bases are few parameters known to guide researchers in understanding the role of siRNAs. We present RAPID, a generic eukaryotic siRNA analysis pipeline, which captures information inherent in the datasets and automatically produces numerous visualizations as user-friendly HTML reports, covering multiple categories required for siRNA analysis. RAPID also facilitates an automated comparison of multiple datasets, with one of the normalization techniques dedicated for siRNA knockdown analysis, and integrates differential expression analysis using DESeq2.\nAVAILABILITY AND IMPLEMENTATION: RAPID is available under MIT license at https://github.com/SchulzLab/RAPID. We recommend using it as a conda environment available from https://anaconda.org/bioconda/rapid.},\n\tlanguage = {eng},\n\tjournal = {PeerJ},\n\tauthor = {Karunanithi, Sivarajan and Simon, Martin and Schulz, Marcel H.},\n\tyear = {2019},\n\tpmid = {30993044},\n\tpmcid = {PMC6462184},\n\tkeywords = {Automated sRNA analysis, Comparative analysis, Computational sRNA analysis, Eukaryotic sRNA, siRNA analysis, siRNA quantification, Small RNA analysis, sRNA, sRNA tool},\n\tpages = {e6710},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/82RBEVVX/Karunanithi et al. - 2019 - Automated analysis of small RNA datasets with RAPI.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Understanding the role of short-interfering RNA (siRNA) in diverse biological processes is of current interest and often approached through small RNA sequencing. However, analysis of these datasets is difficult due to the complexity of biological RNA processing pathways, which differ between species. Several properties like strand specificity, length distribution, and distribution of soft-clipped bases are few parameters known to guide researchers in understanding the role of siRNAs. We present RAPID, a generic eukaryotic siRNA analysis pipeline, which captures information inherent in the datasets and automatically produces numerous visualizations as user-friendly HTML reports, covering multiple categories required for siRNA analysis. RAPID also facilitates an automated comparison of multiple datasets, with one of the normalization techniques dedicated for siRNA knockdown analysis, and integrates differential expression analysis using DESeq2. AVAILABILITY AND IMPLEMENTATION: RAPID is available under MIT license at https://github.com/SchulzLab/RAPID. We recommend using it as a conda environment available from https://anaconda.org/bioconda/rapid.\n
\n\n\n
\n\n\n
\n \n\n \n \n Sonja M. Kessler, Kevan Hosseini, Usama Khamis Hussein, Kyoung Min Kim, Markus List, Christina S. Schultheiß, Marcel H. Schulz, Stephan Laggai, Kyu Yun Jang, & Alexandra K. Kiemer.\n\n\n \n \n \n \n Hepatocellular Carcinoma and Nuclear Paraspeckles: Induction in Chemoresistance and Prediction for Poor Survival.\n \n \n \n\n\n \n\n\n\n Cellular Physiology and Biochemistry: International Journal of Experimental Cellular Physiology, Biochemistry, and Pharmacology, 52(4): 787–801. 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{kessler_hepatocellular_2019,\n\ttitle = {Hepatocellular {Carcinoma} and {Nuclear} {Paraspeckles}: {Induction} in {Chemoresistance} and {Prediction} for {Poor} {Survival}},\n\tvolume = {52},\n\tissn = {1421-9778},\n\tshorttitle = {Hepatocellular {Carcinoma} and {Nuclear} {Paraspeckles}},\n\tdoi = {10.33594/000000055},\n\tabstract = {BACKGROUND/AIMS: Hepatocellular carcinoma (HCC) represents the second most common cause of cancer-related deaths worldwide, not least due to its high chemoresistance. The long non-coding RNA nuclear paraspeckle assembly transcript 1 (NEAT1), localised in nuclear paraspeckles, has been shown to enhance chemoresistance in several cancer types. Since data on NEAT1 in HCC chemosensitivity are completely lacking and chemoresistance is linked to poor prognosis, we aimed to study NEAT1 expression in HCC chemoresistance and its link to HCC prognosis.\nMETHODS: NEAT1 expression was determined in either sensitive, or sorafenib, or doxorubicin resistant HepG2, PLC/PRF/5, and Huh7 cells by qPCR. Paraspeckles were detected by immunostaining of paraspeckle component 1 (PSPC1) in cell culture and in a cohort of HCC patients. PSPC1 expression was correlated with clinical data. The expression of transcript variants of NEAT1 and transcripts encoding the paraspeckle-associated proteins was analysed in the TCGA liver cancer data set.\nRESULTS: NEAT1 was overexpressed in all three sorafenib and doxorubicin resistant cell lines. Paraspeckles were present in all chemoresistant cells, whereas no signal was detected in the sensitive cells. Expression of NEAT1 transcripts as well as transcripts encoding PSPC1, NONO, and RBM14 was increased in tumour tissue. Expression of PSPC1, NONO, and RBM14 transcripts was significantly associated with poor survival, whereas NEAT1 expression was not. Immunohistochemical analysis revealed that nuclear and cytoplasmic PSPC1-positivity was significantly associated with shorter overall survival of HCC patients.\nCONCLUSION: Our data show an induction of NEAT1 in HCC chemoresistance and a high correlation of transcripts encoding paraspeckle-associated proteins with poor survival in HCC. Therefore, NEAT1, PSPC1, NONO, and RBM14 might be promising targets for novel HCC therapies, and the paraspeckle-associated proteins might be clinical markers and predictors for poor survival in HCC.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {Cellular Physiology and Biochemistry: International Journal of Experimental Cellular Physiology, Biochemistry, and Pharmacology},\n\tauthor = {Kessler, Sonja M. and Hosseini, Kevan and Hussein, Usama Khamis and Kim, Kyoung Min and List, Markus and Schultheiß, Christina S. and Schulz, Marcel H. and Laggai, Stephan and Jang, Kyu Yun and Kiemer, Alexandra K.},\n\tyear = {2019},\n\tpmid = {30946555},\n\tkeywords = {Actinomycin D, Antineoplastic Agents, Area Under Curve, Carcinoma, Hepatocellular, Cell Line, Tumor, Chemosensitivity, Chemotherapy, DNA-Binding Proteins, Doxorubicin, Drug Resistance, Neoplasm, Female, Humans, Kaplan-Meier Estimate, Liver, Liver cancer, Liver Neoplasms, lncRNA, MALAT1, Male, Middle Aged, mRNA decay, mRNA stability, NEAT2, Nuclear Matrix-Associated Proteins, Nuclear Proteins, Octamer Transcription Factors, Prognosis, Proportional Hazards Models, RNA-Binding Proteins, RNA, Long Noncoding, ROC Curve, Sorafenib, Therapy response},\n\tpages = {787--801},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/FKJF3UC8/Kessler et al. - 2019 - Hepatocellular Carcinoma and Nuclear Paraspeckles.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND/AIMS: Hepatocellular carcinoma (HCC) represents the second most common cause of cancer-related deaths worldwide, not least due to its high chemoresistance. The long non-coding RNA nuclear paraspeckle assembly transcript 1 (NEAT1), localised in nuclear paraspeckles, has been shown to enhance chemoresistance in several cancer types. Since data on NEAT1 in HCC chemosensitivity are completely lacking and chemoresistance is linked to poor prognosis, we aimed to study NEAT1 expression in HCC chemoresistance and its link to HCC prognosis. METHODS: NEAT1 expression was determined in either sensitive, or sorafenib, or doxorubicin resistant HepG2, PLC/PRF/5, and Huh7 cells by qPCR. Paraspeckles were detected by immunostaining of paraspeckle component 1 (PSPC1) in cell culture and in a cohort of HCC patients. PSPC1 expression was correlated with clinical data. The expression of transcript variants of NEAT1 and transcripts encoding the paraspeckle-associated proteins was analysed in the TCGA liver cancer data set. RESULTS: NEAT1 was overexpressed in all three sorafenib and doxorubicin resistant cell lines. Paraspeckles were present in all chemoresistant cells, whereas no signal was detected in the sensitive cells. Expression of NEAT1 transcripts as well as transcripts encoding PSPC1, NONO, and RBM14 was increased in tumour tissue. Expression of PSPC1, NONO, and RBM14 transcripts was significantly associated with poor survival, whereas NEAT1 expression was not. Immunohistochemical analysis revealed that nuclear and cytoplasmic PSPC1-positivity was significantly associated with shorter overall survival of HCC patients. CONCLUSION: Our data show an induction of NEAT1 in HCC chemoresistance and a high correlation of transcripts encoding paraspeckle-associated proteins with poor survival in HCC. Therefore, NEAT1, PSPC1, NONO, and RBM14 might be promising targets for novel HCC therapies, and the paraspeckle-associated proteins might be clinical markers and predictors for poor survival in HCC.\n
\n\n\n
\n\n\n
\n \n\n \n \n Dilip A. Durai, & Marcel H. Schulz.\n\n\n \n \n \n \n Improving in-silico normalization using read weights.\n \n \n \n\n\n \n\n\n\n Scientific Reports, 9(1): 5133. March 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n
@article{durai_improving_2019,\n\ttitle = {Improving in-silico normalization using read weights},\n\tvolume = {9},\n\tissn = {2045-2322},\n\tdoi = {10.1038/s41598-019-41502-9},\n\tabstract = {Specialized de novo assemblers for diverse datatypes have been developed and are in widespread use for the analyses of single-cell genomics, metagenomics and RNA-seq data. However, assembly of large sequencing datasets produced by modern technologies is challenging and computationally intensive. In-silico read normalization has been suggested as a computational strategy to reduce redundancy in read datasets, which leads to significant speedups and memory savings of assembly pipelines. Previously, we presented a set multi-cover optimization based approach, ORNA, where reads are reduced without losing important k-mer connectivity information, as used in assembly graphs. Here we propose extensions to ORNA, named ORNA-Q and ORNA-K, which consider a weighted set multi-cover optimization formulation for the in-silico read normalization problem. These novel formulations make use of the base quality scores obtained from sequencers (ORNA-Q) or k-mer abundances of reads (ORNA-K) to improve normalization further. We devise efficient heuristic algorithms for solving both formulations. In applications to human RNA-seq data, ORNA-Q and ORNA-K are shown to assemble more or equally many full length transcripts compared to other normalization methods at similar or higher read reduction values. The algorithm is implemented under the latest version of ORNA (v2.0, https://github.com/SchulzLab/ORNA ).},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Scientific Reports},\n\tauthor = {Durai, Dilip A. and Schulz, Marcel H.},\n\tmonth = mar,\n\tyear = {2019},\n\tpmid = {30914698},\n\tpmcid = {PMC6435659},\n\tpages = {5133},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/XQS683WF/Durai und Schulz - 2019 - Improving in-silico normalization using read weigh.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Specialized de novo assemblers for diverse datatypes have been developed and are in widespread use for the analyses of single-cell genomics, metagenomics and RNA-seq data. However, assembly of large sequencing datasets produced by modern technologies is challenging and computationally intensive. In-silico read normalization has been suggested as a computational strategy to reduce redundancy in read datasets, which leads to significant speedups and memory savings of assembly pipelines. Previously, we presented a set multi-cover optimization based approach, ORNA, where reads are reduced without losing important k-mer connectivity information, as used in assembly graphs. Here we propose extensions to ORNA, named ORNA-Q and ORNA-K, which consider a weighted set multi-cover optimization formulation for the in-silico read normalization problem. These novel formulations make use of the base quality scores obtained from sequencers (ORNA-Q) or k-mer abundances of reads (ORNA-K) to improve normalization further. We devise efficient heuristic algorithms for solving both formulations. In applications to human RNA-seq data, ORNA-Q and ORNA-K are shown to assemble more or equally many full length transcripts compared to other normalization methods at similar or higher read reduction values. The algorithm is implemented under the latest version of ORNA (v2.0, https://github.com/SchulzLab/ORNA ).\n
\n\n\n
\n\n\n
\n \n\n \n \n Zhijian Li, Marcel H. Schulz, Thomas Look, Matthias Begemann, Martin Zenke, & Ivan G. Costa.\n\n\n \n \n \n \n Identification of transcription factor binding sites using ATAC-seq.\n \n \n \n\n\n \n\n\n\n Genome Biology, 20(1): 45. February 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{li_identification_2019,\n\ttitle = {Identification of transcription factor binding sites using {ATAC}-seq},\n\tvolume = {20},\n\tissn = {1474-760X},\n\tdoi = {10.1186/s13059-019-1642-2},\n\tabstract = {Transposase-Accessible Chromatin followed by sequencing (ATAC-seq) is a simple protocol for detection of open chromatin. Computational footprinting, the search for regions with depletion of cleavage events due to transcription factor binding, is poorly understood for ATAC-seq. We propose the first footprinting method considering ATAC-seq protocol artifacts. HINT-ATAC uses a position dependency model to learn the cleavage preferences of the transposase. We observe strand-specific cleavage patterns around transcription factor binding sites, which are determined by local nucleosome architecture. By incorporating all these biases, HINT-ATAC is able to significantly outperform competing methods in the prediction of transcription factor binding sites with footprints.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Genome Biology},\n\tauthor = {Li, Zhijian and Schulz, Marcel H. and Look, Thomas and Begemann, Matthias and Zenke, Martin and Costa, Ivan G.},\n\tmonth = feb,\n\tyear = {2019},\n\tpmid = {30808370},\n\tpmcid = {PMC6391789},\n\tkeywords = {Animals, ATAC-seq, Cleavage bias, Computational footprinting, Dendritic Cells, DNA Footprinting, Genomics, Humans, K562 Cells, Mice, Models, Genetic, Nucleosomes, Open chromatin, Sequence Analysis, DNA, Transcription Factors, Transposases},\n\tpages = {45},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/UGQILYCY/Li et al. - 2019 - Identification of transcription factor binding sit.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Transposase-Accessible Chromatin followed by sequencing (ATAC-seq) is a simple protocol for detection of open chromatin. Computational footprinting, the search for regions with depletion of cleavage events due to transcription factor binding, is poorly understood for ATAC-seq. We propose the first footprinting method considering ATAC-seq protocol artifacts. HINT-ATAC uses a position dependency model to learn the cleavage preferences of the transposase. We observe strand-specific cleavage patterns around transcription factor binding sites, which are determined by local nucleosome architecture. By incorporating all these biases, HINT-ATAC is able to significantly outperform competing methods in the prediction of transcription factor binding sites with footprints.\n
\n\n\n
\n\n\n
\n \n\n \n \n Deborah Gérard, Florian Schmidt, Aurélien Ginolhac, Martine Schmitz, Rashi Halder, Peter Ebert, Marcel H. Schulz, Thomas Sauter, & Lasse Sinkkonen.\n\n\n \n \n \n \n Temporal enhancer profiling of parallel lineages identifies AHR and GLIS1 as regulators of mesenchymal multipotency.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 47(3): 1141–1163. February 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{gerard_temporal_2019,\n\ttitle = {Temporal enhancer profiling of parallel lineages identifies {AHR} and {GLIS1} as regulators of mesenchymal multipotency},\n\tvolume = {47},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gky1240},\n\tabstract = {Temporal data on gene expression and context-specific open chromatin states can improve identification of key transcription factors (TFs) and the gene regulatory networks (GRNs) controlling cellular differentiation. However, their integration remains challenging. Here, we delineate a general approach for data-driven and unbiased identification of key TFs and dynamic GRNs, called EPIC-DREM. We generated time-series transcriptomic and epigenomic profiles during differentiation of mouse multipotent bone marrow stromal cell line (ST2) toward adipocytes and osteoblasts. Using our novel approach we constructed time-resolved GRNs for both lineages and identifed the shared TFs involved in both differentiation processes. To take an alternative approach to prioritize the identified shared regulators, we mapped dynamic super-enhancers in both lineages and associated them to target genes with correlated expression profiles. The combination of the two approaches identified aryl hydrocarbon receptor (AHR) and Glis family zinc finger 1 (GLIS1) as mesenchymal key TFs controlled by dynamic cell type-specific super-enhancers that become repressed in both lineages. AHR and GLIS1 control differentiation-induced genes and their overexpression can inhibit the lineage commitment of the multipotent bone marrow-derived ST2 cells.},\n\tlanguage = {eng},\n\tnumber = {3},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Gérard, Deborah and Schmidt, Florian and Ginolhac, Aurélien and Schmitz, Martine and Halder, Rashi and Ebert, Peter and Schulz, Marcel H. and Sauter, Thomas and Sinkkonen, Lasse},\n\tmonth = feb,\n\tyear = {2019},\n\tpmid = {30544251},\n\tpmcid = {PMC6380961},\n\tkeywords = {Adipocytes, Animals, Cell Differentiation, Cell Line, Cell Lineage, DNA-Binding Proteins, Enhancer Elements, Genetic, Gene Regulatory Networks, Mesenchymal Stem Cells, Mice, Osteoblasts, Receptors, Aryl Hydrocarbon, Transcription Factors},\n\tpages = {1141--1163},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/EAGT7HWZ/Gérard et al. - 2019 - Temporal enhancer profiling of parallel lineages i.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Temporal data on gene expression and context-specific open chromatin states can improve identification of key transcription factors (TFs) and the gene regulatory networks (GRNs) controlling cellular differentiation. However, their integration remains challenging. Here, we delineate a general approach for data-driven and unbiased identification of key TFs and dynamic GRNs, called EPIC-DREM. We generated time-series transcriptomic and epigenomic profiles during differentiation of mouse multipotent bone marrow stromal cell line (ST2) toward adipocytes and osteoblasts. Using our novel approach we constructed time-resolved GRNs for both lineages and identifed the shared TFs involved in both differentiation processes. To take an alternative approach to prioritize the identified shared regulators, we mapped dynamic super-enhancers in both lineages and associated them to target genes with correlated expression profiles. The combination of the two approaches identified aryl hydrocarbon receptor (AHR) and Glis family zinc finger 1 (GLIS1) as mesenchymal key TFs controlled by dynamic cell type-specific super-enhancers that become repressed in both lineages. AHR and GLIS1 control differentiation-induced genes and their overexpression can inhibit the lineage commitment of the multipotent bone marrow-derived ST2 cells.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, Fabian Kern, Peter Ebert, Nina Baumgarten, & Marcel H. Schulz.\n\n\n \n \n \n \n TEPIC 2-an extended framework for transcription factor binding prediction and integrative epigenomic analysis.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 35(9): 1608–1609. May 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_tepic_2019,\n\ttitle = {{TEPIC} 2-an extended framework for transcription factor binding prediction and integrative epigenomic analysis},\n\tvolume = {35},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bty856},\n\tabstract = {SUMMARY: Prediction of transcription factor (TF) binding from epigenetics data and integrative analysis thereof are challenging. Here, we present TEPIC 2 a framework allowing for fast, accurate and versatile prediction, and analysis of TF binding from epigenetics data: it supports 30 species with binding motifs, computes TF gene and scores up to two orders of magnitude faster than before due to improved implementation, and offers easy-to-use machine learning pipelines for integrated analysis of TF binding predictions with gene expression data allowing the identification of important TFs.\nAVAILABILITY AND IMPLEMENTATION: TEPIC is implemented in C++, R, and Python. It is freely available at https://github.com/SchulzLab/TEPIC and can be used on Linux based systems.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {9},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Schmidt, Florian and Kern, Fabian and Ebert, Peter and Baumgarten, Nina and Schulz, Marcel H.},\n\tmonth = may,\n\tyear = {2019},\n\tpmid = {30304373},\n\tpmcid = {PMC6499243},\n\tkeywords = {Animals, Binding Sites, Epigenomics, Humans, Mice, Protein Binding, Transcription Factors, Triazines},\n\tpages = {1608--1609},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/XVWYFPBM/Schmidt et al. - 2019 - TEPIC 2-an extended framework for transcription fa.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n SUMMARY: Prediction of transcription factor (TF) binding from epigenetics data and integrative analysis thereof are challenging. Here, we present TEPIC 2 a framework allowing for fast, accurate and versatile prediction, and analysis of TF binding from epigenetics data: it supports 30 species with binding motifs, computes TF gene and scores up to two orders of magnitude faster than before due to improved implementation, and offers easy-to-use machine learning pipelines for integrated analysis of TF binding predictions with gene expression data allowing the identification of important TFs. AVAILABILITY AND IMPLEMENTATION: TEPIC is implemented in C++, R, and Python. It is freely available at https://github.com/SchulzLab/TEPIC and can be used on Linux based systems. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, & Marcel H. Schulz.\n\n\n \n \n \n \n On the problem of confounders in modeling gene expression.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 35(4): 711–719. February 2019.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_problem_2019,\n\ttitle = {On the problem of confounders in modeling gene expression},\n\tvolume = {35},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bty674},\n\tabstract = {MOTIVATION: Modeling of Transcription Factor (TF) binding from both ChIP-seq and chromatin accessibility data has become prevalent in computational biology. Several models have been proposed to generate new hypotheses on transcriptional regulation. However, there is no distinct approach to derive TF binding scores from ChIP-seq and open chromatin experiments. Here, we review biases of various scoring approaches and their effects on the interpretation and reliability of predictive gene expression models.\nRESULTS: We generated predictive models for gene expression using ChIP-seq and DNase1-seq data from DEEP and ENCODE. Via randomization experiments, we identified confounders in TF gene scores derived from both ChIP-seq and DNase1-seq data. We reviewed correction approaches for both data types, which reduced the influence of identified confounders without harm to model performance. Also, our analyses highlighted further quality control measures, in addition to model performance, that may help to assure model reliability and to avoid misinterpretation in future studies.\nAVAILABILITY AND IMPLEMENTATION: The software used in this study is available online at https://github.com/SchulzLab/TEPIC.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Schmidt, Florian and Schulz, Marcel H.},\n\tmonth = feb,\n\tyear = {2019},\n\tpmid = {30084962},\n\tpmcid = {PMC6530814},\n\tkeywords = {Binding Sites, Chromatin, Chromatin Immunoprecipitation, Computational Biology, Gene Expression, High-Throughput Nucleotide Sequencing, Reproducibility of Results, Sequence Analysis, DNA, Transcription Factors},\n\tpages = {711--719},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/MH62E5UM/Schmidt und Schulz - 2019 - On the problem of confounders in modeling gene exp.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: Modeling of Transcription Factor (TF) binding from both ChIP-seq and chromatin accessibility data has become prevalent in computational biology. Several models have been proposed to generate new hypotheses on transcriptional regulation. However, there is no distinct approach to derive TF binding scores from ChIP-seq and open chromatin experiments. Here, we review biases of various scoring approaches and their effects on the interpretation and reliability of predictive gene expression models. RESULTS: We generated predictive models for gene expression using ChIP-seq and DNase1-seq data from DEEP and ENCODE. Via randomization experiments, we identified confounders in TF gene scores derived from both ChIP-seq and DNase1-seq data. We reviewed correction approaches for both data types, which reduced the influence of identified confounders without harm to model performance. Also, our analyses highlighted further quality control measures, in addition to model performance, that may help to assure model reliability and to avoid misinterpretation in future studies. AVAILABILITY AND IMPLEMENTATION: The software used in this study is available online at https://github.com/SchulzLab/TEPIC. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (9)\n \n \n
\n
\n \n \n
\n \n\n \n \n Fatemeh Behjati Ardakani, Florian Schmidt, & Marcel H. Schulz.\n\n\n \n \n \n \n Predicting transcription factor binding using ensemble random forest models.\n \n \n \n\n\n \n\n\n\n F1000Research, 7: 1603. 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{behjati_ardakani_predicting_2018,\n\ttitle = {Predicting transcription factor binding using ensemble random forest models},\n\tvolume = {7},\n\tissn = {2046-1402},\n\tdoi = {10.12688/f1000research.16200.2},\n\tabstract = {Background: Understanding the location and cell-type specific binding of Transcription Factors (TFs) is important in the study of gene regulation. Computational prediction of TF binding sites is challenging, because TFs often bind only to short DNA motifs and cell-type specific co-factors may work together with the same TF to determine binding. Here, we consider the problem of learning a general model for the prediction of TF binding using DNase1-seq data and TF motif description in form of position specific energy matrices (PSEMs). Methods: We use TF ChIP-seq data as a gold-standard for model training and evaluation. Our contribution is a novel ensemble learning approach using random forest classifiers. In the context of the ENCODE-DREAM in vivo TF binding site prediction challenge we consider different learning setups. Results: Our results indicate that the ensemble learning approach is able to better generalize across tissues and cell-types compared to individual tissue-specific classifiers or a classifier built based upon data aggregated across tissues. Furthermore, we show that incorporating DNase1-seq peaks is essential to reduce the false positive rate of TF binding predictions compared to considering the raw DNase1 signal. Conclusions: Analysis of important features reveals that the models preferentially select motifs of other TFs that are close interaction partners in existing protein protein-interaction networks. Code generated in the scope of this project is available on GitHub: https://github.com/SchulzLab/TFAnalysis (DOI: 10.5281/zenodo.1409697).},\n\tlanguage = {eng},\n\tjournal = {F1000Research},\n\tauthor = {Behjati Ardakani, Fatemeh and Schmidt, Florian and Schulz, Marcel H.},\n\tyear = {2018},\n\tpmid = {31723409},\n\tpmcid = {PMC6823902},\n\tkeywords = {Binding Sites, Chromatin accessibility, Chromatin Immunoprecipitation, DNase1-seq, ENCODE-DREAM in vivo Transcription Factor binding site prediction challenge, Ensemble learning, Indirect-binding, Nucleotide Motifs, Protein Binding, TF-complexes, Transcription Factors},\n\tpages = {1603},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/CUP3CS2K/Behjati Ardakani et al. - 2018 - Predicting transcription factor binding using ense.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Background: Understanding the location and cell-type specific binding of Transcription Factors (TFs) is important in the study of gene regulation. Computational prediction of TF binding sites is challenging, because TFs often bind only to short DNA motifs and cell-type specific co-factors may work together with the same TF to determine binding. Here, we consider the problem of learning a general model for the prediction of TF binding using DNase1-seq data and TF motif description in form of position specific energy matrices (PSEMs). Methods: We use TF ChIP-seq data as a gold-standard for model training and evaluation. Our contribution is a novel ensemble learning approach using random forest classifiers. In the context of the ENCODE-DREAM in vivo TF binding site prediction challenge we consider different learning setups. Results: Our results indicate that the ensemble learning approach is able to better generalize across tissues and cell-types compared to individual tissue-specific classifiers or a classifier built based upon data aggregated across tissues. Furthermore, we show that incorporating DNase1-seq peaks is essential to reduce the false positive rate of TF binding predictions compared to considering the raw DNase1 signal. Conclusions: Analysis of important features reveals that the models preferentially select motifs of other TFs that are close interaction partners in existing protein protein-interaction networks. Code generated in the scope of this project is available on GitHub: https://github.com/SchulzLab/TFAnalysis (DOI: 10.5281/zenodo.1409697).\n
\n\n\n
\n\n\n
\n \n\n \n \n Eva-Maria Rogg, Wesley T. Abplanalp, Corinne Bischof, David John, Marcel H. Schulz, Jaya Krishnan, Ariane Fischer, Chiara Poluzzi, Liliana Schaefer, Angelika Bonauer, Andreas M. Zeiher, & Stefanie Dimmeler.\n\n\n \n \n \n \n Analysis of Cell Type-Specific Effects of MicroRNA-92a Provides Novel Insights Into Target Regulation and Mechanism of Action.\n \n \n \n\n\n \n\n\n\n Circulation, 138(22): 2545–2558. November 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{rogg_analysis_2018,\n\ttitle = {Analysis of {Cell} {Type}-{Specific} {Effects} of {MicroRNA}-92a {Provides} {Novel} {Insights} {Into} {Target} {Regulation} and {Mechanism} of {Action}},\n\tvolume = {138},\n\tissn = {1524-4539},\n\tdoi = {10.1161/CIRCULATIONAHA.118.034598},\n\tabstract = {BACKGROUND: MicroRNAs (miRs) regulate nearly all biological pathways. Because the dysregulation of miRs can lead to disease progression, they are being explored as novel therapeutic targets. However, the cell type-specific effects of miRs in the heart are poorly understood. Thus, we assessed miR target regulation using miR-92a-3p as an example. Inhibition of miR-92a is known to improve endothelial cell function and recovery after acute myocardial infarction.\nMETHODS: miR-92a-3p was inhibited by locked nucleic acid (LNA)-based antimiR (LNA-92a) in mice after myocardial infarction. Expression of regulated genes was evaluated 3 days after myocardial infarction by RNA sequencing of isolated endothelial cells, cardiomyocytes, fibroblasts, and CD45+ hematopoietic cells.\nRESULTS: LNA-92a depleted miR-92a-3p expression in all cell types and derepressed predicted miR-92a-3p targets in a cell type-specific manner. RNAseq showed endothelial cell-specific regulation of autophagy-related genes. Imaging confirmed increased endothelial cell autophagy in LNA-92a treated relative to control animals. In vitro inhibition of miR-92a-3p augmented EC autophagy, derepressed autophagy-related gene 4a, and increased luciferase activity in autophagy-related gene 4a 3'UTR containing reporters, whereas miR-92a-3p overexpression had the opposite effect. In cardiomyocytes, LNA-92a derepressed metabolism-related genes, notably, the high-density lipoprotein transporter Abca8b. LNA-92a further increased fatty acid uptake and mitochondrial function in cardiomyocytes in vitro.\nCONCLUSIONS: Our data show that miRs have cell type-specific effects in vivo. Analysis of miR targets in cell subsets disclosed a novel function of miR-92a-3p in endothelial cell autophagy and cardiomyocyte metabolism. Because autophagy is upregulated during ischemia to supply nutrients and cardiomyocyte metabolic-switching improves available substrate utilization, these prosurvival mechanisms may diminish tissue damage.},\n\tlanguage = {eng},\n\tnumber = {22},\n\tjournal = {Circulation},\n\tauthor = {Rogg, Eva-Maria and Abplanalp, Wesley T. and Bischof, Corinne and John, David and Schulz, Marcel H. and Krishnan, Jaya and Fischer, Ariane and Poluzzi, Chiara and Schaefer, Liliana and Bonauer, Angelika and Zeiher, Andreas M. and Dimmeler, Stefanie},\n\tmonth = nov,\n\tyear = {2018},\n\tpmid = {30571345},\n\tkeywords = {3' Untranslated Regions, angiogenesis, Animals, Antagomirs, ATP-Binding Cassette Transporters, autophagy, Autophagy, cardiovascular protection, cell signaling, Disease Models, Animal, Human Umbilical Vein Endothelial Cells, Humans, Male, metabolism, Mice, Mice, Inbred C57BL, microRNA, MicroRNAs, myocardial infarction, Myocardial Infarction, Myocytes, Cardiac, Oligonucleotides, Rats},\n\tpages = {2545--2558},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/SITTMUV5/Rogg et al. - 2018 - Analysis of Cell Type-Specific Effects of MicroRNA.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: MicroRNAs (miRs) regulate nearly all biological pathways. Because the dysregulation of miRs can lead to disease progression, they are being explored as novel therapeutic targets. However, the cell type-specific effects of miRs in the heart are poorly understood. Thus, we assessed miR target regulation using miR-92a-3p as an example. Inhibition of miR-92a is known to improve endothelial cell function and recovery after acute myocardial infarction. METHODS: miR-92a-3p was inhibited by locked nucleic acid (LNA)-based antimiR (LNA-92a) in mice after myocardial infarction. Expression of regulated genes was evaluated 3 days after myocardial infarction by RNA sequencing of isolated endothelial cells, cardiomyocytes, fibroblasts, and CD45+ hematopoietic cells. RESULTS: LNA-92a depleted miR-92a-3p expression in all cell types and derepressed predicted miR-92a-3p targets in a cell type-specific manner. RNAseq showed endothelial cell-specific regulation of autophagy-related genes. Imaging confirmed increased endothelial cell autophagy in LNA-92a treated relative to control animals. In vitro inhibition of miR-92a-3p augmented EC autophagy, derepressed autophagy-related gene 4a, and increased luciferase activity in autophagy-related gene 4a 3'UTR containing reporters, whereas miR-92a-3p overexpression had the opposite effect. In cardiomyocytes, LNA-92a derepressed metabolism-related genes, notably, the high-density lipoprotein transporter Abca8b. LNA-92a further increased fatty acid uptake and mitochondrial function in cardiomyocytes in vitro. CONCLUSIONS: Our data show that miRs have cell type-specific effects in vivo. Analysis of miR targets in cell subsets disclosed a novel function of miR-92a-3p in endothelial cell autophagy and cardiomyocyte metabolism. Because autophagy is upregulated during ischemia to supply nutrients and cardiomyocyte metabolic-switching improves available substrate utilization, these prosurvival mechanisms may diminish tissue damage.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, Markus List, Engin Cukuroglu, Sebastian Köhler, Jonathan Göke, & Marcel H. Schulz.\n\n\n \n \n \n \n An ontology-based method for assessing batch effect adjustment approaches in heterogeneous datasets.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 34(17): i908–i916. September 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_ontology-based_2018,\n\ttitle = {An ontology-based method for assessing batch effect adjustment approaches in heterogeneous datasets},\n\tvolume = {34},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bty553},\n\tabstract = {MOTIVATION: International consortia such as the Genotype-Tissue Expression (GTEx) project, The Cancer Genome Atlas (TCGA) or the International Human Epigenetics Consortium (IHEC) have produced a wealth of genomic datasets with the goal of advancing our understanding of cell differentiation and disease mechanisms. However, utilizing all of these data effectively through integrative analysis is hampered by batch effects, large cell type heterogeneity and low replicate numbers. To study if batch effects across datasets can be observed and adjusted for, we analyze RNA-seq data of 215 samples from ENCODE, Roadmap, BLUEPRINT and DEEP as well as 1336 samples from GTEx and TCGA. While batch effects are a considerable issue, it is non-trivial to determine if batch adjustment leads to an improvement in data quality, especially in cases of low replicate numbers.\nRESULTS: We present a novel method for assessing the performance of batch effect adjustment methods on heterogeneous data. Our method borrows information from the Cell Ontology to establish if batch adjustment leads to a better agreement between observed pairwise similarity and similarity of cell types inferred from the ontology. A comparison of state-of-the art batch effect adjustment methods suggests that batch effects in heterogeneous datasets with low replicate numbers cannot be adequately adjusted. Better methods need to be developed, which can be assessed objectively in the framework presented here.\nAVAILABILITY AND IMPLEMENTATION: Our method is available online at https://github.com/SchulzLab/OntologyEval.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {17},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Schmidt, Florian and List, Markus and Cukuroglu, Engin and Köhler, Sebastian and Göke, Jonathan and Schulz, Marcel H.},\n\tmonth = sep,\n\tyear = {2018},\n\tpmid = {30423059},\n\tpmcid = {PMC6129283},\n\tkeywords = {Data Accuracy, Datasets as Topic, Gene Ontology, Genome, Human, Genomics, Humans, RNA, Sequence Analysis, RNA},\n\tpages = {i908--i916},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/J5F6MWYW/Schmidt et al. - 2018 - An ontology-based method for assessing batch effec.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: International consortia such as the Genotype-Tissue Expression (GTEx) project, The Cancer Genome Atlas (TCGA) or the International Human Epigenetics Consortium (IHEC) have produced a wealth of genomic datasets with the goal of advancing our understanding of cell differentiation and disease mechanisms. However, utilizing all of these data effectively through integrative analysis is hampered by batch effects, large cell type heterogeneity and low replicate numbers. To study if batch effects across datasets can be observed and adjusted for, we analyze RNA-seq data of 215 samples from ENCODE, Roadmap, BLUEPRINT and DEEP as well as 1336 samples from GTEx and TCGA. While batch effects are a considerable issue, it is non-trivial to determine if batch adjustment leads to an improvement in data quality, especially in cases of low replicate numbers. RESULTS: We present a novel method for assessing the performance of batch effect adjustment methods on heterogeneous data. Our method borrows information from the Cell Ontology to establish if batch adjustment leads to a better agreement between observed pairwise similarity and similarity of cell types inferred from the ontology. A comparison of state-of-the art batch effect adjustment methods suggests that batch effects in heterogeneous datasets with low replicate numbers cannot be adequately adjusted. Better methods need to be developed, which can be assessed objectively in the framework presented here. AVAILABILITY AND IMPLEMENTATION: Our method is available online at https://github.com/SchulzLab/OntologyEval. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Fatemeh Behjati Ardakani, Kathrin Kattler, Karl Nordström, Nina Gasparoni, Gilles Gasparoni, Sarah Fuchs, Anupam Sinha, Matthias Barann, Peter Ebert, Jonas Fischer, Barbara Hutter, Gideon Zipprich, Charles D. Imbusch, Bärbel Felder, Jürgen Eils, Benedikt Brors, Thomas Lengauer, Thomas Manke, Philip Rosenstiel, Jörn Walter, & Marcel H. Schulz.\n\n\n \n \n \n \n Integrative analysis of single-cell expression data reveals distinct regulatory states in bidirectional promoters.\n \n \n \n\n\n \n\n\n\n Epigenetics & Chromatin, 11(1): 66. November 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{behjati_ardakani_integrative_2018,\n\ttitle = {Integrative analysis of single-cell expression data reveals distinct regulatory states in bidirectional promoters},\n\tvolume = {11},\n\tissn = {1756-8935},\n\tdoi = {10.1186/s13072-018-0236-7},\n\tabstract = {BACKGROUND: Bidirectional promoters (BPs) are prevalent in eukaryotic genomes. However, it is poorly understood how the cell integrates different epigenomic information, such as transcription factor (TF) binding and chromatin marks, to drive gene expression at BPs. Single-cell sequencing technologies are revolutionizing the field of genome biology. Therefore, this study focuses on the integration of single-cell RNA-seq data with bulk ChIP-seq and other epigenetics data, for which single-cell technologies are not yet established, in the context of BPs.\nRESULTS: We performed integrative analyses of novel human single-cell RNA-seq (scRNA-seq) data with bulk ChIP-seq and other epigenetics data. scRNA-seq data revealed distinct transcription states of BPs that were previously not recognized. We find associations between these transcription states to distinct patterns in structural gene features, DNA accessibility, histone modification, DNA methylation and TF binding profiles.\nCONCLUSIONS: Our results suggest that a complex interplay of all of these elements is required to achieve BP-specific transcriptional output in this specialized promoter configuration. Further, our study implies that novel statistical methods can be developed to deconvolute masked subpopulations of cells measured with different bulk epigenomic assays using scRNA-seq data.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Epigenetics \\& Chromatin},\n\tauthor = {Behjati Ardakani, Fatemeh and Kattler, Kathrin and Nordström, Karl and Gasparoni, Nina and Gasparoni, Gilles and Fuchs, Sarah and Sinha, Anupam and Barann, Matthias and Ebert, Peter and Fischer, Jonas and Hutter, Barbara and Zipprich, Gideon and Imbusch, Charles D. and Felder, Bärbel and Eils, Jürgen and Brors, Benedikt and Lengauer, Thomas and Manke, Thomas and Rosenstiel, Philip and Walter, Jörn and Schulz, Marcel H.},\n\tmonth = nov,\n\tyear = {2018},\n\tpmid = {30414612},\n\tpmcid = {PMC6230222},\n\tkeywords = {Bidirectional genes, Chromatin Assembly and Disassembly, DNA Methylation, Epigenesis, Genetic, Epigenetics, Hep G2 Cells, Histone Code, Humans, Promoter Regions, Genetic, Single-Cell Analysis, Single-cell RNA-seq, Transcription Factors, Transcriptional Activation},\n\tpages = {66},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/TC6SIMSV/Behjati Ardakani et al. - 2018 - Integrative analysis of single-cell expression dat.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Bidirectional promoters (BPs) are prevalent in eukaryotic genomes. However, it is poorly understood how the cell integrates different epigenomic information, such as transcription factor (TF) binding and chromatin marks, to drive gene expression at BPs. Single-cell sequencing technologies are revolutionizing the field of genome biology. Therefore, this study focuses on the integration of single-cell RNA-seq data with bulk ChIP-seq and other epigenetics data, for which single-cell technologies are not yet established, in the context of BPs. RESULTS: We performed integrative analyses of novel human single-cell RNA-seq (scRNA-seq) data with bulk ChIP-seq and other epigenetics data. scRNA-seq data revealed distinct transcription states of BPs that were previously not recognized. We find associations between these transcription states to distinct patterns in structural gene features, DNA accessibility, histone modification, DNA methylation and TF binding profiles. CONCLUSIONS: Our results suggest that a complex interplay of all of these elements is required to achieve BP-specific transcriptional output in this specialized promoter configuration. Further, our study implies that novel statistical methods can be developed to deconvolute masked subpopulations of cells measured with different bulk epigenomic assays using scRNA-seq data.\n
\n\n\n
\n\n\n
\n \n\n \n \n Dilip A. Durai, & Marcel H. Schulz.\n\n\n \n \n \n \n In silico read normalization using set multi-cover optimization.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 34(19): 3273–3280. October 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{durai_silico_2018,\n\ttitle = {In silico read normalization using set multi-cover optimization},\n\tvolume = {34},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bty307},\n\tabstract = {MOTIVATION: De Bruijn graphs are a common assembly data structure for sequencing datasets. But with the advances in sequencing technologies, assembling high coverage datasets has become a computational challenge. Read normalization, which removes redundancy in datasets, is widely applied to reduce resource requirements. Current normalization algorithms, though efficient, provide no guarantee to preserve important k-mers that form connections between regions in the graph.\nRESULTS: Here, normalization is phrased as a set multi-cover problem on reads and a heuristic algorithm, Optimized Read Normalization Algorithm (ORNA), is proposed. ORNA normalizes to the minimum number of reads required to retain all k-mers and their relative k-mer abundances from the original dataset. Hence, all connections from the original graph are preserved. ORNA was tested on various RNA-seq datasets with different coverage values. It was compared to the current normalization algorithms and was found to be performing better. Normalizing error corrected data allows for more accurate assemblies compared to the normalized uncorrected dataset. Further, an application is proposed in which multiple datasets are combined and normalized to predict novel transcripts that would have been missed otherwise. Finally, ORNA is a general purpose normalization algorithm that is fast and significantly reduces datasets with loss of assembly quality in between [1, 30]\\% depending on reduction stringency.\nAVAILABILITY AND IMPLEMENTATION: ORNA is available at https://github.com/SchulzLab/ORNA.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {19},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Durai, Dilip A. and Schulz, Marcel H.},\n\tmonth = oct,\n\tyear = {2018},\n\tpmid = {29912280},\n\tpmcid = {PMC6157080},\n\tkeywords = {Algorithms, Computational Biology, Computer Simulation, Sequence Analysis, RNA},\n\tpages = {3273--3280},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/UGNYIE69/Durai und Schulz - 2018 - In silico read normalization using set multi-cover.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: De Bruijn graphs are a common assembly data structure for sequencing datasets. But with the advances in sequencing technologies, assembling high coverage datasets has become a computational challenge. Read normalization, which removes redundancy in datasets, is widely applied to reduce resource requirements. Current normalization algorithms, though efficient, provide no guarantee to preserve important k-mers that form connections between regions in the graph. RESULTS: Here, normalization is phrased as a set multi-cover problem on reads and a heuristic algorithm, Optimized Read Normalization Algorithm (ORNA), is proposed. ORNA normalizes to the minimum number of reads required to retain all k-mers and their relative k-mer abundances from the original dataset. Hence, all connections from the original graph are preserved. ORNA was tested on various RNA-seq datasets with different coverage values. It was compared to the current normalization algorithms and was found to be performing better. Normalizing error corrected data allows for more accurate assemblies compared to the normalized uncorrected dataset. Further, an application is proposed in which multiple datasets are combined and normalized to predict novel transcripts that would have been missed otherwise. Finally, ORNA is a general purpose normalization algorithm that is fast and significantly reduces datasets with loss of assembly quality in between [1, 30]% depending on reduction stringency. AVAILABILITY AND IMPLEMENTATION: ORNA is available at https://github.com/SchulzLab/ORNA. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Azim Dehghani Amirabad, Pathmanaban Ramasamy, Marina Wierz, Karl Nordström, Sonja M. Kessler, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Transgenic expression of the RNA binding protein IMP2 stabilizes miRNA targets in murine microsteatosis.\n \n \n \n\n\n \n\n\n\n Biochimica Et Biophysica Acta. Molecular Basis of Disease, 1864(10): 3099–3108. October 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{dehghani_amirabad_transgenic_2018,\n\ttitle = {Transgenic expression of the {RNA} binding protein {IMP2} stabilizes {miRNA} targets in murine microsteatosis},\n\tvolume = {1864},\n\tissn = {1879-260X},\n\tdoi = {10.1016/j.bbadis.2018.05.024},\n\tabstract = {Adult expression of IMP2 is often associated with several types of disease and cancer. The RNA binding protein IMP2 binds and stabilizes the IGF2 mRNA as well as hundreds of other transcripts during development. To gain insight into the molecular action of IMP2 and its contribution to disease in context of adult cellular metabolism, we analyze transgenic overexpression of IMP2 in mouse livers, which has been shown to induce a steatosis-like phenotype and enhanced risk to develop hepatocellular carcinoma (HCC). Our data show up-regulation of several HCC marker genes and miRNAs (miR438-3p and miR151-5p). To characterize the impact of miRNAs to their targets, integrative analysis of transcriptome-and miRNAome-dynamics in combination with IMP2 target prediction was carried out. Our analyses show that targets of expressed miRNAs become accumulated in the case that these transcripts have positive IMP2 binding prediction. Therefore, our data indicates that overexpression of IMP2 alters the regulatory capacity of many miRNAs and we conclude that IMP2 competes with miRNAs for binding sites on thousands of transcripts. As a result, our data implicates that overexpression of IMP2 has distinct effects to the regulatory capacity of miRNAs with yet unknown consequences for translational efficiency.},\n\tlanguage = {eng},\n\tnumber = {10},\n\tjournal = {Biochimica Et Biophysica Acta. Molecular Basis of Disease},\n\tauthor = {Dehghani Amirabad, Azim and Ramasamy, Pathmanaban and Wierz, Marina and Nordström, Karl and Kessler, Sonja M. and Schulz, Marcel H. and Simon, Martin},\n\tmonth = oct,\n\tyear = {2018},\n\tpmid = {29859241},\n\tkeywords = {Animals, Binding Sites, DLK1/DIO3, Fatty Liver, Gene Expression Profiling, Gene Expression Regulation, Neoplastic, Gene Regulatory Networks, High-Throughput Nucleotide Sequencing, Humans, IGF2, IMP2, Mice, Mice, Transgenic, miRNA, Murine steatosis, p62, RNA-Binding Proteins, Sequence Analysis, DNA, Transcriptome, Up-Regulation},\n\tpages = {3099--3108},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/MAXXXLLZ/Dehghani Amirabad et al. - 2018 - Transgenic expression of the RNA binding protein I.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Adult expression of IMP2 is often associated with several types of disease and cancer. The RNA binding protein IMP2 binds and stabilizes the IGF2 mRNA as well as hundreds of other transcripts during development. To gain insight into the molecular action of IMP2 and its contribution to disease in context of adult cellular metabolism, we analyze transgenic overexpression of IMP2 in mouse livers, which has been shown to induce a steatosis-like phenotype and enhanced risk to develop hepatocellular carcinoma (HCC). Our data show up-regulation of several HCC marker genes and miRNAs (miR438-3p and miR151-5p). To characterize the impact of miRNAs to their targets, integrative analysis of transcriptome-and miRNAome-dynamics in combination with IMP2 target prediction was carried out. Our analyses show that targets of expressed miRNAs become accumulated in the case that these transcripts have positive IMP2 binding prediction. Therefore, our data indicates that overexpression of IMP2 alters the regulatory capacity of many miRNAs and we conclude that IMP2 competes with miRNAs for binding sites on thousands of transcripts. As a result, our data implicates that overexpression of IMP2 has distinct effects to the regulatory capacity of miRNAs with yet unknown consequences for translational efficiency.\n
\n\n\n
\n\n\n
\n \n\n \n \n Andrea Hornakova, Markus List, Jilles Vreeken, & Marcel H. Schulz.\n\n\n \n \n \n \n JAMI: fast computation of conditional mutual information for ceRNA network analysis.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 34(17): 3050–3051. September 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{hornakova_jami_2018,\n\ttitle = {{JAMI}: fast computation of conditional mutual information for {ceRNA} network analysis},\n\tvolume = {34},\n\tissn = {1367-4811},\n\tshorttitle = {{JAMI}},\n\tdoi = {10.1093/bioinformatics/bty221},\n\tabstract = {MOTIVATION: Genome-wide measurements of paired miRNA and gene expression data have enabled the prediction of competing endogenous RNAs (ceRNAs). It has been shown that the sponge effect mediated by protein-coding as well as non-coding ceRNAs can play an important regulatory role in the cell in health and disease. Therefore, many computational methods for the computational identification of ceRNAs have been suggested. In particular, methods based on Conditional Mutual Information (CMI) have shown promising results. However, the currently available implementation is slow and cannot be used to perform computations on a large scale.\nRESULTS: Here, we present JAMI, a Java tool that uses a non-parametric estimator for CMI values from gene and miRNA expression data. We show that JAMI speeds up the computation of ceRNA networks by a factor of ∼70 compared to currently available implementations. Further, JAMI supports multi-threading to make use of common multi-core architectures for further performance gain.\nREQUIREMENTS: Java 8.\nAVAILABILITY AND IMPLEMENTATION: JAMI is available as open-source software from https://github.com/SchulzLab/JAMI.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {17},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Hornakova, Andrea and List, Markus and Vreeken, Jilles and Schulz, Marcel H.},\n\tmonth = sep,\n\tyear = {2018},\n\tpmid = {29659721},\n\tpmcid = {PMC6129307},\n\tkeywords = {Gene Regulatory Networks, RNA, Software},\n\tpages = {3050--3051},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/W6NXX86N/Hornakova et al. - 2018 - JAMI fast computation of conditional mutual infor.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: Genome-wide measurements of paired miRNA and gene expression data have enabled the prediction of competing endogenous RNAs (ceRNAs). It has been shown that the sponge effect mediated by protein-coding as well as non-coding ceRNAs can play an important regulatory role in the cell in health and disease. Therefore, many computational methods for the computational identification of ceRNAs have been suggested. In particular, methods based on Conditional Mutual Information (CMI) have shown promising results. However, the currently available implementation is slow and cannot be used to perform computations on a large scale. RESULTS: Here, we present JAMI, a Java tool that uses a non-parametric estimator for CMI values from gene and miRNA expression data. We show that JAMI speeds up the computation of ceRNA networks by a factor of ∼70 compared to currently available implementations. Further, JAMI supports multi-threading to make use of common multi-core architectures for further performance gain. REQUIREMENTS: Java 8. AVAILABILITY AND IMPLEMENTATION: JAMI is available as open-source software from https://github.com/SchulzLab/JAMI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcello Pirritano, Ulrike Götz, Sivarajan Karunanithi, Karl Nordström, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Environmental Temperature Controls Accumulation of Transacting siRNAs Involved in Heterochromatin Formation.\n \n \n \n\n\n \n\n\n\n Genes, 9(2): 117. February 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{pirritano_environmental_2018,\n\ttitle = {Environmental {Temperature} {Controls} {Accumulation} of {Transacting} {siRNAs} {Involved} in {Heterochromatin} {Formation}},\n\tvolume = {9},\n\tissn = {2073-4425},\n\tdoi = {10.3390/genes9020117},\n\tabstract = {Genes or alleles can interact by small RNAs in a homology dependent manner meaning that short interfering (siRNAs) can act in trans at the chromatin level producing stable and heritable silencing phenotypes. Because of the puzzling data on endogenous paramutations, their impact contributing to adaptive evolution in a Lamarckian manner remains unknown. An increasing number of studies characterizes the underlying siRNA accumulation pathways using transgene experiments. Also in the ciliate Paramecium tetraurelia, we induce trans silencing on the chromatin level by injection of truncated transgenes. Here, we characterize the efficiency of this mechanism at different temperatures showing that silencing of the endogenous genes is temperature dependent. Analyzing different transgene constructs at different copy numbers, we dissected whether silencing efficiency is due to varying precursor RNAs or siRNA accumulation. Our data shows that silencing efficiency correlates with more efficient accumulation of primary siRNAs at higher temperatures rather than higher expression of precursor RNAs. Due to higher primary levels, secondary siRNAs also show temperature dependency and interestingly increase their relative proportion to primary siRNAs. Our data shows that efficient trans silencing on the chromatin level in P. tetraurelia depends on environmental parameters, thus being an important epigenetic factor limiting regulatory effects of siRNAs.},\n\tlanguage = {eng},\n\tnumber = {2},\n\tjournal = {Genes},\n\tauthor = {Pirritano, Marcello and Götz, Ulrike and Karunanithi, Sivarajan and Nordström, Karl and Schulz, Marcel H. and Simon, Martin},\n\tmonth = feb,\n\tyear = {2018},\n\tpmid = {29466322},\n\tpmcid = {PMC5852613},\n\tkeywords = {chromatin, environment, RNA interference, transitivity},\n\tpages = {117},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/YNC9R6RM/Pirritano et al. - 2018 - Environmental Temperature Controls Accumulation of.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Genes or alleles can interact by small RNAs in a homology dependent manner meaning that short interfering (siRNAs) can act in trans at the chromatin level producing stable and heritable silencing phenotypes. Because of the puzzling data on endogenous paramutations, their impact contributing to adaptive evolution in a Lamarckian manner remains unknown. An increasing number of studies characterizes the underlying siRNA accumulation pathways using transgene experiments. Also in the ciliate Paramecium tetraurelia, we induce trans silencing on the chromatin level by injection of truncated transgenes. Here, we characterize the efficiency of this mechanism at different temperatures showing that silencing of the endogenous genes is temperature dependent. Analyzing different transgene constructs at different copy numbers, we dissected whether silencing efficiency is due to varying precursor RNAs or siRNA accumulation. Our data shows that silencing efficiency correlates with more efficient accumulation of primary siRNAs at higher temperatures rather than higher expression of precursor RNAs. Due to higher primary levels, secondary siRNAs also show temperature dependency and interestingly increase their relative proportion to primary siRNAs. Our data shows that efficient trans silencing on the chromatin level in P. tetraurelia depends on environmental parameters, thus being an important epigenetic factor limiting regulatory effects of siRNAs.\n
\n\n\n
\n\n\n
\n \n\n \n \n Katrin Grosser, Pathmanaban Ramasamy, Azim Dehghani Amirabad, Marcel H. Schulz, Gilles Gasparoni, Martin Simon, & Martina Schrallhammer.\n\n\n \n \n \n \n More than the \"Killer Trait\": Infection with the Bacterial Endosymbiont Caedibacter taeniospiralis Causes Transcriptomic Modulation in Paramecium Host.\n \n \n \n\n\n \n\n\n\n Genome Biology and Evolution, 10(2): 646–656. February 2018.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{grosser_more_2018,\n\ttitle = {More than the "{Killer} {Trait}": {Infection} with the {Bacterial} {Endosymbiont} {Caedibacter} taeniospiralis {Causes} {Transcriptomic} {Modulation} in {Paramecium} {Host}},\n\tvolume = {10},\n\tissn = {1759-6653},\n\tshorttitle = {More than the "{Killer} {Trait}"},\n\tdoi = {10.1093/gbe/evy024},\n\tabstract = {Endosymbiosis is a widespread phenomenon and hosts of bacterial endosymbionts can be found all-over the eukaryotic tree of life. Likely, this evolutionary success is connected to the altered phenotype arising from a symbiotic association. The potential variety of symbiont's contributions to new characteristics or abilities of host organisms are largely unstudied. Addressing this aspect, we focused on an obligate bacterial endosymbiont that confers an intraspecific killer phenotype to its host. The symbiosis between Paramecium tetraurelia and Caedibacter taeniospiralis, living in the host's cytoplasm, enables the infected paramecia to release Caedibacter symbionts, which can simultaneously produce a peculiar protein structure and a toxin. The ingestion of bacteria that harbor both components leads to the death of symbiont-free congeners. Thus, the symbiosis provides Caedibacter-infected cells a competitive advantage, the "killer trait." We characterized the adaptive gene expression patterns in symbiont-harboring Paramecium as a second symbiosis-derived aspect next to the killer phenotype. Comparative transcriptomics of infected P. tetraurelia and genetically identical symbiont-free cells confirmed altered gene expression in the symbiont-bearing line. Our results show up-regulation of specific metabolic and heat shock genes whereas down-regulated genes were involved in signaling pathways and cell cycle regulation. Functional analyses to validate the transcriptomics results demonstrated that the symbiont increases host density hence providing a fitness advantage. Comparative transcriptomics shows gene expression modulation of a ciliate caused by its bacterial endosymbiont thus revealing new adaptive advantages of the symbiosis. Caedibacter taeniospiralis apparently increases its host fitness via manipulation of metabolic pathways and cell cycle control.},\n\tlanguage = {eng},\n\tnumber = {2},\n\tjournal = {Genome Biology and Evolution},\n\tauthor = {Grosser, Katrin and Ramasamy, Pathmanaban and Amirabad, Azim Dehghani and Schulz, Marcel H. and Gasparoni, Gilles and Simon, Martin and Schrallhammer, Martina},\n\tmonth = feb,\n\tyear = {2018},\n\tpmid = {29390087},\n\tpmcid = {PMC5814942},\n\tkeywords = {ciliate, fitness advantage, Gammaproteobacteria, Gene Expression Regulation, Metabolic Networks and Pathways, mutualist, Paramecium, parasite, Phenotype, R-body, RNA-Seq, Sequence Analysis, RNA, Symbiosis, Transcriptome},\n\tpages = {646--656},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/HGYJSPW7/Grosser et al. - 2018 - More than the Killer Trait Infection with the B.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Endosymbiosis is a widespread phenomenon and hosts of bacterial endosymbionts can be found all-over the eukaryotic tree of life. Likely, this evolutionary success is connected to the altered phenotype arising from a symbiotic association. The potential variety of symbiont's contributions to new characteristics or abilities of host organisms are largely unstudied. Addressing this aspect, we focused on an obligate bacterial endosymbiont that confers an intraspecific killer phenotype to its host. The symbiosis between Paramecium tetraurelia and Caedibacter taeniospiralis, living in the host's cytoplasm, enables the infected paramecia to release Caedibacter symbionts, which can simultaneously produce a peculiar protein structure and a toxin. The ingestion of bacteria that harbor both components leads to the death of symbiont-free congeners. Thus, the symbiosis provides Caedibacter-infected cells a competitive advantage, the \"killer trait.\" We characterized the adaptive gene expression patterns in symbiont-harboring Paramecium as a second symbiosis-derived aspect next to the killer phenotype. Comparative transcriptomics of infected P. tetraurelia and genetically identical symbiont-free cells confirmed altered gene expression in the symbiont-bearing line. Our results show up-regulation of specific metabolic and heat shock genes whereas down-regulated genes were involved in signaling pathways and cell cycle regulation. Functional analyses to validate the transcriptomics results demonstrated that the symbiont increases host density hence providing a fitness advantage. Comparative transcriptomics shows gene expression modulation of a ciliate caused by its bacterial endosymbiont thus revealing new adaptive advantages of the symbiosis. Caedibacter taeniospiralis apparently increases its host fitness via manipulation of metabolic pathways and cell cycle control.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n Christina S. Schultheiss, Stephan Laggai, Beate Czepukojc, Usama K. Hussein, Markus List, Ahmad Barghash, Sascha Tierling, Kevan Hosseini, Nicole Golob-Schwarzl, Juliane Pokorny, Nina Hachenthal, Marcel Schulz, Volkhard Helms, Jörn Walter, Vincent Zimmer, Frank Lammert, Rainer M. Bohle, Luisa Dandolo, Johannes Haybaeck, Alexandra K. Kiemer, & Sonja M. Kessler.\n\n\n \n \n \n \n The long non-coding RNA H19 suppresses carcinogenesis and chemoresistance in hepatocellular carcinoma.\n \n \n \n\n\n \n\n\n\n Cell Stress, 1(1): 37–54. August 2017.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schultheiss_long_2017,\n\ttitle = {The long non-coding {RNA} {H19} suppresses carcinogenesis and chemoresistance in hepatocellular carcinoma},\n\tvolume = {1},\n\tissn = {2523-0204},\n\tdoi = {10.15698/cst2017.10.105},\n\tabstract = {The long non-coding RNA (lncRNA) H19 represents a maternally expressed and epigenetically regulated imprinted gene product and is discussed to have either tumor-promoting or tumor-suppressive actions. Recently, H19 was shown to be regulated under inflammatory conditions. Therefore, aim of this study was to determine the function of H19 in hepatocellular carcinoma (HCC), an inflammation-associated type of tumor. In four different human HCC patient cohorts H19 was distinctly downregulated in tumor tissue compared to normal or non-tumorous adjacent tissue. We therefore determined the action of H19 in three different human hepatoma cell lines (HepG2, Plc/Prf5, and Huh7). Clonogenicity and proliferation assays showed that H19 overexpression could suppress tumor cell survival and proliferation after treatment with either sorafenib or doxorubicin, suggesting chemosensitizing actions of H19. Since HCC displays a highly chemoresistant tumor entity, cell lines resistant to doxorubicin or sorafenib were established. In all six chemoresistant cell lines H19 expression was significantly downregulated. The promoter methylation of the H19 gene was significantly different in chemoresistant cell lines compared to their sensitive counterparts. Chemoresistant cells were sensitized after H19 overexpression by either increasing the cytotoxic action of doxorubicin or decreasing cell proliferation upon sorafenib treatment. An H19 knockout mouse model (H19Δ3) showed increased tumor development and tumor cell proliferation after treatment with the carcinogen diethylnitrosamine (DEN) independent of the reciprocally imprinted insulin-like growth factor 2 (IGF2). In conclusion, H19 suppresses hepatocarcinogenesis, hepatoma cell growth, and HCC chemoresistance. Thus, mimicking H19 action might be a potential target to overcome chemoresistance in future HCC therapy.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Cell Stress},\n\tauthor = {Schultheiss, Christina S. and Laggai, Stephan and Czepukojc, Beate and Hussein, Usama K. and List, Markus and Barghash, Ahmad and Tierling, Sascha and Hosseini, Kevan and Golob-Schwarzl, Nicole and Pokorny, Juliane and Hachenthal, Nina and Schulz, Marcel and Helms, Volkhard and Walter, Jörn and Zimmer, Vincent and Lammert, Frank and Bohle, Rainer M. and Dandolo, Luisa and Haybaeck, Johannes and Kiemer, Alexandra K. and Kessler, Sonja M.},\n\tmonth = aug,\n\tyear = {2017},\n\tpmid = {31225433},\n\tpmcid = {PMC6551655},\n\tkeywords = {Bi-PROF, ELAVL1/HuR, flow cytometry, Ki67, loss of imprinting, miR-675, SNuPE},\n\tpages = {37--54},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/UX8YIA7K/Schultheiss et al. - 2017 - The long non-coding RNA H19 suppresses carcinogene.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The long non-coding RNA (lncRNA) H19 represents a maternally expressed and epigenetically regulated imprinted gene product and is discussed to have either tumor-promoting or tumor-suppressive actions. Recently, H19 was shown to be regulated under inflammatory conditions. Therefore, aim of this study was to determine the function of H19 in hepatocellular carcinoma (HCC), an inflammation-associated type of tumor. In four different human HCC patient cohorts H19 was distinctly downregulated in tumor tissue compared to normal or non-tumorous adjacent tissue. We therefore determined the action of H19 in three different human hepatoma cell lines (HepG2, Plc/Prf5, and Huh7). Clonogenicity and proliferation assays showed that H19 overexpression could suppress tumor cell survival and proliferation after treatment with either sorafenib or doxorubicin, suggesting chemosensitizing actions of H19. Since HCC displays a highly chemoresistant tumor entity, cell lines resistant to doxorubicin or sorafenib were established. In all six chemoresistant cell lines H19 expression was significantly downregulated. The promoter methylation of the H19 gene was significantly different in chemoresistant cell lines compared to their sensitive counterparts. Chemoresistant cells were sensitized after H19 overexpression by either increasing the cytotoxic action of doxorubicin or decreasing cell proliferation upon sorafenib treatment. An H19 knockout mouse model (H19Δ3) showed increased tumor development and tumor cell proliferation after treatment with the carcinogen diethylnitrosamine (DEN) independent of the reciprocally imprinted insulin-like growth factor 2 (IGF2). In conclusion, H19 suppresses hepatocarcinogenesis, hepatoma cell growth, and HCC chemoresistance. Thus, mimicking H19 action might be a potential target to overcome chemoresistance in future HCC therapy.\n
\n\n\n
\n\n\n
\n \n\n \n \n Tim Kehl, Lara Schneider, Florian Schmidt, Daniel Stöckel, Nico Gerstner, Christina Backes, Eckart Meese, Andreas Keller, Marcel H. Schulz, & Hans-Peter Lenhof.\n\n\n \n \n \n \n RegulatorTrail: a web service for the identification of key transcriptional regulators.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 45(W1): W146–W153. July 2017.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{kehl_regulatortrail_2017,\n\ttitle = {{RegulatorTrail}: a web service for the identification of key transcriptional regulators},\n\tvolume = {45},\n\tissn = {1362-4962},\n\tshorttitle = {{RegulatorTrail}},\n\tdoi = {10.1093/nar/gkx350},\n\tabstract = {Transcriptional regulators such as transcription factors and chromatin modifiers play a central role in most biological processes. Alterations in their activities have been observed in many diseases, e.g. cancer. Hence, it is of utmost importance to evaluate and assess the effects of transcriptional regulators on natural and pathogenic processes. Here, we present RegulatorTrail, a web service that provides rich functionality for the identification and prioritization of key transcriptional regulators that have a strong impact on, e.g. pathological processes. RegulatorTrail offers eight methods that use regulator binding information in combination with transcriptomic or epigenomic data to infer the most influential regulators. Our web service not only provides an intuitive web interface, but also a well-documented RESTful API that allows for a straightforward integration into third-party workflows. The presented case studies highlight the capabilities of our web service and demonstrate its potential for the identification of influential regulators: we successfully identified regulators that might explain the increased malignancy in metastatic melanoma compared to primary tumors, as well as important regulators in macrophages. RegulatorTrail is freely accessible at: https://regulatortrail.bioinf.uni-sb.de/.},\n\tlanguage = {eng},\n\tnumber = {W1},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Kehl, Tim and Schneider, Lara and Schmidt, Florian and Stöckel, Daniel and Gerstner, Nico and Backes, Christina and Meese, Eckart and Keller, Andreas and Schulz, Marcel H. and Lenhof, Hans-Peter},\n\tmonth = jul,\n\tyear = {2017},\n\tpmid = {28472408},\n\tpmcid = {PMC5570139},\n\tkeywords = {Chromatin, Epigenesis, Genetic, Gene Expression Profiling, Humans, Internet, Macrophages, Melanoma, Neoplasm Metastasis, Software, Transcription Factors, Workflow},\n\tpages = {W146--W153},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/24EYS5CT/Kehl et al. - 2017 - RegulatorTrail a web service for the identificati.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Transcriptional regulators such as transcription factors and chromatin modifiers play a central role in most biological processes. Alterations in their activities have been observed in many diseases, e.g. cancer. Hence, it is of utmost importance to evaluate and assess the effects of transcriptional regulators on natural and pathogenic processes. Here, we present RegulatorTrail, a web service that provides rich functionality for the identification and prioritization of key transcriptional regulators that have a strong impact on, e.g. pathological processes. RegulatorTrail offers eight methods that use regulator binding information in combination with transcriptomic or epigenomic data to infer the most influential regulators. Our web service not only provides an intuitive web interface, but also a well-documented RESTful API that allows for a straightforward integration into third-party workflows. The presented case studies highlight the capabilities of our web service and demonstrate its potential for the identification of influential regulators: we successfully identified regulators that might explain the increased malignancy in metastatic melanoma compared to primary tumors, as well as important regulators in macrophages. RegulatorTrail is freely accessible at: https://regulatortrail.bioinf.uni-sb.de/.\n
\n\n\n
\n\n\n
\n \n\n \n \n Florian Schmidt, Nina Gasparoni, Gilles Gasparoni, Kathrin Gianmoena, Cristina Cadenas, Julia K. Polansky, Peter Ebert, Karl Nordström, Matthias Barann, Anupam Sinha, Sebastian Fröhler, Jieyi Xiong, Azim Dehghani Amirabad, Fatemeh Behjati Ardakani, Barbara Hutter, Gideon Zipprich, Bärbel Felder, Jürgen Eils, Benedikt Brors, Wei Chen, Jan G. Hengstler, Alf Hamann, Thomas Lengauer, Philip Rosenstiel, Jörn Walter, & Marcel H. Schulz.\n\n\n \n \n \n \n Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 45(1): 54–66. January 2017.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schmidt_combining_2017,\n\ttitle = {Combining transcription factor binding affinities with open-chromatin data for accurate gene expression prediction},\n\tvolume = {45},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkw1061},\n\tabstract = {The binding and contribution of transcription factors (TF) to cell specific gene expression is often deduced from open-chromatin measurements to avoid costly TF ChIP-seq assays. Thus, it is important to develop computational methods for accurate TF binding prediction in open-chromatin regions (OCRs). Here, we report a novel segmentation-based method, TEPIC, to predict TF binding by combining sets of OCRs with position weight matrices. TEPIC can be applied to various open-chromatin data, e.g. DNaseI-seq and NOMe-seq. Additionally, Histone-Marks (HMs) can be used to identify candidate TF binding sites. TEPIC computes TF affinities and uses open-chromatin/HM signal intensity as quantitative measures of TF binding strength. Using machine learning, we find low affinity binding sites to improve our ability to explain gene expression variability compared to the standard presence/absence classification of binding sites. Further, we show that both footprints and peaks capture essential TF binding events and lead to a good prediction performance. In our application, gene-based scores computed by TEPIC with one open-chromatin assay nearly reach the quality of several TF ChIP-seq data sets. Finally, these scores correctly predict known transcriptional regulators as illustrated by the application to novel DNaseI-seq and NOMe-seq data for primary human hepatocytes and CD4+ T-cells, respectively.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Schmidt, Florian and Gasparoni, Nina and Gasparoni, Gilles and Gianmoena, Kathrin and Cadenas, Cristina and Polansky, Julia K. and Ebert, Peter and Nordström, Karl and Barann, Matthias and Sinha, Anupam and Fröhler, Sebastian and Xiong, Jieyi and Dehghani Amirabad, Azim and Behjati Ardakani, Fatemeh and Hutter, Barbara and Zipprich, Gideon and Felder, Bärbel and Eils, Jürgen and Brors, Benedikt and Chen, Wei and Hengstler, Jan G. and Hamann, Alf and Lengauer, Thomas and Rosenstiel, Philip and Walter, Jörn and Schulz, Marcel H.},\n\tmonth = jan,\n\tyear = {2017},\n\tpmid = {27899623},\n\tpmcid = {PMC5224477},\n\tkeywords = {Algorithms, Binding Sites, CD4-Positive T-Lymphocytes, Cell Line, Cell Line, Tumor, Chromatin, Chromatin Assembly and Disassembly, DNA, Gene Expression Regulation, Hep G2 Cells, Hepatocytes, Histones, Human Embryonic Stem Cells, Humans, K562 Cells, Machine Learning, Organ Specificity, Primary Cell Culture, Principal Component Analysis, Protein Binding, Transcription Factors},\n\tpages = {54--66},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/3DCIKS5Z/Schmidt et al. - 2017 - Combining transcription factor binding affinities .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The binding and contribution of transcription factors (TF) to cell specific gene expression is often deduced from open-chromatin measurements to avoid costly TF ChIP-seq assays. Thus, it is important to develop computational methods for accurate TF binding prediction in open-chromatin regions (OCRs). Here, we report a novel segmentation-based method, TEPIC, to predict TF binding by combining sets of OCRs with position weight matrices. TEPIC can be applied to various open-chromatin data, e.g. DNaseI-seq and NOMe-seq. Additionally, Histone-Marks (HMs) can be used to identify candidate TF binding sites. TEPIC computes TF affinities and uses open-chromatin/HM signal intensity as quantitative measures of TF binding strength. Using machine learning, we find low affinity binding sites to improve our ability to explain gene expression variability compared to the standard presence/absence classification of binding sites. Further, we show that both footprints and peaks capture essential TF binding events and lead to a good prediction performance. In our application, gene-based scores computed by TEPIC with one open-chromatin assay nearly reach the quality of several TF ChIP-seq data sets. Finally, these scores correctly predict known transcriptional regulators as illustrated by the application to novel DNaseI-seq and NOMe-seq data for primary human hepatocytes and CD4+ T-cells, respectively.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2016\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n Hendrik G. Stunnenberg, International Human Epigenome Consortium, & Martin Hirst.\n\n\n \n \n \n \n The International Human Epigenome Consortium: A Blueprint for Scientific Collaboration and Discovery.\n \n \n \n\n\n \n\n\n\n Cell, 167(5): 1145–1149. November 2016.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{stunnenberg_international_2016,\n\ttitle = {The {International} {Human} {Epigenome} {Consortium}: {A} {Blueprint} for {Scientific} {Collaboration} and {Discovery}},\n\tvolume = {167},\n\tissn = {1097-4172},\n\tshorttitle = {The {International} {Human} {Epigenome} {Consortium}},\n\tdoi = {10.1016/j.cell.2016.11.007},\n\tabstract = {The International Human Epigenome Consortium (IHEC) coordinates the generation of a catalog of high-resolution reference epigenomes of major primary human cell types. The studies now presented (see the Cell Press IHEC web portal at http://www.cell.com/consortium/IHEC) highlight the coordinated achievements of IHEC teams to gather and interpret comprehensive epigenomic datasets to gain insights in the epigenetic control of cell states relevant for human health and disease. PAPERCLIP.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Cell},\n\tauthor = {Stunnenberg, Hendrik G. and {International Human Epigenome Consortium} and Hirst, Martin},\n\tmonth = nov,\n\tyear = {2016},\n\tpmid = {27863232},\n\tkeywords = {Databases, Genetic, Disease, DNA Methylation, Epigenesis, Genetic, Epigenomics, Genome, Human, Histone Code, Humans},\n\tpages = {1145--1149},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/JTJDHDQM/Stunnenberg et al. - 2016 - The International Human Epigenome Consortium A Bl.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The International Human Epigenome Consortium (IHEC) coordinates the generation of a catalog of high-resolution reference epigenomes of major primary human cell types. The studies now presented (see the Cell Press IHEC web portal at http://www.cell.com/consortium/IHEC) highlight the coordinated achievements of IHEC teams to gather and interpret comprehensive epigenomic datasets to gain insights in the epigenetic control of cell states relevant for human health and disease. PAPERCLIP.\n
\n\n\n
\n\n\n
\n \n\n \n \n Pawel Durek, Karl Nordström, Gilles Gasparoni, Abdulrahman Salhab, Christopher Kressler, Melanie Almeida, Kevin Bassler, Thomas Ulas, Florian Schmidt, Jieyi Xiong, Petar Glažar, Filippos Klironomos, Anupam Sinha, Sarah Kinkley, Xinyi Yang, Laura Arrigoni, Azim Dehghani Amirabad, Fatemeh Behjati Ardakani, Lars Feuerbach, Oliver Gorka, Peter Ebert, Fabian Müller, Na Li, Stefan Frischbutter, Stephan Schlickeiser, Carla Cendon, Sebastian Fröhler, Bärbel Felder, Nina Gasparoni, Charles D. Imbusch, Barbara Hutter, Gideon Zipprich, Yvonne Tauchmann, Simon Reinke, Georgi Wassilew, Ute Hoffmann, Andreas S. Richter, Lina Sieverling, DEEP Consortium, Hyun-Dong Chang, Uta Syrbe, Ulrich Kalus, Jürgen Eils, Benedikt Brors, Thomas Manke, Jürgen Ruland, Thomas Lengauer, Nikolaus Rajewsky, Wei Chen, Jun Dong, Birgit Sawitzki, Ho-Ryun Chung, Philip Rosenstiel, Marcel H. Schulz, Joachim L. Schultze, Andreas Radbruch, Jörn Walter, Alf Hamann, & Julia K. Polansky.\n\n\n \n \n \n \n Epigenomic Profiling of Human CD4+ T Cells Supports a Linear Differentiation Model and Highlights Molecular Regulators of Memory Development.\n \n \n \n\n\n \n\n\n\n Immunity, 45(5): 1148–1161. November 2016.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{durek_epigenomic_2016,\n\ttitle = {Epigenomic {Profiling} of {Human} {CD4}+ {T} {Cells} {Supports} a {Linear} {Differentiation} {Model} and {Highlights} {Molecular} {Regulators} of {Memory} {Development}},\n\tvolume = {45},\n\tissn = {1097-4180},\n\tdoi = {10.1016/j.immuni.2016.10.022},\n\tabstract = {The impact of epigenetics on the differentiation of memory T (Tmem) cells is poorly defined. We generated deep epigenomes comprising genome-wide profiles of DNA methylation, histone modifications, DNA accessibility, and coding and non-coding RNA expression in naive, central-, effector-, and terminally differentiated CD45RA+ CD4+ Tmem cells from blood and CD69+ Tmem cells from bone marrow (BM-Tmem). We observed a progressive and proliferation-associated global loss of DNA methylation in heterochromatic parts of the genome during Tmem cell differentiation. Furthermore, distinct gradually changing signatures in the epigenome and the transcriptome supported a linear model of memory development in circulating T cells, while tissue-resident BM-Tmem branched off with a unique epigenetic profile. Integrative analyses identified candidate master regulators of Tmem cell differentiation, including the transcription factor FOXP1. This study highlights the importance of epigenomic changes for Tmem cell biology and demonstrates the value of epigenetic data for the identification of lineage regulators.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Immunity},\n\tauthor = {Durek, Pawel and Nordström, Karl and Gasparoni, Gilles and Salhab, Abdulrahman and Kressler, Christopher and de Almeida, Melanie and Bassler, Kevin and Ulas, Thomas and Schmidt, Florian and Xiong, Jieyi and Glažar, Petar and Klironomos, Filippos and Sinha, Anupam and Kinkley, Sarah and Yang, Xinyi and Arrigoni, Laura and Amirabad, Azim Dehghani and Ardakani, Fatemeh Behjati and Feuerbach, Lars and Gorka, Oliver and Ebert, Peter and Müller, Fabian and Li, Na and Frischbutter, Stefan and Schlickeiser, Stephan and Cendon, Carla and Fröhler, Sebastian and Felder, Bärbel and Gasparoni, Nina and Imbusch, Charles D. and Hutter, Barbara and Zipprich, Gideon and Tauchmann, Yvonne and Reinke, Simon and Wassilew, Georgi and Hoffmann, Ute and Richter, Andreas S. and Sieverling, Lina and {DEEP Consortium} and Chang, Hyun-Dong and Syrbe, Uta and Kalus, Ulrich and Eils, Jürgen and Brors, Benedikt and Manke, Thomas and Ruland, Jürgen and Lengauer, Thomas and Rajewsky, Nikolaus and Chen, Wei and Dong, Jun and Sawitzki, Birgit and Chung, Ho-Ryun and Rosenstiel, Philip and Schulz, Marcel H. and Schultze, Joachim L. and Radbruch, Andreas and Walter, Jörn and Hamann, Alf and Polansky, Julia K.},\n\tmonth = nov,\n\tyear = {2016},\n\tpmid = {27851915},\n\tkeywords = {CD4-Positive T-Lymphocytes, Cell Differentiation, Epigenesis, Genetic, Epigenomics, Female, Flow Cytometry, Gene Expression Profiling, Humans, Immunologic Memory, Machine Learning, Polymerase Chain Reaction, Transcriptome},\n\tpages = {1148--1161},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/RWMVA79F/Durek et al. - 2016 - Epigenomic Profiling of Human CD4+ T Cells Support.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The impact of epigenetics on the differentiation of memory T (Tmem) cells is poorly defined. We generated deep epigenomes comprising genome-wide profiles of DNA methylation, histone modifications, DNA accessibility, and coding and non-coding RNA expression in naive, central-, effector-, and terminally differentiated CD45RA+ CD4+ Tmem cells from blood and CD69+ Tmem cells from bone marrow (BM-Tmem). We observed a progressive and proliferation-associated global loss of DNA methylation in heterochromatic parts of the genome during Tmem cell differentiation. Furthermore, distinct gradually changing signatures in the epigenome and the transcriptome supported a linear model of memory development in circulating T cells, while tissue-resident BM-Tmem branched off with a unique epigenetic profile. Integrative analyses identified candidate master regulators of Tmem cell differentiation, including the transcription factor FOXP1. This study highlights the importance of epigenomic changes for Tmem cell biology and demonstrates the value of epigenetic data for the identification of lineage regulators.\n
\n\n\n
\n\n\n
\n \n\n \n \n Dilip A. Durai, & Marcel H. Schulz.\n\n\n \n \n \n \n Informed kmer selection for de novo transcriptome assembly.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 32(11): 1670–1677. June 2016.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{durai_informed_2016,\n\ttitle = {Informed kmer selection for de novo transcriptome assembly},\n\tvolume = {32},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/btw217},\n\tabstract = {MOTIVATION: De novo transcriptome assembly is an integral part for many RNA-seq workflows. Common applications include sequencing of non-model organisms, cancer or meta transcriptomes. Most de novo transcriptome assemblers use the de Bruijn graph (DBG) as the underlying data structure. The quality of the assemblies produced by such assemblers is highly influenced by the exact word length k As such no single kmer value leads to optimal results. Instead, DBGs over different kmer values are built and the assemblies are merged to improve sensitivity. However, no studies have investigated thoroughly the problem of automatically learning at which kmer value to stop the assembly. Instead a suboptimal selection of kmer values is often used in practice.\nRESULTS: Here we investigate the contribution of a single kmer value in a multi-kmer based assembly approach. We find that a comparative clustering of related assemblies can be used to estimate the importance of an additional kmer assembly. Using a model fit based algorithm we predict the kmer value at which no further assemblies are necessary. Our approach is tested with different de novo assemblers for datasets with different coverage values and read lengths. Further, we suggest a simple post processing step that significantly improves the quality of multi-kmer assemblies.\nCONCLUSION: We provide an automatic method for limiting the number of kmer values without a significant loss in assembly quality but with savings in assembly time. This is a step forward to making multi-kmer methods more reliable and easier to use.\nAVAILABILITY AND IMPLEMENTATION: A general implementation of our approach can be found under: https://github.com/SchulzLab/KREATIONSupplementary information: Supplementary data are available at Bioinformatics online.\nCONTACT: mschulz@mmci.uni-saarland.de.},\n\tlanguage = {eng},\n\tnumber = {11},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Durai, Dilip A. and Schulz, Marcel H.},\n\tmonth = jun,\n\tyear = {2016},\n\tpmid = {27153653},\n\tpmcid = {PMC4892416},\n\tkeywords = {Algorithms, Cluster Analysis, High-Throughput Nucleotide Sequencing, Transcriptome},\n\tpages = {1670--1677},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/VAGY6WZI/Durai und Schulz - 2016 - Informed kmer selection for de novo transcriptome .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: De novo transcriptome assembly is an integral part for many RNA-seq workflows. Common applications include sequencing of non-model organisms, cancer or meta transcriptomes. Most de novo transcriptome assemblers use the de Bruijn graph (DBG) as the underlying data structure. The quality of the assemblies produced by such assemblers is highly influenced by the exact word length k As such no single kmer value leads to optimal results. Instead, DBGs over different kmer values are built and the assemblies are merged to improve sensitivity. However, no studies have investigated thoroughly the problem of automatically learning at which kmer value to stop the assembly. Instead a suboptimal selection of kmer values is often used in practice. RESULTS: Here we investigate the contribution of a single kmer value in a multi-kmer based assembly approach. We find that a comparative clustering of related assemblies can be used to estimate the importance of an additional kmer assembly. Using a model fit based algorithm we predict the kmer value at which no further assemblies are necessary. Our approach is tested with different de novo assemblers for datasets with different coverage values and read lengths. Further, we suggest a simple post processing step that significantly improves the quality of multi-kmer assemblies. CONCLUSION: We provide an automatic method for limiting the number of kmer values without a significant loss in assembly quality but with savings in assembly time. This is a step forward to making multi-kmer methods more reliable and easier to use. AVAILABILITY AND IMPLEMENTATION: A general implementation of our approach can be found under: https://github.com/SchulzLab/KREATIONSupplementary information: Supplementary data are available at Bioinformatics online. CONTACT: mschulz@mmci.uni-saarland.de.\n
\n\n\n
\n\n\n
\n \n\n \n \n Ulrike Götz, Simone Marker, Miriam Cheaib, Karsten Andresen, Simon Shrestha, Dilip A. Durai, Karl J. Nordström, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Two sets of RNAi components are required for heterochromatin formation in trans triggered by truncated transgenes.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 44(12): 5908–5923. July 2016.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{gotz_two_2016,\n\ttitle = {Two sets of {RNAi} components are required for heterochromatin formation in trans triggered by truncated transgenes},\n\tvolume = {44},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkw267},\n\tabstract = {Across kingdoms, RNA interference (RNAi) has been shown to control gene expression at the transcriptional- or the post-transcriptional level. Here, we describe a mechanism which involves both aspects: truncated transgenes, which fail to produce intact mRNA, induce siRNA accumulation and silencing of homologous loci in trans in the ciliate Paramecium We show that silencing is achieved by co-transcriptional silencing, associated with repressive histone marks at the endogenous gene. This is accompanied by secondary siRNA accumulation, strictly limited to the open reading frame of the remote locus. Our data shows that in this mechanism, heterochromatic marks depend on a variety of RNAi components. These include RDR3 and PTIWI14 as well as a second set of components, which are also involved in post-transcriptional silencing: RDR2, PTIWI13, DCR1 and CID2. Our data indicates differential processing of nascent un-spliced and long, spliced transcripts thus suggesting a hitherto-unrecognized functional interaction between post-transcriptional and co-transcriptional RNAi. Both sets of RNAi components are required for efficient trans-acting RNAi at the chromatin level and our data indicates similar mechanisms contributing to genome wide regulation of gene expression by epigenetic mechanisms.},\n\tlanguage = {eng},\n\tnumber = {12},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Götz, Ulrike and Marker, Simone and Cheaib, Miriam and Andresen, Karsten and Shrestha, Simon and Durai, Dilip A. and Nordström, Karl J. and Schulz, Marcel H. and Simon, Martin},\n\tmonth = jul,\n\tyear = {2016},\n\tpmid = {27085807},\n\tpmcid = {PMC4937312},\n\tkeywords = {Chromatin Assembly and Disassembly, DNA-Binding Proteins, Escherichia coli, Gene Expression Profiling, Gene Expression Regulation, Gene Ontology, Heterochromatin, Molecular Sequence Annotation, Paramecium, Plasmids, Polynucleotide Adenylyltransferase, Protozoan Proteins, RNA Interference, RNA, Double-Stranded, RNA, Messenger, RNA, Small Interfering, Transcription Factors, Transgenes},\n\tpages = {5908--5923},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/2P6ZNS88/Götz et al. - 2016 - Two sets of RNAi components are required for heter.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Across kingdoms, RNA interference (RNAi) has been shown to control gene expression at the transcriptional- or the post-transcriptional level. Here, we describe a mechanism which involves both aspects: truncated transgenes, which fail to produce intact mRNA, induce siRNA accumulation and silencing of homologous loci in trans in the ciliate Paramecium We show that silencing is achieved by co-transcriptional silencing, associated with repressive histone marks at the endogenous gene. This is accompanied by secondary siRNA accumulation, strictly limited to the open reading frame of the remote locus. Our data shows that in this mechanism, heterochromatic marks depend on a variety of RNAi components. These include RDR3 and PTIWI14 as well as a second set of components, which are also involved in post-transcriptional silencing: RDR2, PTIWI13, DCR1 and CID2. Our data indicates differential processing of nascent un-spliced and long, spliced transcripts thus suggesting a hitherto-unrecognized functional interaction between post-transcriptional and co-transcriptional RNAi. Both sets of RNAi components are required for efficient trans-acting RNAi at the chromatin level and our data indicates similar mechanisms contributing to genome wide regulation of gene expression by epigenetic mechanisms.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2015\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n Xin He, A. Ercument Cicek, Yuhao Wang, Marcel H. Schulz, Hai-Son Le, & Ziv Bar-Joseph.\n\n\n \n \n \n \n De novo ChIP-seq analysis.\n \n \n \n\n\n \n\n\n\n Genome Biology, 16(1): 205. September 2015.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{he_novo_2015,\n\ttitle = {De novo {ChIP}-seq analysis},\n\tvolume = {16},\n\tissn = {1474-760X},\n\tdoi = {10.1186/s13059-015-0756-4},\n\tabstract = {Methods for the analysis of chromatin immunoprecipitation sequencing (ChIP-seq) data start by aligning the short reads to a reference genome. While often successful, they are not appropriate for cases where a reference genome is not available. Here we develop methods for de novo analysis of ChIP-seq data. Our methods combine de novo assembly with statistical tests enabling motif discovery without the use of a reference genome. We validate the performance of our method using human and mouse data. Analysis of fly data indicates that our method outperforms alignment based methods that utilize closely related species.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {Genome Biology},\n\tauthor = {He, Xin and Cicek, A. Ercument and Wang, Yuhao and Schulz, Marcel H. and Le, Hai-Son and Bar-Joseph, Ziv},\n\tmonth = sep,\n\tyear = {2015},\n\tpmid = {26400819},\n\tpmcid = {PMC4579611},\n\tkeywords = {Animals, Cell Line, Tumor, Chromatin Immunoprecipitation, Drosophila, Embryonic Stem Cells, Humans, Mice, Nucleotide Motifs, Sequence Analysis, DNA, Transcription Factors},\n\tpages = {205},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/Y3SCLVN8/He et al. - 2015 - De novo ChIP-seq analysis.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Methods for the analysis of chromatin immunoprecipitation sequencing (ChIP-seq) data start by aligning the short reads to a reference genome. While often successful, they are not appropriate for cases where a reference genome is not available. Here we develop methods for de novo analysis of ChIP-seq data. Our methods combine de novo assembly with statistical tests enabling motif discovery without the use of a reference genome. We validate the performance of our method using human and mouse data. Analysis of fly data indicates that our method outperforms alignment based methods that utilize closely related species.\n
\n\n\n
\n\n\n
\n \n\n \n \n Miriam Cheaib, Azim Dehghani Amirabad, Karl J. V. Nordström, Marcel H. Schulz, & Martin Simon.\n\n\n \n \n \n \n Epigenetic regulation of serotype expression antagonizes transcriptome dynamics in Paramecium tetraurelia.\n \n \n \n\n\n \n\n\n\n DNA research: an international journal for rapid publication of reports on genes and genomes, 22(4): 293–305. August 2015.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{cheaib_epigenetic_2015,\n\ttitle = {Epigenetic regulation of serotype expression antagonizes transcriptome dynamics in {Paramecium} tetraurelia},\n\tvolume = {22},\n\tissn = {1756-1663},\n\tdoi = {10.1093/dnares/dsv014},\n\tabstract = {Phenotypic variation of a single genotype is achieved by alterations in gene expression patterns. Regulation of such alterations depends on their time scale, where short-time adaptations differ from permanently established gene expression patterns maintained by epigenetic mechanisms. In the ciliate Paramecium, serotypes were described for an epigenetically controlled gene expression pattern of an individual multigene family. Paradoxically, individual serotypes can be triggered in Paramecium by alternating environments but are then stabilized by epigenetic mechanisms, thus raising the question to which extend their expression follows environmental stimuli. To characterize environmental adaptation in the context of epigenetically controlled serotype expression, we used RNA-seq to characterize transcriptomes of serotype pure cultures. The resulting vegetative transcriptome resource is first analysed for genes involved in the adaptive response to the altered environment. Secondly, we identified groups of genes that do not follow the adaptive response but show co-regulation with the epigenetically controlled serotype system, suggesting that their gene expression pattern becomes manifested by similar mechanisms. In our experimental set-up, serotype expression and the entire group of co-regulated genes were stable among environmental changes and only heat-shock genes altered expression of these gene groups. The data suggest that the maintenance of these gene expression patterns in a lineage represents epigenetically controlled robustness counteracting short-time adaptation processes.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {DNA research: an international journal for rapid publication of reports on genes and genomes},\n\tauthor = {Cheaib, Miriam and Dehghani Amirabad, Azim and Nordström, Karl J. V. and Schulz, Marcel H. and Simon, Martin},\n\tmonth = aug,\n\tyear = {2015},\n\tpmid = {26231545},\n\tpmcid = {PMC4535620},\n\tkeywords = {Adaptation, Biological, antigenic variation, Antigens, Protozoan, ciliate, Cluster Analysis, Cold Temperature, DNA, Epigenesis, Genetic, epigenetics, Gene Expression Profiling, Gene Expression Regulation, heat-shock, Heat-Shock Response, Multigene Family, Paramecium tetraurelia, Protein Biosynthesis, Serogroup, Starvation, telomere position effect, Transcriptome},\n\tpages = {293--305},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/IJYPFDM5/Cheaib et al. - 2015 - Epigenetic regulation of serotype expression antag.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Phenotypic variation of a single genotype is achieved by alterations in gene expression patterns. Regulation of such alterations depends on their time scale, where short-time adaptations differ from permanently established gene expression patterns maintained by epigenetic mechanisms. In the ciliate Paramecium, serotypes were described for an epigenetically controlled gene expression pattern of an individual multigene family. Paradoxically, individual serotypes can be triggered in Paramecium by alternating environments but are then stabilized by epigenetic mechanisms, thus raising the question to which extend their expression follows environmental stimuli. To characterize environmental adaptation in the context of epigenetically controlled serotype expression, we used RNA-seq to characterize transcriptomes of serotype pure cultures. The resulting vegetative transcriptome resource is first analysed for genes involved in the adaptive response to the altered environment. Secondly, we identified groups of genes that do not follow the adaptive response but show co-regulation with the epigenetically controlled serotype system, suggesting that their gene expression pattern becomes manifested by similar mechanisms. In our experimental set-up, serotype expression and the entire group of co-regulated genes were stable among environmental changes and only heat-shock genes altered expression of these gene groups. The data suggest that the maintenance of these gene expression patterns in a lineage represents epigenetically controlled robustness counteracting short-time adaptation processes.\n
\n\n\n
\n\n\n
\n \n\n \n \n Peter Ebert, Fabian Müller, Karl Nordström, Thomas Lengauer, & Marcel H. Schulz.\n\n\n \n \n \n \n A general concept for consistent documentation of computational analyses.\n \n \n \n\n\n \n\n\n\n Database: The Journal of Biological Databases and Curation, 2015: bav050. 2015.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{ebert_general_2015,\n\ttitle = {A general concept for consistent documentation of computational analyses},\n\tvolume = {2015},\n\tissn = {1758-0463},\n\tdoi = {10.1093/database/bav050},\n\tabstract = {The ever-growing amount of data in the field of life sciences demands standardized ways of high-throughput computational analysis. This standardization requires a thorough documentation of each step in the computational analysis to enable researchers to understand and reproduce the results. However, due to the heterogeneity in software setups and the high rate of change during tool development, reproducibility is hard to achieve. One reason is that there is no common agreement in the research community on how to document computational studies. In many cases, simple flat files or other unstructured text documents are provided by researchers as documentation, which are often missing software dependencies, versions and sufficient documentation to understand the workflow and parameter settings. As a solution we suggest a simple and modest approach for documenting and verifying computational analysis pipelines. We propose a two-part scheme that defines a computational analysis using a Process and an Analysis metadata document, which jointly describe all necessary details to reproduce the results. In this design we separate the metadata specifying the process from the metadata describing an actual analysis run, thereby reducing the effort of manual documentation to an absolute minimum. Our approach is independent of a specific software environment, results in human readable XML documents that can easily be shared with other researchers and allows an automated validation to ensure consistency of the metadata. Because our approach has been designed with little to no assumptions concerning the workflow of an analysis, we expect it to be applicable in a wide range of computational research fields.},\n\tlanguage = {eng},\n\tjournal = {Database: The Journal of Biological Databases and Curation},\n\tauthor = {Ebert, Peter and Müller, Fabian and Nordström, Karl and Lengauer, Thomas and Schulz, Marcel H.},\n\tyear = {2015},\n\tpmid = {26055099},\n\tpmcid = {PMC4460408},\n\tkeywords = {Data Curation, Electronic Data Processing, Humans, Word Processing},\n\tpages = {bav050},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/PZEQH6ZU/Ebert et al. - 2015 - A general concept for consistent documentation of .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The ever-growing amount of data in the field of life sciences demands standardized ways of high-throughput computational analysis. This standardization requires a thorough documentation of each step in the computational analysis to enable researchers to understand and reproduce the results. However, due to the heterogeneity in software setups and the high rate of change during tool development, reproducibility is hard to achieve. One reason is that there is no common agreement in the research community on how to document computational studies. In many cases, simple flat files or other unstructured text documents are provided by researchers as documentation, which are often missing software dependencies, versions and sufficient documentation to understand the workflow and parameter settings. As a solution we suggest a simple and modest approach for documenting and verifying computational analysis pipelines. We propose a two-part scheme that defines a computational analysis using a Process and an Analysis metadata document, which jointly describe all necessary details to reproduce the results. In this design we separate the metadata specifying the process from the metadata describing an actual analysis run, thereby reducing the effort of manual documentation to an absolute minimum. Our approach is independent of a specific software environment, results in human readable XML documents that can easily be shared with other researchers and allows an automated validation to ensure consistency of the metadata. Because our approach has been designed with little to no assumptions concerning the workflow of an analysis, we expect it to be applicable in a wide range of computational research fields.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n Marcel H. Schulz, David Weese, Manuel Holtgrewe, Viktoria Dimitrova, Sijia Niu, Knut Reinert, & Hugues Richard.\n\n\n \n \n \n \n Fiona: a parallel and automatic strategy for read error correction.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 30(17): i356–363. September 2014.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_fiona_2014,\n\ttitle = {Fiona: a parallel and automatic strategy for read error correction},\n\tvolume = {30},\n\tissn = {1367-4811},\n\tshorttitle = {Fiona},\n\tdoi = {10.1093/bioinformatics/btu440},\n\tabstract = {MOTIVATION: Automatic error correction of high-throughput sequencing data can have a dramatic impact on the amount of usable base pairs and their quality. It has been shown that the performance of tasks such as de novo genome assembly and SNP calling can be dramatically improved after read error correction. While a large number of methods specialized for correcting substitution errors as found in Illumina data exist, few methods for the correction of indel errors, common to technologies like 454 or Ion Torrent, have been proposed.\nRESULTS: We present Fiona, a new stand-alone read error-correction method. Fiona provides a new statistical approach for sequencing error detection and optimal error correction and estimates its parameters automatically. Fiona is able to correct substitution, insertion and deletion errors and can be applied to any sequencing technology. It uses an efficient implementation of the partial suffix array to detect read overlaps with different seed lengths in parallel. We tested Fiona on several real datasets from a variety of organisms with different read lengths and compared its performance with state-of-the-art methods. Fiona shows a constantly higher correction accuracy over a broad range of datasets from 454 and Ion Torrent sequencers, without compromise in speed.\nCONCLUSION: Fiona is an accurate parameter-free read error-correction method that can be run on inexpensive hardware and can make use of multicore parallelization whenever available. Fiona was implemented using the SeqAn library for sequence analysis and is publicly available for download at http://www.seqan.de/projects/fiona.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {17},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Schulz, Marcel H. and Weese, David and Holtgrewe, Manuel and Dimitrova, Viktoria and Niu, Sijia and Reinert, Knut and Richard, Hugues},\n\tmonth = sep,\n\tyear = {2014},\n\tpmid = {25161220},\n\tpmcid = {PMC4147893},\n\tkeywords = {Algorithms, High-Throughput Nucleotide Sequencing, INDEL Mutation, Sequence Analysis, DNA},\n\tpages = {i356--363},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/YWWHMEP3/Schulz et al. - 2014 - Fiona a parallel and automatic strategy for read .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: Automatic error correction of high-throughput sequencing data can have a dramatic impact on the amount of usable base pairs and their quality. It has been shown that the performance of tasks such as de novo genome assembly and SNP calling can be dramatically improved after read error correction. While a large number of methods specialized for correcting substitution errors as found in Illumina data exist, few methods for the correction of indel errors, common to technologies like 454 or Ion Torrent, have been proposed. RESULTS: We present Fiona, a new stand-alone read error-correction method. Fiona provides a new statistical approach for sequencing error detection and optimal error correction and estimates its parameters automatically. Fiona is able to correct substitution, insertion and deletion errors and can be applied to any sequencing technology. It uses an efficient implementation of the partial suffix array to detect read overlaps with different seed lengths in parallel. We tested Fiona on several real datasets from a variety of organisms with different read lengths and compared its performance with state-of-the-art methods. Fiona shows a constantly higher correction accuracy over a broad range of datasets from 454 and Ion Torrent sequencers, without compromise in speed. CONCLUSION: Fiona is an accurate parameter-free read error-correction method that can be run on inexpensive hardware and can make use of multicore parallelization whenever available. Fiona was implemented using the SeqAn library for sequence analysis and is publicly available for download at http://www.seqan.de/projects/fiona. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcel H. Schulz.\n\n\n \n \n \n \n Letting the data speak for themselves: a fully Bayesian approach to transcriptome assembly.\n \n \n \n\n\n \n\n\n\n Genome Biology, 15(10): 498. 2014.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_letting_2014,\n\ttitle = {Letting the data speak for themselves: a fully {Bayesian} approach to transcriptome assembly},\n\tvolume = {15},\n\tissn = {1474-760X},\n\tshorttitle = {Letting the data speak for themselves},\n\tdoi = {10.1186/s13059-014-0498-8},\n\tabstract = {A novel method for transcriptome assembly, Bayesembler, provides greater accuracy without sacrifice of computational speed, and particular advantages for alternative transcripts expressed at low levels.},\n\tlanguage = {eng},\n\tnumber = {10},\n\tjournal = {Genome Biology},\n\tauthor = {Schulz, Marcel H.},\n\tyear = {2014},\n\tpmid = {25830215},\n\tpmcid = {PMC4318165},\n\tkeywords = {Bayes Theorem, Gene Expression Profiling, Humans, Software, Transcriptome},\n\tpages = {498},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/AS6XZBYF/Schulz - 2014 - Letting the data speak for themselves a fully Bay.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n A novel method for transcriptome assembly, Bayesembler, provides greater accuracy without sacrifice of computational speed, and particular advantages for alternative transcripts expressed at low levels.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2013\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n Tamara Steijger, Josep F. Abril, Pär G. Engström, Felix Kokocinski, RGASP Consortium, Tim J. Hubbard, Roderic Guigó, Jennifer Harrow, & Paul Bertone.\n\n\n \n \n \n \n Assessment of transcript reconstruction methods for RNA-seq.\n \n \n \n\n\n \n\n\n\n Nature Methods, 10(12): 1177–1184. December 2013.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{steijger_assessment_2013,\n\ttitle = {Assessment of transcript reconstruction methods for {RNA}-seq},\n\tvolume = {10},\n\tissn = {1548-7105},\n\tdoi = {10.1038/nmeth.2714},\n\tabstract = {We evaluated 25 protocol variants of 14 independent computational methods for exon identification, transcript reconstruction and expression-level quantification from RNA-seq data. Our results show that most algorithms are able to identify discrete transcript components with high success rates but that assembly of complete isoform structures poses a major challenge even when all constituent elements are identified. Expression-level estimates also varied widely across methods, even when based on similar transcript models. Consequently, the complexity of higher eukaryotic genomes imposes severe limitations on transcript recall and splice product discrimination that are likely to remain limiting factors for the analysis of current-generation RNA-seq data.},\n\tlanguage = {eng},\n\tnumber = {12},\n\tjournal = {Nature Methods},\n\tauthor = {Steijger, Tamara and Abril, Josep F. and Engström, Pär G. and Kokocinski, Felix and {RGASP Consortium} and Hubbard, Tim J. and Guigó, Roderic and Harrow, Jennifer and Bertone, Paul},\n\tmonth = dec,\n\tyear = {2013},\n\tpmid = {24185837},\n\tpmcid = {PMC3851240},\n\tkeywords = {Algorithms, Animals, Caenorhabditis elegans, Computational Biology, Drosophila melanogaster, Exons, Gene Expression Profiling, Genome, Humans, Introns, RNA Splice Sites, RNA Splicing, RNA, Messenger, Sequence Analysis, RNA, Software},\n\tpages = {1177--1184},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/26XDQVWE/Steijger et al. - 2013 - Assessment of transcript reconstruction methods fo.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n We evaluated 25 protocol variants of 14 independent computational methods for exon identification, transcript reconstruction and expression-level quantification from RNA-seq data. Our results show that most algorithms are able to identify discrete transcript components with high success rates but that assembly of complete isoform structures poses a major challenge even when all constituent elements are identified. Expression-level estimates also varied widely across methods, even when based on similar transcript models. Consequently, the complexity of higher eukaryotic genomes imposes severe limitations on transcript recall and splice product discrimination that are likely to remain limiting factors for the analysis of current-generation RNA-seq data.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcel H. Schulz, Kusum V. Pandit, Christian L. Lino Cardenas, Namasivayam Ambalavanan, Naftali Kaminski, & Ziv Bar-Joseph.\n\n\n \n \n \n \n Reconstructing dynamic microRNA-regulated interaction networks.\n \n \n \n\n\n \n\n\n\n Proceedings of the National Academy of Sciences of the United States of America, 110(39): 15686–15691. September 2013.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_reconstructing_2013,\n\ttitle = {Reconstructing dynamic {microRNA}-regulated interaction networks},\n\tvolume = {110},\n\tissn = {1091-6490},\n\tdoi = {10.1073/pnas.1303236110},\n\tabstract = {The regulation of gene expression in cells, including by microRNAs (miRNAs), is a dynamic process. Current methods for identifying miRNA targets by combining sequence and miRNA and mRNA expression data do not adequately use the temporal information and thus miss important miRNAs and their targets. We developed the MIRna Dynamic Regulatory Events Miner (mirDREM), a probabilistic modeling method that uses input-output hidden Markov models to reconstruct dynamic regulatory networks that explain how temporal gene expression is jointly regulated by miRNAs and transcription factors. We measured miRNA and mRNA expression for postnatal lung development in mice and used mirDREM to study the regulation of this process. The reconstructed dynamic network correctly identified known miRNAs and transcription factors. The method has also provided predictions about additional miRNAs regulating this process and the specific developmental phases they regulate, several of which were experimentally validated. Our analysis uncovered links between miRNAs involved in lung development and differentially expressed miRNAs in idiopathic pulmonary fibrosis patients, some of which we have experimentally validated using proliferation assays. These results indicate that some disease progression pathways in idiopathic pulmonary fibrosis may represent partial reversal of lung differentiation.},\n\tlanguage = {eng},\n\tnumber = {39},\n\tjournal = {Proceedings of the National Academy of Sciences of the United States of America},\n\tauthor = {Schulz, Marcel H. and Pandit, Kusum V. and Lino Cardenas, Christian L. and Ambalavanan, Namasivayam and Kaminski, Naftali and Bar-Joseph, Ziv},\n\tmonth = sep,\n\tyear = {2013},\n\tpmid = {23986498},\n\tpmcid = {PMC3785769},\n\tkeywords = {Algorithms, Animals, Cell Proliferation, Gene Expression Regulation, Gene Knockdown Techniques, Gene Regulatory Networks, Humans, Idiopathic Pulmonary Fibrosis, Lung, Mice, MicroRNAs, Models, Genetic, network modeling, Reproducibility of Results, RNA, Messenger, systems biology},\n\tpages = {15686--15691},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/KKYHTV5Q/Schulz et al. - 2013 - Reconstructing dynamic microRNA-regulated interact.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The regulation of gene expression in cells, including by microRNAs (miRNAs), is a dynamic process. Current methods for identifying miRNA targets by combining sequence and miRNA and mRNA expression data do not adequately use the temporal information and thus miss important miRNAs and their targets. We developed the MIRna Dynamic Regulatory Events Miner (mirDREM), a probabilistic modeling method that uses input-output hidden Markov models to reconstruct dynamic regulatory networks that explain how temporal gene expression is jointly regulated by miRNAs and transcription factors. We measured miRNA and mRNA expression for postnatal lung development in mice and used mirDREM to study the regulation of this process. The reconstructed dynamic network correctly identified known miRNAs and transcription factors. The method has also provided predictions about additional miRNAs regulating this process and the specific developmental phases they regulate, several of which were experimentally validated. Our analysis uncovered links between miRNAs involved in lung development and differentially expressed miRNAs in idiopathic pulmonary fibrosis patients, some of which we have experimentally validated using proliferation assays. These results indicate that some disease progression pathways in idiopathic pulmonary fibrosis may represent partial reversal of lung differentiation.\n
\n\n\n
\n\n\n
\n \n\n \n \n Hai-Son Le, Marcel H. Schulz, Brenna M. McCauley, Veronica F. Hinman, & Ziv Bar-Joseph.\n\n\n \n \n \n \n Probabilistic error correction for RNA sequencing.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 41(10): e109. May 2013.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{le_probabilistic_2013,\n\ttitle = {Probabilistic error correction for {RNA} sequencing},\n\tvolume = {41},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkt215},\n\tabstract = {Sequencing of RNAs (RNA-Seq) has revolutionized the field of transcriptomics, but the reads obtained often contain errors. Read error correction can have a large impact on our ability to accurately assemble transcripts. This is especially true for de novo transcriptome analysis, where a reference genome is not available. Current read error correction methods, developed for DNA sequence data, cannot handle the overlapping effects of non-uniform abundance, polymorphisms and alternative splicing. Here we present SEquencing Error CorrEction in Rna-seq data (SEECER), a hidden Markov Model (HMM)-based method, which is the first to successfully address these problems. SEECER efficiently learns hundreds of thousands of HMMs and uses these to correct sequencing errors. Using human RNA-Seq data, we show that SEECER greatly improves on previous methods in terms of quality of read alignment to the genome and assembly accuracy. To illustrate the usefulness of SEECER for de novo transcriptome studies, we generated new RNA-Seq data to study the development of the sea cucumber Parastichopus parvimensis. Our corrected assembled transcripts shed new light on two important stages in sea cucumber development. Comparison of the assembled transcripts to known transcripts in other species has also revealed novel transcripts that are unique to sea cucumber, some of which we have experimentally validated. Supporting website: http://sb.cs.cmu.edu/seecer/.},\n\tlanguage = {eng},\n\tnumber = {10},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Le, Hai-Son and Schulz, Marcel H. and McCauley, Brenna M. and Hinman, Veronica F. and Bar-Joseph, Ziv},\n\tmonth = may,\n\tyear = {2013},\n\tpmid = {23558750},\n\tpmcid = {PMC3664804},\n\tkeywords = {Animals, Humans, Markov Chains, Sea Cucumbers, Sequence Analysis, RNA},\n\tpages = {e109},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/YV3CU8DR/Le et al. - 2013 - Probabilistic error correction for RNA sequencing.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Sequencing of RNAs (RNA-Seq) has revolutionized the field of transcriptomics, but the reads obtained often contain errors. Read error correction can have a large impact on our ability to accurately assemble transcripts. This is especially true for de novo transcriptome analysis, where a reference genome is not available. Current read error correction methods, developed for DNA sequence data, cannot handle the overlapping effects of non-uniform abundance, polymorphisms and alternative splicing. Here we present SEquencing Error CorrEction in Rna-seq data (SEECER), a hidden Markov Model (HMM)-based method, which is the first to successfully address these problems. SEECER efficiently learns hundreds of thousands of HMMs and uses these to correct sequencing errors. Using human RNA-Seq data, we show that SEECER greatly improves on previous methods in terms of quality of read alignment to the genome and assembly accuracy. To illustrate the usefulness of SEECER for de novo transcriptome studies, we generated new RNA-Seq data to study the development of the sea cucumber Parastichopus parvimensis. Our corrected assembled transcripts shed new light on two important stages in sea cucumber development. Comparison of the assembled transcripts to known transcripts in other species has also revealed novel transcripts that are unique to sea cucumber, some of which we have experimentally validated. Supporting website: http://sb.cs.cmu.edu/seecer/.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2012\n \n \n (5)\n \n \n
\n
\n \n \n
\n \n\n \n \n Marcel H. Schulz, William E. Devanny, Anthony Gitter, Shan Zhong, Jason Ernst, & Ziv Bar-Joseph.\n\n\n \n \n \n \n DREM 2.0: Improved reconstruction of dynamic regulatory networks from time-series expression data.\n \n \n \n\n\n \n\n\n\n BMC systems biology, 6: 104. August 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_drem_2012,\n\ttitle = {{DREM} 2.0: {Improved} reconstruction of dynamic regulatory networks from time-series expression data},\n\tvolume = {6},\n\tissn = {1752-0509},\n\tshorttitle = {{DREM} 2.0},\n\tdoi = {10.1186/1752-0509-6-104},\n\tabstract = {BACKGROUND: Modeling dynamic regulatory networks is a major challenge since much of the protein-DNA interaction data available is static. The Dynamic Regulatory Events Miner (DREM) uses a Hidden Markov Model-based approach to integrate this static interaction data with time series gene expression leading to models that can determine when transcription factors (TFs) activate genes and what genes they regulate. DREM has been used successfully in diverse areas of biological research. However, several issues were not addressed by the original version.\nRESULTS: DREM 2.0 is a comprehensive software for reconstructing dynamic regulatory networks that supports interactive graphical or batch mode. With version 2.0 a set of new features that are unique in comparison with other softwares are introduced. First, we provide static interaction data for additional species. Second, DREM 2.0 now accepts continuous binding values and we added a new method to utilize TF expression levels when searching for dynamic models. Third, we added support for discriminative motif discovery, which is particularly powerful for species with limited experimental interaction data. Finally, we improved the visualization to support the new features. Combined, these changes improve the ability of DREM 2.0 to accurately recover dynamic regulatory networks and make it much easier to use it for analyzing such networks in several species with varying degrees of interaction information.\nCONCLUSIONS: DREM 2.0 provides a unique framework for constructing and visualizing dynamic regulatory networks. DREM 2.0 can be downloaded from: http://www.sb.cs.cmu.edu/drem.},\n\tlanguage = {eng},\n\tjournal = {BMC systems biology},\n\tauthor = {Schulz, Marcel H. and Devanny, William E. and Gitter, Anthony and Zhong, Shan and Ernst, Jason and Bar-Joseph, Ziv},\n\tmonth = aug,\n\tyear = {2012},\n\tpmid = {22897824},\n\tpmcid = {PMC3464930},\n\tkeywords = {Asbestos, Cell Line, Tumor, Gene Expression Profiling, Humans, Nucleotide Motifs, Software, Time Factors},\n\tpages = {104},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/MWR86DJC/Schulz et al. - 2012 - DREM 2.0 Improved reconstruction of dynamic regul.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Modeling dynamic regulatory networks is a major challenge since much of the protein-DNA interaction data available is static. The Dynamic Regulatory Events Miner (DREM) uses a Hidden Markov Model-based approach to integrate this static interaction data with time series gene expression leading to models that can determine when transcription factors (TFs) activate genes and what genes they regulate. DREM has been used successfully in diverse areas of biological research. However, several issues were not addressed by the original version. RESULTS: DREM 2.0 is a comprehensive software for reconstructing dynamic regulatory networks that supports interactive graphical or batch mode. With version 2.0 a set of new features that are unique in comparison with other softwares are introduced. First, we provide static interaction data for additional species. Second, DREM 2.0 now accepts continuous binding values and we added a new method to utilize TF expression levels when searching for dynamic models. Third, we added support for discriminative motif discovery, which is particularly powerful for species with limited experimental interaction data. Finally, we improved the visualization to support the new features. Combined, these changes improve the ability of DREM 2.0 to accurately recover dynamic regulatory networks and make it much easier to use it for analyzing such networks in several species with varying degrees of interaction information. CONCLUSIONS: DREM 2.0 provides a unique framework for constructing and visualizing dynamic regulatory networks. DREM 2.0 can be downloaded from: http://www.sb.cs.cmu.edu/drem.\n
\n\n\n
\n\n\n
\n \n\n \n \n Sebastian Bauer, Sebastian Köhler, Marcel H. Schulz, & Peter N. Robinson.\n\n\n \n \n \n \n Bayesian ontology querying for accurate and noise-tolerant semantic searches.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 28(19): 2502–2508. October 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{bauer_bayesian_2012,\n\ttitle = {Bayesian ontology querying for accurate and noise-tolerant semantic searches},\n\tvolume = {28},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bts471},\n\tabstract = {MOTIVATION: Ontologies provide a structured representation of the concepts of a domain of knowledge as well as the relations between them. Attribute ontologies are used to describe the characteristics of the items of a domain, such as the functions of proteins or the signs and symptoms of disease, which opens the possibility of searching a database of items for the best match to a list of observed or desired attributes. However, naive search methods do not perform well on realistic data because of noise in the data, imprecision in typical queries and because individual items may not display all attributes of the category they belong to.\nRESULTS: We present a method for combining ontological analysis with Bayesian networks to deal with noise, imprecision and attribute frequencies and demonstrate an application of our method as a differential diagnostic support system for human genetics.\nAVAILABILITY: We provide an implementation for the algorithm and the benchmark at http://compbio.charite.de/boqa/.\nCONTACT: Sebastian.Bauer@charite.de or Peter.Robinson@charite.de\nSUPPLEMENTARY INFORMATION: Supplementary Material for this article is available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {19},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Bauer, Sebastian and Köhler, Sebastian and Schulz, Marcel H. and Robinson, Peter N.},\n\tmonth = oct,\n\tyear = {2012},\n\tpmid = {22843981},\n\tpmcid = {PMC3463114},\n\tkeywords = {Algorithms, Bayes Theorem, Computational Biology, Decision Support Techniques, Diagnosis, Differential, Humans, Models, Statistical, Semantics},\n\tpages = {2502--2508},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/NFWSUV89/Bauer et al. - 2012 - Bayesian ontology querying for accurate and noise-.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: Ontologies provide a structured representation of the concepts of a domain of knowledge as well as the relations between them. Attribute ontologies are used to describe the characteristics of the items of a domain, such as the functions of proteins or the signs and symptoms of disease, which opens the possibility of searching a database of items for the best match to a list of observed or desired attributes. However, naive search methods do not perform well on realistic data because of noise in the data, imprecision in typical queries and because individual items may not display all attributes of the category they belong to. RESULTS: We present a method for combining ontological analysis with Bayesian networks to deal with noise, imprecision and attribute frequencies and demonstrate an application of our method as a differential diagnostic support system for human genetics. AVAILABILITY: We provide an implementation for the algorithm and the benchmark at http://compbio.charite.de/boqa/. CONTACT: Sebastian.Bauer@charite.de or Peter.Robinson@charite.de SUPPLEMENTARY INFORMATION: Supplementary Material for this article is available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcel H. Schulz, Daniel R. Zerbino, Martin Vingron, & Ewan Birney.\n\n\n \n \n \n \n Oases: robust de novo RNA-seq assembly across the dynamic range of expression levels.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 28(8): 1086–1092. April 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_oases_2012,\n\ttitle = {Oases: robust de novo {RNA}-seq assembly across the dynamic range of expression levels},\n\tvolume = {28},\n\tissn = {1367-4811},\n\tshorttitle = {Oases},\n\tdoi = {10.1093/bioinformatics/bts094},\n\tabstract = {MOTIVATION: High-throughput sequencing has made the analysis of new model organisms more affordable. Although assembling a new genome can still be costly and difficult, it is possible to use RNA-seq to sequence mRNA. In the absence of a known genome, it is necessary to assemble these sequences de novo, taking into account possible alternative isoforms and the dynamic range of expression values.\nRESULTS: We present a software package named Oases designed to heuristically assemble RNA-seq reads in the absence of a reference genome, across a broad spectrum of expression values and in presence of alternative isoforms. It achieves this by using an array of hash lengths, a dynamic filtering of noise, a robust resolution of alternative splicing events and the efficient merging of multiple assemblies. It was tested on human and mouse RNA-seq data and is shown to improve significantly on the transABySS and Trinity de novo transcriptome assemblers.\nAVAILABILITY AND IMPLEMENTATION: Oases is freely available under the GPL license at www.ebi.ac.uk/{\\textasciitilde}zerbino/oases/.},\n\tlanguage = {eng},\n\tnumber = {8},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Schulz, Marcel H. and Zerbino, Daniel R. and Vingron, Martin and Birney, Ewan},\n\tmonth = apr,\n\tyear = {2012},\n\tpmid = {22368243},\n\tpmcid = {PMC3324515},\n\tkeywords = {Algorithms, Alternative Splicing, Animals, Gene Expression Profiling, High-Throughput Nucleotide Sequencing, Humans, Mice, RNA, Messenger, Sequence Analysis, RNA, Software},\n\tpages = {1086--1092},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/G9M5GEGD/Schulz et al. - 2012 - Oases robust de novo RNA-seq assembly across the .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: High-throughput sequencing has made the analysis of new model organisms more affordable. Although assembling a new genome can still be costly and difficult, it is possible to use RNA-seq to sequence mRNA. In the absence of a known genome, it is necessary to assemble these sequences de novo, taking into account possible alternative isoforms and the dynamic range of expression values. RESULTS: We present a software package named Oases designed to heuristically assemble RNA-seq reads in the absence of a reference genome, across a broad spectrum of expression values and in presence of alternative isoforms. It achieves this by using an array of hash lengths, a dynamic filtering of noise, a robust resolution of alternative splicing events and the efficient merging of multiple assemblies. It was tested on human and mouse RNA-seq data and is shown to improve significantly on the transABySS and Trinity de novo transcriptome assemblers. AVAILABILITY AND IMPLEMENTATION: Oases is freely available under the GPL license at www.ebi.ac.uk/~zerbino/oases/.\n
\n\n\n
\n\n\n
\n \n\n \n \n Jonathan Göke, Marcel H. Schulz, Julia Lasserre, & Martin Vingron.\n\n\n \n \n \n \n Estimation of pairwise sequence similarity of mammalian enhancers with word neighbourhood counts.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 28(5): 656–663. March 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{goke_estimation_2012,\n\ttitle = {Estimation of pairwise sequence similarity of mammalian enhancers with word neighbourhood counts},\n\tvolume = {28},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bts028},\n\tabstract = {MOTIVATION: The identity of cells and tissues is to a large degree governed by transcriptional regulation. A major part is accomplished by the combinatorial binding of transcription factors at regulatory sequences, such as enhancers. Even though binding of transcription factors is sequence-specific, estimating the sequence similarity of two functionally similar enhancers is very difficult. However, a similarity measure for regulatory sequences is crucial to detect and understand functional similarities between two enhancers and will facilitate large-scale analyses like clustering, prediction and classification of genome-wide datasets.\nRESULTS: We present the standardized alignment-free sequence similarity measure N2, a flexible framework that is defined for word neighbourhoods. We explore the usefulness of adding reverse complement words as well as words including mismatches into the neighbourhood. On simulated enhancer sequences as well as functional enhancers in mouse development, N2 is shown to outperform previous alignment-free measures. N2 is flexible, faster than competing methods and less susceptible to single sequence noise and the occurrence of repetitive sequences. Experiments on the mouse enhancers reveal that enhancers active in different tissues can be separated by pairwise comparison using N2.\nCONCLUSION: N2 represents an improvement over previous alignment-free similarity measures without compromising speed, which makes it a good candidate for large-scale sequence comparison of regulatory sequences.\nAVAILABILITY: The software is part of the open-source C++ library SeqAn (www.seqan.de) and a compiled version can be downloaded at http://www.seqan.de/projects/alf.html.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Göke, Jonathan and Schulz, Marcel H. and Lasserre, Julia and Vingron, Martin},\n\tmonth = mar,\n\tyear = {2012},\n\tpmid = {22247280},\n\tpmcid = {PMC3289921},\n\tkeywords = {Algorithms, Animals, Cluster Analysis, Enhancer Elements, Genetic, Genome-Wide Association Study, Mice, Organ Specificity, Software},\n\tpages = {656--663},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/UF5XWXJL/Göke et al. - 2012 - Estimation of pairwise sequence similarity of mamm.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: The identity of cells and tissues is to a large degree governed by transcriptional regulation. A major part is accomplished by the combinatorial binding of transcription factors at regulatory sequences, such as enhancers. Even though binding of transcription factors is sequence-specific, estimating the sequence similarity of two functionally similar enhancers is very difficult. However, a similarity measure for regulatory sequences is crucial to detect and understand functional similarities between two enhancers and will facilitate large-scale analyses like clustering, prediction and classification of genome-wide datasets. RESULTS: We present the standardized alignment-free sequence similarity measure N2, a flexible framework that is defined for word neighbourhoods. We explore the usefulness of adding reverse complement words as well as words including mismatches into the neighbourhood. On simulated enhancer sequences as well as functional enhancers in mouse development, N2 is shown to outperform previous alignment-free measures. N2 is flexible, faster than competing methods and less susceptible to single sequence noise and the occurrence of repetitive sequences. Experiments on the mouse enhancers reveal that enhancers active in different tissues can be separated by pairwise comparison using N2. CONCLUSION: N2 represents an improvement over previous alignment-free similarity measures without compromising speed, which makes it a good candidate for large-scale sequence comparison of regulatory sequences. AVAILABILITY: The software is part of the open-source C++ library SeqAn (www.seqan.de) and a compiled version can be downloaded at http://www.seqan.de/projects/alf.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Anne-Katrin Emde, Marcel H. Schulz, David Weese, Ruping Sun, Martin Vingron, Vera M. Kalscheuer, Stefan A. Haas, & Knut Reinert.\n\n\n \n \n \n \n Detecting genomic indel variants with exact breakpoints in single- and paired-end sequencing data using SplazerS.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 28(5): 619–627. March 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{emde_detecting_2012,\n\ttitle = {Detecting genomic indel variants with exact breakpoints in single- and paired-end sequencing data using {SplazerS}},\n\tvolume = {28},\n\tissn = {1367-4811},\n\tdoi = {10.1093/bioinformatics/bts019},\n\tabstract = {MOTIVATION: The reliable detection of genomic variation in resequencing data is still a major challenge, especially for variants larger than a few base pairs. Sequencing reads crossing boundaries of structural variation carry the potential for their identification, but are difficult to map.\nRESULTS: Here we present a method for 'split' read mapping, where prefix and suffix match of a read may be interrupted by a longer gap in the read-to-reference alignment. We use this method to accurately detect medium-sized insertions and long deletions with precise breakpoints in genomic resequencing data. Compared with alternative split mapping methods, SplazerS significantly improves sensitivity for detecting large indel events, especially in variant-rich regions. Our method is robust in the presence of sequencing errors as well as alignment errors due to genomic mutations/divergence, and can be used on reads of variable lengths. Our analysis shows that SplazerS is a versatile tool applicable to unanchored or single-end as well as anchored paired-end reads. In addition, application of SplazerS to targeted resequencing data led to the interesting discovery of a complete, possibly functional gene retrocopy variant.\nAVAILABILITY: SplazerS is available from http://www.seqan.de/projects/ splazers.\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Emde, Anne-Katrin and Schulz, Marcel H. and Weese, David and Sun, Ruping and Vingron, Martin and Kalscheuer, Vera M. and Haas, Stefan A. and Reinert, Knut},\n\tmonth = mar,\n\tyear = {2012},\n\tpmid = {22238266},\n\tkeywords = {Algorithms, Genomics, Humans, INDEL Mutation, Sequence Analysis, DNA},\n\tpages = {619--627},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/45JYHFG2/Emde et al. - 2012 - Detecting genomic indel variants with exact breakp.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: The reliable detection of genomic variation in resequencing data is still a major challenge, especially for variants larger than a few base pairs. Sequencing reads crossing boundaries of structural variation carry the potential for their identification, but are difficult to map. RESULTS: Here we present a method for 'split' read mapping, where prefix and suffix match of a read may be interrupted by a longer gap in the read-to-reference alignment. We use this method to accurately detect medium-sized insertions and long deletions with precise breakpoints in genomic resequencing data. Compared with alternative split mapping methods, SplazerS significantly improves sensitivity for detecting large indel events, especially in variant-rich regions. Our method is robust in the presence of sequencing errors as well as alignment errors due to genomic mutations/divergence, and can be used on reads of variable lengths. Our analysis shows that SplazerS is a versatile tool applicable to unanchored or single-end as well as anchored paired-end reads. In addition, application of SplazerS to targeted resequencing data led to the interesting discovery of a complete, possibly functional gene retrocopy variant. AVAILABILITY: SplazerS is available from http://www.seqan.de/projects/ splazers. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2011\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n Stefan Roepcke, Silke Stahlberg, Holger Klein, Marcel H. Schulz, Lars Theobald, Sabrina Gohlke, Martin Vingron, & Diego J. Walther.\n\n\n \n \n \n \n A tandem sequence motif acts as a distance-dependent enhancer in a set of genes involved in translation by binding the proteins NonO and SFPQ.\n \n \n \n\n\n \n\n\n\n BMC genomics, 12: 624. December 2011.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{roepcke_tandem_2011,\n\ttitle = {A tandem sequence motif acts as a distance-dependent enhancer in a set of genes involved in translation by binding the proteins {NonO} and {SFPQ}},\n\tvolume = {12},\n\tissn = {1471-2164},\n\tdoi = {10.1186/1471-2164-12-624},\n\tabstract = {BACKGROUND: Bioinformatic analyses of expression control sequences in promoters of co-expressed or functionally related genes enable the discovery of common regulatory sequence motifs that might be involved in co-ordinated gene expression. By studying promoter sequences of the human ribosomal protein genes we recently identified a novel highly specific Localized Tandem Sequence Motif (LTSM). In this work we sought to identify additional genes and LTSM-binding proteins to elucidate potential regulatory mechanisms.\nRESULTS: Genome-wide analyses allowed finding a considerable number of additional LTSM-positive genes, the products of which are involved in translation, among them, translation initiation and elongation factors, and 5S rRNA. Electromobility shift assays then showed specific signals demonstrating the binding of protein complexes to LTSM in ribosomal protein gene promoters. Pull-down assays with LTSM-containing oligonucleotides and subsequent mass spectrometric analysis identified the related multifunctional nucleotide binding proteins NonO and SFPQ in the binding complex. Functional characterization then revealed that LTSM enhances the transcriptional activity of the promoters in dependency of the distance from the transcription start site.\nCONCLUSIONS: Our data demonstrate the power of bioinformatic analyses for the identification of biologically relevant sequence motifs. LTSM and the here found LTSM-binding proteins NonO and SFPQ were discovered through a synergistic combination of bioinformatic and biochemical methods and are regulators of the expression of a set of genes of the translational apparatus in a distance-dependent manner.},\n\tlanguage = {eng},\n\tjournal = {BMC genomics},\n\tauthor = {Roepcke, Stefan and Stahlberg, Silke and Klein, Holger and Schulz, Marcel H. and Theobald, Lars and Gohlke, Sabrina and Vingron, Martin and Walther, Diego J.},\n\tmonth = dec,\n\tyear = {2011},\n\tpmid = {22185324},\n\tpmcid = {PMC3262029},\n\tkeywords = {DNA-Binding Proteins, Enhancer Elements, Genetic, Humans, Nuclear Matrix-Associated Proteins, Octamer Transcription Factors, Promoter Regions, Genetic, Protein Binding, Protein Biosynthesis, PTB-Associated Splicing Factor, RNA-Binding Proteins},\n\tpages = {624},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/2IRGDRJH/Roepcke et al. - 2011 - A tandem sequence motif acts as a distance-depende.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Bioinformatic analyses of expression control sequences in promoters of co-expressed or functionally related genes enable the discovery of common regulatory sequence motifs that might be involved in co-ordinated gene expression. By studying promoter sequences of the human ribosomal protein genes we recently identified a novel highly specific Localized Tandem Sequence Motif (LTSM). In this work we sought to identify additional genes and LTSM-binding proteins to elucidate potential regulatory mechanisms. RESULTS: Genome-wide analyses allowed finding a considerable number of additional LTSM-positive genes, the products of which are involved in translation, among them, translation initiation and elongation factors, and 5S rRNA. Electromobility shift assays then showed specific signals demonstrating the binding of protein complexes to LTSM in ribosomal protein gene promoters. Pull-down assays with LTSM-containing oligonucleotides and subsequent mass spectrometric analysis identified the related multifunctional nucleotide binding proteins NonO and SFPQ in the binding complex. Functional characterization then revealed that LTSM enhances the transcriptional activity of the promoters in dependency of the distance from the transcription start site. CONCLUSIONS: Our data demonstrate the power of bioinformatic analyses for the identification of biologically relevant sequence motifs. LTSM and the here found LTSM-binding proteins NonO and SFPQ were discovered through a synergistic combination of bioinformatic and biochemical methods and are regulators of the expression of a set of genes of the translational apparatus in a distance-dependent manner.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcel H. Schulz, Sebastian Köhler, Sebastian Bauer, & Peter N. Robinson.\n\n\n \n \n \n \n Exact score distribution computation for ontological similarity searches.\n \n \n \n\n\n \n\n\n\n BMC bioinformatics, 12: 441. November 2011.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_exact_2011,\n\ttitle = {Exact score distribution computation for ontological similarity searches},\n\tvolume = {12},\n\tissn = {1471-2105},\n\tdoi = {10.1186/1471-2105-12-441},\n\tabstract = {BACKGROUND: Semantic similarity searches in ontologies are an important component of many bioinformatic algorithms, e.g., finding functionally related proteins with the Gene Ontology or phenotypically similar diseases with the Human Phenotype Ontology (HPO). We have recently shown that the performance of semantic similarity searches can be improved by ranking results according to the probability of obtaining a given score at random rather than by the scores themselves. However, to date, there are no algorithms for computing the exact distribution of semantic similarity scores, which is necessary for computing the exact P-value of a given score.\nRESULTS: In this paper we consider the exact computation of score distributions for similarity searches in ontologies, and introduce a simple null hypothesis which can be used to compute a P-value for the statistical significance of similarity scores. We concentrate on measures based on Resnik's definition of ontological similarity. A new algorithm is proposed that collapses subgraphs of the ontology graph and thereby allows fast score distribution computation. The new algorithm is several orders of magnitude faster than the naive approach, as we demonstrate by computing score distributions for similarity searches in the HPO. It is shown that exact P-value calculation improves clinical diagnosis using the HPO compared to approaches based on sampling.\nCONCLUSIONS: The new algorithm enables for the first time exact P-value calculation via exact score distribution computation for ontology similarity searches. The approach is applicable to any ontology for which the annotation-propagation rule holds and can improve any bioinformatic method that makes only use of the raw similarity scores. The algorithm was implemented in Java, supports any ontology in OBO format, and is available for non-commercial and academic usage under: https://compbio.charite.de/svn/hpo/trunk/src/tools/significance/},\n\tlanguage = {eng},\n\tjournal = {BMC bioinformatics},\n\tauthor = {Schulz, Marcel H. and Köhler, Sebastian and Bauer, Sebastian and Robinson, Peter N.},\n\tmonth = nov,\n\tyear = {2011},\n\tpmid = {22078312},\n\tpmcid = {PMC3240574},\n\tkeywords = {Algorithms, Databases, Genetic, Humans, Knowledge Bases, Phenotype, Proteins, Vocabulary, Controlled},\n\tpages = {441},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/B29H7CVD/Schulz et al. - 2011 - Exact score distribution computation for ontologic.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n BACKGROUND: Semantic similarity searches in ontologies are an important component of many bioinformatic algorithms, e.g., finding functionally related proteins with the Gene Ontology or phenotypically similar diseases with the Human Phenotype Ontology (HPO). We have recently shown that the performance of semantic similarity searches can be improved by ranking results according to the probability of obtaining a given score at random rather than by the scores themselves. However, to date, there are no algorithms for computing the exact distribution of semantic similarity scores, which is necessary for computing the exact P-value of a given score. RESULTS: In this paper we consider the exact computation of score distributions for similarity searches in ontologies, and introduce a simple null hypothesis which can be used to compute a P-value for the statistical significance of similarity scores. We concentrate on measures based on Resnik's definition of ontological similarity. A new algorithm is proposed that collapses subgraphs of the ontology graph and thereby allows fast score distribution computation. The new algorithm is several orders of magnitude faster than the naive approach, as we demonstrate by computing score distributions for similarity searches in the HPO. It is shown that exact P-value calculation improves clinical diagnosis using the HPO compared to approaches based on sampling. CONCLUSIONS: The new algorithm enables for the first time exact P-value calculation via exact score distribution computation for ontology similarity searches. The approach is applicable to any ontology for which the annotation-propagation rule holds and can improve any bioinformatic method that makes only use of the raw similarity scores. The algorithm was implemented in Java, supports any ontology in OBO format, and is available for non-commercial and academic usage under: https://compbio.charite.de/svn/hpo/trunk/src/tools/significance/\n
\n\n\n
\n\n\n
\n \n\n \n \n Peter Huggins, Shan Zhong, Idit Shiff, Rachel Beckerman, Oleg Laptenko, Carol Prives, Marcel H. Schulz, Itamar Simon, & Ziv Bar-Joseph.\n\n\n \n \n \n \n DECOD: fast and accurate discriminative DNA motif finding.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 27(17): 2361–2367. September 2011.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{huggins_decod_2011,\n\ttitle = {{DECOD}: fast and accurate discriminative {DNA} motif finding},\n\tvolume = {27},\n\tissn = {1367-4811},\n\tshorttitle = {{DECOD}},\n\tdoi = {10.1093/bioinformatics/btr412},\n\tabstract = {MOTIVATION: Motif discovery is now routinely used in high-throughput studies including large-scale sequencing and proteomics. These datasets present new challenges. The first is speed. Many motif discovery methods do not scale well to large datasets. Another issue is identifying discriminative rather than generative motifs. Such discriminative motifs are important for identifying co-factors and for explaining changes in behavior between different conditions.\nRESULTS: To address these issues we developed a method for DECOnvolved Discriminative motif discovery (DECOD). DECOD uses a k-mer count table and so its running time is independent of the size of the input set. By deconvolving the k-mers DECOD considers context information without using the sequences directly. DECOD outperforms previous methods both in speed and in accuracy when using simulated and real biological benchmark data. We performed new binding experiments for p53 mutants and used DECOD to identify p53 co-factors, suggesting new mechanisms for p53 activation.\nAVAILABILITY: The source code and binaries for DECOD are available at http://www.sb.cs.cmu.edu/DECOD CONTACT: zivbj@cs.cmu.edu\nSUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},\n\tlanguage = {eng},\n\tnumber = {17},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Huggins, Peter and Zhong, Shan and Shiff, Idit and Beckerman, Rachel and Laptenko, Oleg and Prives, Carol and Schulz, Marcel H. and Simon, Itamar and Bar-Joseph, Ziv},\n\tmonth = sep,\n\tyear = {2011},\n\tpmid = {21752801},\n\tpmcid = {PMC3157928},\n\tkeywords = {Algorithms, Base Sequence, DNA, Nucleotide Motifs, Sequence Analysis, DNA, Tumor Suppressor Protein p53},\n\tpages = {2361--2367},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/U5E4SB97/Huggins et al. - 2011 - DECOD fast and accurate discriminative DNA motif .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: Motif discovery is now routinely used in high-throughput studies including large-scale sequencing and proteomics. These datasets present new challenges. The first is speed. Many motif discovery methods do not scale well to large datasets. Another issue is identifying discriminative rather than generative motifs. Such discriminative motifs are important for identifying co-factors and for explaining changes in behavior between different conditions. RESULTS: To address these issues we developed a method for DECOnvolved Discriminative motif discovery (DECOD). DECOD uses a k-mer count table and so its running time is independent of the size of the input set. By deconvolving the k-mers DECOD considers context information without using the sequences directly. DECOD outperforms previous methods both in speed and in accuracy when using simulated and real biological benchmark data. We performed new binding experiments for p53 mutants and used DECOD to identify p53 co-factors, suggesting new mechanisms for p53 activation. AVAILABILITY: The source code and binaries for DECOD are available at http://www.sb.cs.cmu.edu/DECOD CONTACT: zivbj@cs.cmu.edu SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.\n
\n\n\n
\n\n\n
\n \n\n \n \n Christian Rödelsperger, Gao Guo, Mateusz Kolanczyk, Angelika Pletschacher, Sebastian Köhler, Sebastian Bauer, Marcel H. Schulz, & Peter N. Robinson.\n\n\n \n \n \n \n Integrative analysis of genomic, functional and protein interaction data predicts long-range enhancer-target gene interactions.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 39(7): 2492–2502. April 2011.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{rodelsperger_integrative_2011,\n\ttitle = {Integrative analysis of genomic, functional and protein interaction data predicts long-range enhancer-target gene interactions},\n\tvolume = {39},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkq1081},\n\tabstract = {Multicellular organismal development is controlled by a complex network of transcription factors, promoters and enhancers. Although reliable computational and experimental methods exist for enhancer detection, prediction of their target genes remains a major challenge. On the basis of available literature and ChIP-seq and ChIP-chip data for enhanceosome factor p300 and the transcriptional regulator Gli3, we found that genomic proximity and conserved synteny predict target genes with a relatively low recall of 12-27\\% within 2 Mb intervals centered at the enhancers. Here, we show that functional similarities between enhancer binding proteins and their transcriptional targets and proximity in the protein-protein interactome improve prediction of target genes. We used all four features to train random forest classifiers that predict target genes with a recall of 58\\% in 2 Mb intervals that may contain dozens of genes, representing a better than two-fold improvement over the performance of prediction based on single features alone. Genome-wide ChIP data is still relatively poorly understood, and it remains difficult to assign biological significance to binding events. Our study represents a first step in integrating various genomic features in order to elucidate the genomic network of long-range regulatory interactions.},\n\tlanguage = {eng},\n\tnumber = {7},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Rödelsperger, Christian and Guo, Gao and Kolanczyk, Mateusz and Pletschacher, Angelika and Köhler, Sebastian and Bauer, Sebastian and Schulz, Marcel H. and Robinson, Peter N.},\n\tmonth = apr,\n\tyear = {2011},\n\tpmid = {21109530},\n\tpmcid = {PMC3074119},\n\tkeywords = {Algorithms, Animals, Chromatin Immunoprecipitation, DNA-Binding Proteins, Enhancer Elements, Genetic, Genomics, Kruppel-Like Transcription Factors, Mice, Nerve Tissue Proteins, Oligonucleotide Array Sequence Analysis, Protein Interaction Mapping, Synteny, Zinc Finger Protein Gli3},\n\tpages = {2492--2502},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/7LP7JNLT/Rödelsperger et al. - 2011 - Integrative analysis of genomic, functional and pr.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Multicellular organismal development is controlled by a complex network of transcription factors, promoters and enhancers. Although reliable computational and experimental methods exist for enhancer detection, prediction of their target genes remains a major challenge. On the basis of available literature and ChIP-seq and ChIP-chip data for enhanceosome factor p300 and the transcriptional regulator Gli3, we found that genomic proximity and conserved synteny predict target genes with a relatively low recall of 12-27% within 2 Mb intervals centered at the enhancers. Here, we show that functional similarities between enhancer binding proteins and their transcriptional targets and proximity in the protein-protein interactome improve prediction of target genes. We used all four features to train random forest classifiers that predict target genes with a recall of 58% in 2 Mb intervals that may contain dozens of genes, representing a better than two-fold improvement over the performance of prediction based on single features alone. Genome-wide ChIP data is still relatively poorly understood, and it remains difficult to assign biological significance to binding events. Our study represents a first step in integrating various genomic features in order to elucidate the genomic network of long-range regulatory interactions.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2010\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n Hugues Richard, Marcel H. Schulz, Marc Sultan, Asja Nürnberger, Sabine Schrinner, Daniela Balzereit, Emilie Dagand, Axel Rasche, Hans Lehrach, Martin Vingron, Stefan A. Haas, & Marie-Laure Yaspo.\n\n\n \n \n \n \n Prediction of alternative isoforms from exon expression levels in RNA-Seq experiments.\n \n \n \n\n\n \n\n\n\n Nucleic Acids Research, 38(10): e112. June 2010.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{richard_prediction_2010,\n\ttitle = {Prediction of alternative isoforms from exon expression levels in {RNA}-{Seq} experiments},\n\tvolume = {38},\n\tissn = {1362-4962},\n\tdoi = {10.1093/nar/gkq041},\n\tabstract = {Alternative splicing, polyadenylation of pre-messenger RNA molecules and differential promoter usage can produce a variety of transcript isoforms whose respective expression levels are regulated in time and space, thus contributing specific biological functions. However, the repertoire of mammalian alternative transcripts and their regulation are still poorly understood. Second-generation sequencing is now opening unprecedented routes to address the analysis of entire transcriptomes. Here, we developed methods that allow the prediction and quantification of alternative isoforms derived solely from exon expression levels in RNA-Seq data. These are based on an explicit statistical model and enable the prediction of alternative isoforms within or between conditions using any known gene annotation, as well as the relative quantification of known transcript structures. Applying these methods to a human RNA-Seq dataset, we validated a significant fraction of the predictions by RT-PCR. Data further showed that these predictions correlated well with information originating from junction reads. A direct comparison with exon arrays indicated improved performances of RNA-Seq over microarrays in the prediction of skipped exons. Altogether, the set of methods presented here comprehensively addresses multiple aspects of alternative isoform analysis. The software is available as an open-source R-package called Solas at http://cmb.molgen.mpg.de/2ndGenerationSequencing/Solas/.},\n\tlanguage = {eng},\n\tnumber = {10},\n\tjournal = {Nucleic Acids Research},\n\tauthor = {Richard, Hugues and Schulz, Marcel H. and Sultan, Marc and Nürnberger, Asja and Schrinner, Sabine and Balzereit, Daniela and Dagand, Emilie and Rasche, Axel and Lehrach, Hans and Vingron, Martin and Haas, Stefan A. and Yaspo, Marie-Laure},\n\tmonth = jun,\n\tyear = {2010},\n\tpmid = {20150413},\n\tpmcid = {PMC2879520},\n\tkeywords = {Alternative Splicing, Cell Line, Computer Simulation, Exons, Expressed Sequence Tags, Gene Expression Profiling, Humans, Models, Statistical, Oligonucleotide Array Sequence Analysis, Protein Isoforms, Sequence Analysis, RNA},\n\tpages = {e112},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/DEWA3GMB/Richard et al. - 2010 - Prediction of alternative isoforms from exon expre.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Alternative splicing, polyadenylation of pre-messenger RNA molecules and differential promoter usage can produce a variety of transcript isoforms whose respective expression levels are regulated in time and space, thus contributing specific biological functions. However, the repertoire of mammalian alternative transcripts and their regulation are still poorly understood. Second-generation sequencing is now opening unprecedented routes to address the analysis of entire transcriptomes. Here, we developed methods that allow the prediction and quantification of alternative isoforms derived solely from exon expression levels in RNA-Seq data. These are based on an explicit statistical model and enable the prediction of alternative isoforms within or between conditions using any known gene annotation, as well as the relative quantification of known transcript structures. Applying these methods to a human RNA-Seq dataset, we validated a significant fraction of the predictions by RT-PCR. Data further showed that these predictions correlated well with information originating from junction reads. A direct comparison with exon arrays indicated improved performances of RNA-Seq over microarrays in the prediction of skipped exons. Altogether, the set of methods presented here comprehensively addresses multiple aspects of alternative isoform analysis. The software is available as an open-source R-package called Solas at http://cmb.molgen.mpg.de/2ndGenerationSequencing/Solas/.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2009\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n Sebastian Köhler, Marcel H. Schulz, Peter Krawitz, Sebastian Bauer, Sandra Dölken, Claus E. Ott, Christine Mundlos, Denise Horn, Stefan Mundlos, & Peter N. Robinson.\n\n\n \n \n \n \n Clinical diagnostics in human genetics with semantic similarity searches in ontologies.\n \n \n \n\n\n \n\n\n\n American Journal of Human Genetics, 85(4): 457–464. October 2009.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{kohler_clinical_2009,\n\ttitle = {Clinical diagnostics in human genetics with semantic similarity searches in ontologies},\n\tvolume = {85},\n\tissn = {1537-6605},\n\tdoi = {10.1016/j.ajhg.2009.09.003},\n\tabstract = {The differential diagnostic process attempts to identify candidate diseases that best explain a set of clinical features. This process can be complicated by the fact that the features can have varying degrees of specificity, as well as by the presence of features unrelated to the disease itself. Depending on the experience of the physician and the availability of laboratory tests, clinical abnormalities may be described in greater or lesser detail. We have adapted semantic similarity metrics to measure phenotypic similarity between queries and hereditary diseases annotated with the use of the Human Phenotype Ontology (HPO) and have developed a statistical model to assign p values to the resulting similarity scores, which can be used to rank the candidate diseases. We show that our approach outperforms simpler term-matching approaches that do not take the semantic interrelationships between terms into account. The advantage of our approach was greater for queries containing phenotypic noise or imprecise clinical descriptions. The semantic network defined by the HPO can be used to refine the differential diagnosis by suggesting clinical features that, if present, best differentiate among the candidate diagnoses. Thus, semantic similarity searches in ontologies represent a useful way of harnessing the semantic structure of human phenotypic abnormalities to help with the differential diagnosis. We have implemented our methods in a freely available web application for the field of human Mendelian disorders.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {American Journal of Human Genetics},\n\tauthor = {Köhler, Sebastian and Schulz, Marcel H. and Krawitz, Peter and Bauer, Sebastian and Dölken, Sandra and Ott, Claus E. and Mundlos, Christine and Horn, Denise and Mundlos, Stefan and Robinson, Peter N.},\n\tmonth = oct,\n\tyear = {2009},\n\tpmid = {19800049},\n\tpmcid = {PMC2756558},\n\tkeywords = {Computational Biology, Databases, Genetic, Diagnosis, Differential, Genetic Diseases, Inborn, Genome, Human, Genomics, Humans, Internet, Models, Genetic, Models, Statistical, Monte Carlo Method, Pattern Recognition, Automated, Phenotype, Software, Vocabulary, Controlled},\n\tpages = {457--464},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/AKYDW2UE/Köhler et al. - 2009 - Clinical diagnostics in human genetics with semant.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n The differential diagnostic process attempts to identify candidate diseases that best explain a set of clinical features. This process can be complicated by the fact that the features can have varying degrees of specificity, as well as by the presence of features unrelated to the disease itself. Depending on the experience of the physician and the availability of laboratory tests, clinical abnormalities may be described in greater or lesser detail. We have adapted semantic similarity metrics to measure phenotypic similarity between queries and hereditary diseases annotated with the use of the Human Phenotype Ontology (HPO) and have developed a statistical model to assign p values to the resulting similarity scores, which can be used to rank the candidate diseases. We show that our approach outperforms simpler term-matching approaches that do not take the semantic interrelationships between terms into account. The advantage of our approach was greater for queries containing phenotypic noise or imprecise clinical descriptions. The semantic network defined by the HPO can be used to refine the differential diagnosis by suggesting clinical features that, if present, best differentiate among the candidate diagnoses. Thus, semantic similarity searches in ontologies represent a useful way of harnessing the semantic structure of human phenotypic abnormalities to help with the differential diagnosis. We have implemented our methods in a freely available web application for the field of human Mendelian disorders.\n
\n\n\n
\n\n\n
\n \n\n \n \n Christian Rödelsperger, Sebastian Köhler, Marcel H. Schulz, Thomas Manke, Sebastian Bauer, & Peter N. Robinson.\n\n\n \n \n \n \n Short ultraconserved promoter regions delineate a class of preferentially expressed alternatively spliced transcripts.\n \n \n \n\n\n \n\n\n\n Genomics, 94(5): 308–316. November 2009.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{rodelsperger_short_2009,\n\ttitle = {Short ultraconserved promoter regions delineate a class of preferentially expressed alternatively spliced transcripts},\n\tvolume = {94},\n\tissn = {1089-8646},\n\tdoi = {10.1016/j.ygeno.2009.07.005},\n\tabstract = {Ultraconservation has been variously defined to describe sequences that have remained identical or nearly so over long periods of evolution to a degree that is higher than expected for sequences under typical constraints associated with protein-coding sequences, splice sites, or transcription factor binding sites. Most intergenic ultraconserved elements (UCE) appear to be tissue-specific enhancers, whereas another class of intragenic UCEs is involved in regulation of gene expression by means of alternative splicing. In this study we define a set of 2827 short ultraconserved promoter regions (SUPR) in 5 kb upstream regions of 1268 human protein-coding genes using a definition of 98\\% identity for at least 30 bp in 7 mammalian species. Our analysis shows that SUPRs are enriched in genes playing a role in regulation and development. Many of the genes having a SUPR-containing promoter have additional alternative promoters that do not contain SUPRs. Comparison of such promoters by CAGE tag, EST, and Solexa read analysis revealed that SUPR-associated transcripts show a significantly higher mean expression than transcripts associated with non-SUPR-containing promoters. The same was true for the comparison between all SUPR-associated and non-SUPR-associated transcripts on a genome-wide basis. SUPR-associated genes show a highly significant tendency to occur in regions that are also enriched for intergenic short ultraconserved elements (SUE) in the vicinity of developmental genes. A number of predicted transcription factor binding sites (TFBS) are overrepresented in SUPRs and SUEs, including those for transcription factors of the homeodomain family, but in contrast to SUEs, SUPRs are also enriched in core-promoter motifs. These observations suggest that SUPRs delineate a distinct class of ultraconserved sequences.},\n\tlanguage = {eng},\n\tnumber = {5},\n\tjournal = {Genomics},\n\tauthor = {Rödelsperger, Christian and Köhler, Sebastian and Schulz, Marcel H. and Manke, Thomas and Bauer, Sebastian and Robinson, Peter N.},\n\tmonth = nov,\n\tyear = {2009},\n\tpmid = {19660540},\n\tkeywords = {Adult, Alternative Splicing, Animals, Cattle, Conserved Sequence, Dogs, Exons, Female, Gene Expression Regulation, Developmental, Genomics, Humans, Infant, Infant, Newborn, Introns, Male, Mice, Organ Specificity, Promoter Regions, Genetic, Proteins, Rabbits},\n\tpages = {308--316},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/VD3MTULE/Rödelsperger et al. - 2009 - Short ultraconserved promoter regions delineate a .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Ultraconservation has been variously defined to describe sequences that have remained identical or nearly so over long periods of evolution to a degree that is higher than expected for sequences under typical constraints associated with protein-coding sequences, splice sites, or transcription factor binding sites. Most intergenic ultraconserved elements (UCE) appear to be tissue-specific enhancers, whereas another class of intragenic UCEs is involved in regulation of gene expression by means of alternative splicing. In this study we define a set of 2827 short ultraconserved promoter regions (SUPR) in 5 kb upstream regions of 1268 human protein-coding genes using a definition of 98% identity for at least 30 bp in 7 mammalian species. Our analysis shows that SUPRs are enriched in genes playing a role in regulation and development. Many of the genes having a SUPR-containing promoter have additional alternative promoters that do not contain SUPRs. Comparison of such promoters by CAGE tag, EST, and Solexa read analysis revealed that SUPR-associated transcripts show a significantly higher mean expression than transcripts associated with non-SUPR-containing promoters. The same was true for the comparison between all SUPR-associated and non-SUPR-associated transcripts on a genome-wide basis. SUPR-associated genes show a highly significant tendency to occur in regions that are also enriched for intergenic short ultraconserved elements (SUE) in the vicinity of developmental genes. A number of predicted transcription factor binding sites (TFBS) are overrepresented in SUPRs and SUEs, including those for transcription factors of the homeodomain family, but in contrast to SUEs, SUPRs are also enriched in core-promoter motifs. These observations suggest that SUPRs delineate a distinct class of ultraconserved sequences.\n
\n\n\n
\n\n\n
\n \n\n \n \n Kai Ye, Marcel H. Schulz, Quan Long, Rolf Apweiler, & Zemin Ning.\n\n\n \n \n \n \n Pindel: a pattern growth approach to detect break points of large deletions and medium sized insertions from paired-end short reads.\n \n \n \n\n\n \n\n\n\n Bioinformatics (Oxford, England), 25(21): 2865–2871. November 2009.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{ye_pindel_2009,\n\ttitle = {Pindel: a pattern growth approach to detect break points of large deletions and medium sized insertions from paired-end short reads},\n\tvolume = {25},\n\tissn = {1367-4811},\n\tshorttitle = {Pindel},\n\tdoi = {10.1093/bioinformatics/btp394},\n\tabstract = {MOTIVATION: There is a strong demand in the genomic community to develop effective algorithms to reliably identify genomic variants. Indel detection using next-gen data is difficult and identification of long structural variations is extremely challenging.\nRESULTS: We present Pindel, a pattern growth approach, to detect breakpoints of large deletions and medium-sized insertions from paired-end short reads. We use both simulated reads and real data to demonstrate the efficiency of the computer program and accuracy of the results.\nAVAILABILITY: The binary code and a short user manual can be freely downloaded from http://www.ebi.ac.uk/ approximately kye/pindel/.\nCONTACT: k.ye@lumc.nl; zn1@sanger.ac.uk.},\n\tlanguage = {eng},\n\tnumber = {21},\n\tjournal = {Bioinformatics (Oxford, England)},\n\tauthor = {Ye, Kai and Schulz, Marcel H. and Long, Quan and Apweiler, Rolf and Ning, Zemin},\n\tmonth = nov,\n\tyear = {2009},\n\tpmid = {19561018},\n\tpmcid = {PMC2781750},\n\tkeywords = {Algorithms, Chromosome Breakpoints, Computational Biology, DNA Breaks, Genome, INDEL Mutation, Sequence Analysis, DNA, Software},\n\tpages = {2865--2871},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/IZVKUL3B/Ye et al. - 2009 - Pindel a pattern growth approach to detect break .pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n MOTIVATION: There is a strong demand in the genomic community to develop effective algorithms to reliably identify genomic variants. Indel detection using next-gen data is difficult and identification of long structural variations is extremely challenging. RESULTS: We present Pindel, a pattern growth approach, to detect breakpoints of large deletions and medium-sized insertions from paired-end short reads. We use both simulated reads and real data to demonstrate the efficiency of the computer program and accuracy of the results. AVAILABILITY: The binary code and a short user manual can be freely downloaded from http://www.ebi.ac.uk/ approximately kye/pindel/. CONTACT: k.ye@lumc.nl; zn1@sanger.ac.uk.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2008\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n Marc Sultan, Marcel H. Schulz, Hugues Richard, Alon Magen, Andreas Klingenhoff, Matthias Scherf, Martin Seifert, Tatjana Borodina, Aleksey Soldatov, Dmitri Parkhomchuk, Dominic Schmidt, Sean O'Keeffe, Stefan Haas, Martin Vingron, Hans Lehrach, & Marie-Laure Yaspo.\n\n\n \n \n \n \n A global view of gene activity and alternative splicing by deep sequencing of the human transcriptome.\n \n \n \n\n\n \n\n\n\n Science (New York, N.Y.), 321(5891): 956–960. August 2008.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{sultan_global_2008,\n\ttitle = {A global view of gene activity and alternative splicing by deep sequencing of the human transcriptome},\n\tvolume = {321},\n\tissn = {1095-9203},\n\tdoi = {10.1126/science.1160342},\n\tabstract = {The functional complexity of the human transcriptome is not yet fully elucidated. We report a high-throughput sequence of the human transcriptome from a human embryonic kidney and a B cell line. We used shotgun sequencing of transcripts to generate randomly distributed reads. Of these, 50\\% mapped to unique genomic locations, of which 80\\% corresponded to known exons. We found that 66\\% of the polyadenylated transcriptome mapped to known genes and 34\\% to nonannotated genomic regions. On the basis of known transcripts, RNA-Seq can detect 25\\% more genes than can microarrays. A global survey of messenger RNA splicing events identified 94,241 splice junctions (4096 of which were previously unidentified) and showed that exon skipping is the most prevalent form of alternative splicing.},\n\tlanguage = {eng},\n\tnumber = {5891},\n\tjournal = {Science (New York, N.Y.)},\n\tauthor = {Sultan, Marc and Schulz, Marcel H. and Richard, Hugues and Magen, Alon and Klingenhoff, Andreas and Scherf, Matthias and Seifert, Martin and Borodina, Tatjana and Soldatov, Aleksey and Parkhomchuk, Dmitri and Schmidt, Dominic and O'Keeffe, Sean and Haas, Stefan and Vingron, Martin and Lehrach, Hans and Yaspo, Marie-Laure},\n\tmonth = aug,\n\tyear = {2008},\n\tpmid = {18599741},\n\tkeywords = {Alternative Splicing, Cell Line, Cell Line, Tumor, Computational Biology, DNA, Complementary, DNA, Intergenic, Exons, Gene Expression Profiling, Genome, Human, Humans, Introns, Oligonucleotide Array Sequence Analysis, RNA Polymerase II, RNA Splice Sites, RNA, Messenger, Sequence Analysis, RNA},\n\tpages = {956--960},\n}\n\n
\n
\n\n\n
\n The functional complexity of the human transcriptome is not yet fully elucidated. We report a high-throughput sequence of the human transcriptome from a human embryonic kidney and a B cell line. We used shotgun sequencing of transcripts to generate randomly distributed reads. Of these, 50% mapped to unique genomic locations, of which 80% corresponded to known exons. We found that 66% of the polyadenylated transcriptome mapped to known genes and 34% to nonannotated genomic regions. On the basis of known transcripts, RNA-Seq can detect 25% more genes than can microarrays. A global survey of messenger RNA splicing events identified 94,241 splice junctions (4096 of which were previously unidentified) and showed that exon skipping is the most prevalent form of alternative splicing.\n
\n\n\n
\n\n\n
\n \n\n \n \n Wei Chen, Vera Kalscheuer, Andreas Tzschach, Corinna Menzel, Reinhard Ullmann, Marcel Holger Schulz, Fikret Erdogan, Na Li, Zofia Kijas, Ger Arkesteijn, Isidora Lopez Pajares, Margret Goetz-Sothmann, Uwe Heinrich, Imma Rost, Andreas Dufke, Ute Grasshoff, Birgitta Glaeser, Martin Vingron, & H. Hilger Ropers.\n\n\n \n \n \n \n Mapping translocation breakpoints by next-generation sequencing.\n \n \n \n\n\n \n\n\n\n Genome Research, 18(7): 1143–1149. July 2008.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{chen_mapping_2008,\n\ttitle = {Mapping translocation breakpoints by next-generation sequencing},\n\tvolume = {18},\n\tissn = {1088-9051},\n\tdoi = {10.1101/gr.076166.108},\n\tabstract = {Balanced chromosome rearrangements (BCRs) can cause genetic diseases by disrupting or inactivating specific genes, and the characterization of breakpoints in disease-associated BCRs has been instrumental in the molecular elucidation of a wide variety of genetic disorders. However, mapping chromosome breakpoints using traditional methods, such as in situ hybridization with fluorescent dye-labeled bacterial artificial chromosome clones (BAC-FISH), is rather laborious and time-consuming. In addition, the resolution of BAC-FISH is often insufficient to unequivocally identify the disrupted gene. To overcome these limitations, we have performed shotgun sequencing of flow-sorted derivative chromosomes using "next-generation" (Illumina/Solexa) multiplex sequencing-by-synthesis technology. As shown here for three different disease-associated BCRs, the coverage attained by this platform is sufficient to bridge the breakpoints by PCR amplification, and this procedure allows the determination of their exact nucleotide positions within a few weeks. Its implementation will greatly facilitate large-scale breakpoint mapping and gene finding in patients with disease-associated balanced translocations.},\n\tlanguage = {eng},\n\tnumber = {7},\n\tjournal = {Genome Research},\n\tauthor = {Chen, Wei and Kalscheuer, Vera and Tzschach, Andreas and Menzel, Corinna and Ullmann, Reinhard and Schulz, Marcel Holger and Erdogan, Fikret and Li, Na and Kijas, Zofia and Arkesteijn, Ger and Pajares, Isidora Lopez and Goetz-Sothmann, Margret and Heinrich, Uwe and Rost, Imma and Dufke, Andreas and Grasshoff, Ute and Glaeser, Birgitta and Vingron, Martin and Ropers, H. Hilger},\n\tmonth = jul,\n\tyear = {2008},\n\tpmid = {18326688},\n\tpmcid = {PMC2493403},\n\tkeywords = {Adolescent, Base Sequence, Child, Chromosome Breakage, Chromosome Mapping, Female, Humans, Intellectual Disability, Male, Molecular Sequence Data, Sequence Analysis, DNA, Translocation, Genetic},\n\tpages = {1143--1149},\n\tfile = {Volltext:/Users/mschulz/Zotero/storage/UU2S77AV/Chen et al. - 2008 - Mapping translocation breakpoints by next-generati.pdf:application/pdf},\n}\n\n
\n
\n\n\n
\n Balanced chromosome rearrangements (BCRs) can cause genetic diseases by disrupting or inactivating specific genes, and the characterization of breakpoints in disease-associated BCRs has been instrumental in the molecular elucidation of a wide variety of genetic disorders. However, mapping chromosome breakpoints using traditional methods, such as in situ hybridization with fluorescent dye-labeled bacterial artificial chromosome clones (BAC-FISH), is rather laborious and time-consuming. In addition, the resolution of BAC-FISH is often insufficient to unequivocally identify the disrupted gene. To overcome these limitations, we have performed shotgun sequencing of flow-sorted derivative chromosomes using \"next-generation\" (Illumina/Solexa) multiplex sequencing-by-synthesis technology. As shown here for three different disease-associated BCRs, the coverage attained by this platform is sufficient to bridge the breakpoints by PCR amplification, and this procedure allows the determination of their exact nucleotide positions within a few weeks. Its implementation will greatly facilitate large-scale breakpoint mapping and gene finding in patients with disease-associated balanced translocations.\n
\n\n\n
\n\n\n
\n \n\n \n \n Marcel H. Schulz, Sebastian Bauer, & Peter N. Robinson.\n\n\n \n \n \n \n The generalised k-Truncated Suffix Tree for time-and space-efficient searches in multiple DNA or protein sequences.\n \n \n \n\n\n \n\n\n\n International Journal of Bioinformatics Research and Applications, 4(1): 81–95. 2008.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{schulz_generalised_2008,\n\ttitle = {The generalised k-{Truncated} {Suffix} {Tree} for time-and space-efficient searches in multiple {DNA} or protein sequences},\n\tvolume = {4},\n\tissn = {1744-5485},\n\tdoi = {10.1504/IJBRA.2008.017165},\n\tabstract = {Efficient searching for specific subsequences in a set of longer sequences is an important component of many bioinformatics algorithms. Generalised suffix trees and suffix arrays allow searches for a pattern of length n in time proportional to n independent of the length of the sequences, and are thus attractive for a variety of applications. Here, we present an algorithm termed the generalised k-Truncated Suffix Tree (kTST), that represents an adaption of Ukkonen's linear-time suffix tree construction algorithm. The kTST algorithm creates a k-deep tree in linear time that allows rapid searches for short patterns of length of up to k characters. The kTST can offer advantages in computational time and memory usage for searches for short sequences in DNA or protein sequences compared to other suffix-based algorithms.},\n\tlanguage = {eng},\n\tnumber = {1},\n\tjournal = {International Journal of Bioinformatics Research and Applications},\n\tauthor = {Schulz, Marcel H. and Bauer, Sebastian and Robinson, Peter N.},\n\tyear = {2008},\n\tpmid = {18283030},\n\tkeywords = {Algorithms, Amino Acid Sequence, Base Sequence, Molecular Sequence Data, Pattern Recognition, Automated, Sequence Alignment, Sequence Analysis, DNA, Sequence Analysis, Protein},\n\tpages = {81--95},\n}\n\n
\n
\n\n\n
\n Efficient searching for specific subsequences in a set of longer sequences is an important component of many bioinformatics algorithms. Generalised suffix trees and suffix arrays allow searches for a pattern of length n in time proportional to n independent of the length of the sequences, and are thus attractive for a variety of applications. Here, we present an algorithm termed the generalised k-Truncated Suffix Tree (kTST), that represents an adaption of Ukkonen's linear-time suffix tree construction algorithm. The kTST algorithm creates a k-deep tree in linear time that allows rapid searches for short patterns of length of up to k characters. The kTST can offer advantages in computational time and memory usage for searches for short sequences in DNA or protein sequences compared to other suffix-based algorithms.\n
\n\n\n
\n\n\n
\n \n\n \n \n Gao Guo, Sebastian Bauer, Jochen Hecht, Marcel H. Schulz, Andreas Busche, & Peter N. Robinson.\n\n\n \n \n \n \n A short ultraconserved sequence drives transcription from an alternate FBN1 promoter.\n \n \n \n\n\n \n\n\n\n The International Journal of Biochemistry & Cell Biology, 40(4): 638–650. 2008.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n
@article{guo_short_2008,\n\ttitle = {A short ultraconserved sequence drives transcription from an alternate {FBN1} promoter},\n\tvolume = {40},\n\tissn = {1357-2725},\n\tdoi = {10.1016/j.biocel.2007.09.004},\n\tabstract = {FBN1, the gene mutated in Marfan syndrome, encodes fibrillin-1, a large glycoprotein component of the extracellular microfibrils. Human FBN1 has three untranslated upstream exons, and homologous sequences can be identified in a number of mammalian species. In this work, we have used functional assays to characterize the FBN1 upstream region. Sequences upstream of exon 1 and at least two of the upstream untranslated exons were shown to possess promoter activity in vitro. The strongest activity in luciferase assays was shown for sequences upstream of the untranslated exon A. Sequence analysis of the sequences in and upstream of exon A in humans and six other mammalian species demonstrated several highly conserved potential cis-acting sequences as well as a 66-basepair (bp) ultraconserved sequence with nearly perfect conservation in the seven species. The ultraconserved sequence contains an initiator element (Inr), a downstream promoter element (DPE), and a 10-bp palindromic element. Mutational assays showed that both the Inr and the DPE are critical for full promoter activity. A mutation of the 10-bp palindromic element completely abolished basal promoter activity. The element was shown to bind specifically to an unknown nuclear protein by electrophoretic mobility shift assay. Ultraconservation within an alternate promoter has not been previously reported. We suggest that the ultraconservation may reflect the importance of finely tuned regulation of alternate transcription of FBN1 and that the sequences involved have been under negative selective pressure for at least the last 180 million years of mammalian evolution.},\n\tlanguage = {eng},\n\tnumber = {4},\n\tjournal = {The International Journal of Biochemistry \\& Cell Biology},\n\tauthor = {Guo, Gao and Bauer, Sebastian and Hecht, Jochen and Schulz, Marcel H. and Busche, Andreas and Robinson, Peter N.},\n\tyear = {2008},\n\tpmid = {17996480},\n\tkeywords = {Base Sequence, Binding Sites, Cells, Cultured, Conserved Sequence, DNA Mutational Analysis, Electrophoretic Mobility Shift Assay, Exons, Fibrillin-1, Fibrillins, Humans, Microfilament Proteins, Models, Genetic, Molecular Sequence Data, Mutation, Promoter Regions, Genetic, Sequence Homology, Nucleic Acid, Transcription, Genetic},\n\tpages = {638--650},\n}\n\n
\n
\n\n\n
\n FBN1, the gene mutated in Marfan syndrome, encodes fibrillin-1, a large glycoprotein component of the extracellular microfibrils. Human FBN1 has three untranslated upstream exons, and homologous sequences can be identified in a number of mammalian species. In this work, we have used functional assays to characterize the FBN1 upstream region. Sequences upstream of exon 1 and at least two of the upstream untranslated exons were shown to possess promoter activity in vitro. The strongest activity in luciferase assays was shown for sequences upstream of the untranslated exon A. Sequence analysis of the sequences in and upstream of exon A in humans and six other mammalian species demonstrated several highly conserved potential cis-acting sequences as well as a 66-basepair (bp) ultraconserved sequence with nearly perfect conservation in the seven species. The ultraconserved sequence contains an initiator element (Inr), a downstream promoter element (DPE), and a 10-bp palindromic element. Mutational assays showed that both the Inr and the DPE are critical for full promoter activity. A mutation of the 10-bp palindromic element completely abolished basal promoter activity. The element was shown to bind specifically to an unknown nuclear protein by electrophoretic mobility shift assay. Ultraconservation within an alternate promoter has not been previously reported. We suggest that the ultraconservation may reflect the importance of finely tuned regulation of alternate transcription of FBN1 and that the sequences involved have been under negative selective pressure for at least the last 180 million years of mammalian evolution.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n\n \n \n \n \n\n
\n"}; document.write(bibbase_data.data);