<script src="https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d/group/f5b9ee19-654f-3d16-8c8d-62e8c4f73340?jsonp=1"></script>
<?php
$contents = file_get_contents("https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d/group/f5b9ee19-654f-3d16-8c8d-62e8c4f73340");
print_r($contents);
?>
<iframe src="https://bibbase.org/service/mendeley/42d295c0-0737-38d6-8b43-508cab6ea85d/group/f5b9ee19-654f-3d16-8c8d-62e8c4f73340"></iframe>
For more details see the documention.
To the site owner:
Action required! Mendeley is changing its API. In order to keep using Mendeley with BibBase past April 14th, you need to:
@article{ title = {Population Genetics of Paramecium Mitochondrial Genomes: Recombination, Mutation Spectrum, and Efficacy of Selection.}, type = {article}, year = {2019}, keywords = {Paramecium,efficacy of purifying selection,mitochondria,mutation spectrum,recombination,telomeres}, pages = {1398-1416}, volume = {11}, websites = {http://www.ncbi.nlm.nih.gov/pubmed/30980669,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC6505448}, day = {1}, id = {fbae2b83-f710-335c-baf7-45137643735c}, created = {2019-08-19T20:55:39.494Z}, accessed = {2019-08-09}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-19T20:55:39.494Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {The evolution of mitochondrial genomes and their population-genetic environment among unicellular eukaryotes are understudied. Ciliate mitochondrial genomes exhibit a unique combination of characteristics, including a linear organization and the presence of multiple genes with no known function or detectable homologs in other eukaryotes. Here we study the variation of ciliate mitochondrial genomes both within and across 13 highly diverged Paramecium species, including multiple species from the P. aurelia species complex, with four outgroup species: P. caudatum, P. multimicronucleatum, and two strains that may represent novel related species. We observe extraordinary conservation of gene order and protein-coding content in Paramecium mitochondria across species. In contrast, significant differences are observed in tRNA content and copy number, which is highly conserved in species belonging to the P. aurelia complex but variable among and even within the other Paramecium species. There is an increase in GC content from ∼20% to ∼40% on the branch leading to the P. aurelia complex. Patterns of polymorphism in population-genomic data and mutation-accumulation experiments suggest that the increase in GC content is primarily due to changes in the mutation spectra in the P. aurelia species. Finally, we find no evidence of recombination in Paramecium mitochondria and find that the mitochondrial genome appears to experience either similar or stronger efficacy of purifying selection than the nucleus.}, bibtype = {article}, author = {Johri, Parul and Marinov, Georgi K and Doak, Thomas G and Lynch, Michael}, doi = {10.1093/gbe/evz081}, journal = {Genome Biology and Evolution}, number = {5} }
@techreport{ title = {The Pervasive Technology Institute at 20: Two decades of success and counting}, type = {techreport}, year = {2019}, websites = {http://hdl.handle.net/2022/22607}, id = {c51dc48e-468b-3770-8f33-dc0b4b91c039}, created = {2019-08-20T15:53:54.669Z}, accessed = {2019-08-20}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-10-01T17:56:36.556Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, bibtype = {techreport}, author = {Stewart, Craig A.; and Welch, Von; and Doak, Thomas G.; and Miller, Therese; and Plale, Beth; and Walsh, John A.; and Link, Matthew R.; and Snapp-Childs, Winona}, doi = {10.5967/QDF0-S837} }
@article{ title = {Escherichia coli cultures maintain stable subpopulation structure during long-term evolution}, type = {article}, year = {2018}, keywords = {Article; bacterial colonization; bacterial gene; b}, pages = {E4642-E4650}, volume = {115}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85046974773&doi=10.1073%2Fpnas.1708371115&partnerID=40&md5=f03cd74612020bba927dfd16284a2ae6}, publisher = {National Academy of Sciences}, id = {96ec5e81-f3ac-3655-86dc-2fbf48bddc5a}, created = {2018-07-12T19:57:02.649Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-07-12T19:57:02.649Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Behringer2018E4642}, source_type = {article}, notes = {cited By 0}, private_publication = {false}, abstract = {How genetic variation is generated and maintained remains a central question in evolutionary biology. When presented with a complex environment, microbes can take advantage of genetic variation to exploit new niches. Here we present a massively parallel experiment where WT and repair-deficient (ΔmutL) Escherichia coli populations have evolved over 3 y in a spatially heterogeneous and nutritionally complex environment. Metage-nomic sequencing revealed that these initially isogenic populations evolved and maintained stable subpopulation structure in just 10 mL of medium for up to 10,000 generations, consisting of up to five major haplotypes with many minor haplotypes. We characterized the genomic, transcriptomic, exometabolomic, and phenotypic differences between clonal isolates, revealing subpopulation structure driven primarily by spatial segregation followed by differential utilization of nutrients. In addition to genes regulating the import and catabolism of nutrients, major polymorphisms of note included insertion elements transposing into fimE (regulator of the type I fimbriae) and upstream of hns (global regulator of environmental-change and stress-response genes), both known to regulate biofilm formation. Interestingly, these genes have also been identified as critical to colonization in uro-pathogenic E. coli infections. Our findings illustrate the complexity that can arise and persist even in small cultures, raising the possibility that infections may often be promoted by an evolving and complex pathogen population. © 2018 National Academy of Sciences. All rights reserved.}, bibtype = {article}, author = {Behringer, M G and Choi, B I and Miller, S F and Doak, T G and Karty, J A and Guo, W and Lynch, M}, doi = {10.1073/pnas.1708371115}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, number = {20} }
@article{ title = {Insights into an Extensively Fragmented Eukaryotic Genome: De Novo Genome Sequencing of the Multinuclear Ciliate Uroleptopsis citrina}, type = {article}, year = {2018}, pages = {883-894}, volume = {10}, publisher = {Oxford University Press}, id = {060b722b-39e3-3fd3-98da-b031ae8f6d90}, created = {2018-07-12T19:57:02.768Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-19T19:27:00.874Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {JOUR}, private_publication = {false}, abstract = {Ciliated protists are a large group of single-celled eukaryotes with separate germline and somatic nuclei in each cell. The somatic genome is developed from the zygotic nucleus through a series of chromosomal rearrangements, including fragmentation, DNA elimination, de novo telomere addition, and DNA amplification. This unique feature makes them perfect models for research in genome biology and evolution. However, genomic research of ciliates has been limited to a few species, owing to problems with DNA contamination and obstacles in cultivation. Here, we introduce a method combining telomere-primer PCR amplification and high-throughput sequencing, which can reduce DNA contamination and obtain genomic data efficiently. Based on this method, we report a draft somatic genome of a multimacronuclear ciliate, Uroleptopsis citrina. 1) The telomeric sequence in U. citrina is confirmed to be C4A4C4A4C4 by directly blunt-end cloning. 2) Genomic analysis of the resulting chromosomes shows a “one-gene one-chromosome” pattern, with a small number of multiple-gene chromosomes. 3) Amino acid usage is analyzed, and reassignment of stop codons is confirmed. 4) Chromosomal analysis shows an obvious asymmetrical GC skew and high bias between A and T in the subtelomeric regions of the sense-strand, with the detection of an 11-bp high AT motif region in the 3′ subtelomeric region. 5) The subtelomeric sequence also has an obvious 40 nt strand oscillation of nucleotide ratio. 6) In the 5′ subtelomeric region of the coding strand, the distribution of potential TATA-box regions is illustrated, which accumulate between 30 and 50 nt. This work provides a valuable reference for genomic research and furthers our understanding of the dynamic nature of unicellular eukaryotic genomes.}, bibtype = {article}, author = {Zheng, Weibo and Wang, Chundi and Yan, Ying and Gao, Feng and Doak, Thomas G and Song, Weibo}, doi = {https://doi.org/10.1093/gbe/evy055}, journal = {Genome Biology and Evolution}, number = {3} }
@article{ title = {Limited mutation-rate variation within the Paramecium aurelia species complex}, type = {article}, year = {2018}, keywords = {Ciliated protozoa mutationaccumulation,Neutral evolution}, pages = {2523-2526}, volume = {8}, month = {7}, publisher = {Genetics Society of America}, day = {1}, id = {b5cc56ae-3f67-342e-886f-4a3978c491bb}, created = {2019-08-20T14:05:14.026Z}, accessed = {2019-08-20}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-20T14:09:28.316Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {© 2018 Long et al. Mutation is one of the most fundamental evolutionary forces. Studying variation in the mutation rate within and among closely-related species can help reveal mechanisms of genome divergence, but such variation is unstudied in the vast majority of organisms. Previous studies on ciliated protozoa have found extremely low mutation rates. In this study, using mutation-accumulation techniques combined with deep whole-genome sequencing, we explore the germline base-substitution mutation-rate variation of three cryptic species in the Paramecium aurelia species complex-P. biaurelia, P. sexaurelia, and P. tetraurelia. We find that there is extremely limited variation of the mutation rate and spectrum in the three species and confirm the extremely low mutation rate of ciliates.}, bibtype = {article}, author = {Long, Hongan and Doak, Thomas G. and Lynch, Michael}, doi = {10.1534/g3.118.200420}, journal = {G3: Genes, Genomes, Genetics}, number = {7} }
@article{ title = {Stilbenoid prenyltransferases define key steps in the diversification of peanut phytoalexins.}, type = {article}, year = {2018}, keywords = {Arachidin,arachidin,hairy root,peanut,plant biochemistry,prenylation,resveratrol,secondary metabolism,small molecule,stilbenoid,transcriptomics}, pages = {28-46}, volume = {293}, websites = {http://www.ncbi.nlm.nih.gov/pubmed/29158266,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC5766904}, id = {17352f82-23fd-3fbf-ad08-5820e6d003fc}, created = {2019-08-27T17:33:45.773Z}, accessed = {2019-08-27}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:44:30.521Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {Defense responses of peanut (Arachis hypogaea) to biotic and abiotic stresses include the synthesis of prenylated stilbenoids. Members of this compound class show several protective activities in human disease studies, and the list of potential therapeutic targets continues to expand. Despite their medical and biological importance, the biosynthetic pathways of prenylated stilbenoids remain to be elucidated, and the genes encoding stilbenoid-specific prenyltransferases have yet to be identified in any plant species. In this study, we combined targeted transcriptomic and metabolomic analyses to discover prenyltransferase genes in elicitor-treated peanut hairy root cultures. Transcripts encoding five enzymes were identified, and two of these were functionally characterized in a transient expression system consisting of Agrobacterium-infiltrated leaves of Nicotiana benthamiana We observed that one of these prenyltransferases, AhR4DT-1, catalyzes a key reaction in the biosynthesis of prenylated stilbenoids, in which resveratrol is prenylated at its C-4 position to form arachidin-2, whereas another, AhR3'DT-1, added the prenyl group to C-3' of resveratrol. Each of these prenyltransferases was highly specific for stilbenoid substrates, and we confirmed their subcellular location in the plastid by fluorescence microscopy. Structural analysis of the prenylated stilbenoids suggested that these two prenyltransferase activities represent the first committed steps in the biosynthesis of a large number of prenylated stilbenoids and their derivatives in peanut. In summary, we have identified five candidate prenyltransferases in peanut and confirmed that two of them are stilbenoid-specific, advancing our understanding of this specialized enzyme family and shedding critical light onto the biosynthesis of bioactive stilbenoids.}, bibtype = {article}, author = {Yang, Tianhong and Fang, Lingling and Sanders, Sheri and Jayanthi, Srinivas and Rajan, Gayathri and Podicheti, Ram and Thallapuranam, Suresh Kumar and Mockaitis, Keithanne and Medina-Bolivar, Fabricio}, doi = {10.1074/jbc.RA117.000564}, journal = {The Journal of biological chemistry}, number = {1} }
@techreport{ title = {ABI Sustaining: The National Center for Genome Analysis Support 2018 Annual Report}, type = {techreport}, year = {2018}, keywords = {NCGAS,National Science Foundation}, websites = {http://creativecommons.org/licenses/by/4.0/.}, month = {9}, day = {10}, id = {10e9e19c-a1d6-3bd0-b79e-a9d28e84f354}, created = {2020-09-09T20:51:15.358Z}, accessed = {2020-09-09}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-11T16:59:05.396Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {National Science Foundation ABI-1458641}, bibtype = {techreport}, author = {Michaels, Scott D and Doak, T G and Stewart, C A and Michaels, S D (} }
@techreport{ title = {Summary of the National Center for Genome Analysis Support (NCGAS) 2018 de Novo Transcriptome Workflow and Workshop}, type = {techreport}, year = {2018}, keywords = {NCGAS,NSF Report,Transcriptome Assembly,Workshop}, websites = {https://scholarworks.iu.edu/dspace/handle/2022/22254}, month = {6}, day = {7}, id = {f53aba7a-6437-3cf9-b893-96737fca42d4}, created = {2020-09-09T21:03:58.828Z}, accessed = {2020-09-09}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-09T21:03:58.933Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, bibtype = {techreport}, author = {Sanders, Sheri A and Ganote, Carrie L and Papudeshi, Bhavya and Stewart, Craig A and Doak, Thomas G} }
@article{ title = {Population Genomics of Paramecium Species}, type = {article}, year = {2017}, keywords = {Animals; DNA,DNA flanking region; genetic polymorphism; genome;,Mitochondrial; Evolution,Molecular; Genetic Variation; Genome,Protozoan; Genomics; Metagenomics; Mutation; Para,mitochondrial DNA}, pages = {1194-1216}, volume = {34}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85019092588&doi=10.1093%2Fmolbev%2Fmsx074&partnerID=40&md5=3f72c45c5cb74e418d2e45c4368ebd32}, publisher = {Oxford University Press}, id = {c72fe2c9-d65f-384f-873e-cd4902cb8ad1}, created = {2018-02-27T18:07:45.769Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.769Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Johri20171194}, source_type = {article}, notes = {cited By 0}, private_publication = {false}, abstract = {Population-genomic analyses are essential to understanding factors shaping genomic variation and lineage-specific sequence constraints. The dearth of such analyses for unicellular eukaryotes prompted us to assess genomic variation in Paramecium, one of the most well-studied ciliate genera. The Paramecium aurelia complex consists of ∼15 morphologically indistinguishable species that diverged subsequent to two rounds of whole-genome duplications (WGDs, as long as 320 MYA) and possess extremely streamlined genomes. We examine patterns of both nuclear and mitochondrial polymorphism, by sequencing whole genomes of 10-13 worldwide isolates of each of three species belonging to the P. aurelia complex: P. tetraurelia, P. biaurelia, P. sexaurelia, as well as two outgroup species that do not share the WGDs: P. caudatum and P. multimicronucleatum. An apparent absence of global geographic population structure suggests continuous or recent dispersal of Paramecium over long distances. Intergenic regions are highly constrained relative to coding sequences, especially in P. caudatum and P. multimicronucleatum that have shorter intergenic distances. Sequence diversity and divergence are reduced up to ∼100-150 bp both upstream and downstream of genes, suggesting strong constraints imposed by the presence of densely packed regulatory modules. In addition, comparison of sequence variation at non-synonymous and synonymous sites suggests similar recent selective pressures on paralogs within and orthologs across the deeply diverging species. This study presents the first genome-wide population-genomic analysis in ciliates and provides a valuable resource for future studies in evolutionary and functional genetics in Paramecium. © 2017 Published by Oxford University Press on behalf of the Society for Molecular Biology and Evolution. All rights reserved.}, bibtype = {article}, author = {Johri, P and Krenek, S and Marinov, G K and Doak, T G and Berendonk, T U and Lynch, M}, doi = {10.1093/molbev/msx074}, journal = {Molecular Biology and Evolution}, number = {5} }
@techreport{ title = {ABI Sustaining: The National Center for Genome Analysis Support 2017 Annual Report}, type = {techreport}, year = {2017}, id = {b9f6e0be-e20c-36ed-8431-d48d94b36cba}, created = {2018-02-27T18:07:46.131Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.131Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {RPRT}, private_publication = {false}, bibtype = {techreport}, author = {Doak, Thomas G and Stewart, Craig A and Michaels, Scott D} }
@techreport{ title = {Summary of the 2017 NCGAS User Survey}, type = {techreport}, year = {2017}, id = {5b1d061a-1ac2-3de6-89e2-057d23667e75}, created = {2018-02-27T18:07:47.126Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.126Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {RPRT}, private_publication = {false}, bibtype = {techreport}, author = {Doak, Thomas G and Stewart, Craig A and Michaels, Scott D} }
@inproceedings{ title = {A voice for bioinformatics}, type = {inproceedings}, year = {2017}, keywords = {Bioinformatics,Command line,Computer applications,Computer programming,Data movements,Ge,Genome analysis}, volume = {Part F1287}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85025816701&doi=10.1145%2F3093338.3093374&partnerID=40&md5=f475d6d55b3e3145ad7094dd9005a1f2}, publisher = {Association for Computing Machinery}, id = {60dd2c88-e5fe-3d32-9c37-1eb60d6e1fea}, created = {2018-02-27T18:07:47.324Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-19T20:44:28.534Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Ganote2017}, source_type = {conference}, notes = {cited By 0; Conference of 2017 Practice and Experience in Advanced Research Computing, PEARC 2017 ; Conference Date: 9 July 2017 Through 13 July 2017; Conference Code:128771}, private_publication = {false}, abstract = {One of the challenges to adoption of HPC is the disjunction between those who need it and those who know it. Biology (specifically, genomics) is a growing field for computational use, but the typical biologist does not have an established informatics background. The National Center for Genome Analysis Support (NCGAS) AIDS users in getting past the initial shock of the command line and guides them toward savvy cluster use. NCGAS is initiating a push to become domain champions alongside Oklahoma State's Brian Cougar. Our position at IU gives us a close relationship with XSEDE and we already fulfill a role in pushing users toward XSEDE resources when our local clusters are ill-suited to the job. We currently act as liaison between biologists and Jetstream, IU and TACC's research computing cloud. Typical issues include: Software installation; Software usage-what parameters do I choose, and how do I interpret the results; Batch job submission; Understanding how queues and job handlers work; Data movement, Spinning up VMs on Jetstream We will discuss how we have structured our support, and illustrate our impact on XSEDE resources. © 2017 ACM.}, bibtype = {inproceedings}, author = {Ganote, C L and Sanders, S A and Papudeshi, B N and Blood, P D and Doak, T G}, doi = {10.1145/3093338.3093374}, booktitle = {Proceedings of the Practice and Experience in Advanced Research Computing 2017 on Sustainability, Success and Impact (PEARC17)} }
@article{ title = {Estimating seven coefficients of pairwise relatedness using population-genomic data}, type = {article}, year = {2017}, keywords = {Alleles; Animals; Computer Simulation; Daphnia; G,Genetic,Population; Genotype; Heterozygote; Inbreeding; M,animal; Article; consanguinity; Daphnia pulex; gen}, pages = {105-118}, volume = {206}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85020718072&doi=10.1534%2Fgenetics.116.190660&partnerID=40&md5=74072b13c07af013108eb10cbe219fac}, publisher = {Genetics}, id = {f8d8da89-3b0d-3c48-843b-66e63bf817bc}, created = {2018-02-27T18:07:47.366Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.366Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Ackerman2017105}, source_type = {article}, notes = {cited By 0}, private_publication = {false}, abstract = {Population structure can be described by genotypic-correlation coefficients between groups of individuals, the most basic of which are the pairwise relatedness coefficients between any two individuals. There are nine pairwise relatedness coefficients in the most general model, and we show that these can be reduced to seven coefficients for biallelic loci. Although all nine coefficients can be estimated from pedigrees, six coefficients have been beyond empirical reach. We provide a numerical optimization procedure that estimates all seven reduced coefficients from population-genomic data. Simulations show that the procedure is nearly unbiased, even at 33 coverage, and errors in five of the seven coefficients are statistically uncorrelated. The remaining two coefficients have a negative correlation of errors, but their sum provides an unbiased assessment of the overall correlation of heterozygosity between two individuals. Application of these new methods to four populations of the freshwater crustacean Daphnia pulex reveal the occurrence of half siblings in our samples, as well as a number of identical individuals that are likely obligately asexual clone mates. Statistically significant negative estimates of these pairwise relatedness coefficients, including inbreeding coefficients that were typically negative, underscore the difficulties that arise when interpreting genotypic correlations as estimations of the probability that alleles are identical by descent. © 2017 by the Genetics Society of America.}, bibtype = {article}, author = {Ackerman, M S and Johri, P and Spitze, K and Xu, S and Doak, T G and Young, K and Lynch, M}, doi = {10.1534/genetics.116.190660}, journal = {Genetics}, number = {1} }
@article{ title = {Diversity and universality of endosymbiotic Rickettsia in the fish parasite Ichthyophthirius multifiliis}, type = {article}, year = {2017}, keywords = {Article,Bayesian learning,biodiversity,bootstra}, pages = {189}, volume = {8}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85014553705&doi=10.3389%2Ffmicb.2017.00189&partnerID=40&md5=f5b72ffd87ab95121f40b8b97320b41f}, publisher = {Frontiers Research Foundation}, id = {8e0e7246-3ea0-3f3f-bc94-def515506ff7}, created = {2018-02-27T18:07:47.887Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:44:30.546Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Zaila2017}, source_type = {article}, notes = {cited By 1}, private_publication = {false}, abstract = {Although the presence of endosymbiotic rickettsial bacteria, specifically Candidatus Megaira, has been reported in diverse habitats and a wide range of eukaryotic hosts, it remains unclear how broadly Ca. Megaira are distributed in a single host species. In this study we seek to address whether Ca. Megaira are present in most, if not all isolates, of the parasitic ciliate Ichthyophthirius multifiliis. Conserved regions of bacterial 16S rRNA genes were either PCR amplified, or assembled from deep sequencing data, from 18 isolates/populations of I. multifiliis sampled worldwide (Brazil, Taiwan, and USA). We found that rickettsial rRNA sequences belonging to three out of four Ca. Megaira subclades could be consistently detected in all I. multifiliis samples. I. multifiliis collected from local fish farms tend to be inhabited by the same subclade of Ca. Megaira, whereas those derived from pet fish are often inhabited by more than one subclade of Ca. Megaira. Distributions of Ca. Megaira in I. multifiliis thus better reflect the travel history, but not the phylogeny, of I. multifiliis. In summary, our results suggest that I. multifiliis may be dependent on this endosymbiotic relationship, and the association between Ca. Megaira and I. multifiliis is more diverse than previously thought. © 2017 Zaila, Doak, Ellerbrock, Tung, Martins, Kolbin, Yao, Cassidy-Hanley, Clark and Chang.}, bibtype = {article}, author = {Zaila, K E and Doak, T G and Ellerbrock, H and Tung, C.-H. and Martins, M L and Kolbin, D and Yao, M.-C. and Cassidy-Hanley, D M and Clark, T G and Chang, W.-J.}, doi = {10.3389/fmicb.2017.00189}, journal = {Frontiers in Microbiology}, number = {FEB} }
@article{ title = {Investigating biogeographic boundaries of the Sunda shelf: A phylogenetic analysis of two island populations of Macaca fascicularis}, type = {article}, year = {2017}, websites = {https://onlinelibrary.wiley.com/doi/full/10.1002/ajpa.23235}, id = {169e73fb-d708-3f38-a0e1-47bd8fe190ae}, created = {2019-08-19T20:55:39.428Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:33:55.981Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Klegarth2017}, source_type = {JOUR}, private_publication = {false}, bibtype = {article}, author = {Klegarth, A R and Sanders, S A and Gloss, A D and Lane‐deGraaf, K E and Jones‐Engel, L and Fuentes, A and Hollocher, H}, doi = {10.1002/ajpa.23235}, journal = {American Journal of Physical Anthropology}, keywords = {PY7} }
@article{ title = {Optimizing and evaluating the reconstruction of Metagenome-assembled microbial genomes}, type = {article}, year = {2017}, volume = {18}, websites = {https://bmcgenomics.biomedcentral.com/articles/10.1186/s12864-017-4294-1}, id = {5bd60dbe-aad2-3560-9d88-9bf1ba87f163}, created = {2019-08-19T20:55:39.450Z}, accessed = {2019-08-09}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:33:55.965Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {Background: Microbiome/host interactions describe characteristics that affect the host's health. Shotgun metagenomics includes sequencing a random subset of the microbiome to analyze its taxonomic and metabolic potential. Reconstruction of DNA fragments into genomes from metagenomes (called metagenome-assembled genomes) assigns unknown fragments to taxa/function and facilitates discovery of novel organisms. Genome reconstruction incorporates sequence assembly and sorting of assembled sequences into bins, characteristic of a genome. However, the microbial community composition, including taxonomic and phylogenetic diversity may influence genome reconstruction. We determine the optimal reconstruction method for four microbiome projects that had variable sequencing platforms (IonTorrent and Illumina), diversity (high or low), and environment (coral reefs and kelp forests), using a set of parameters to select for optimal assembly and binning tools. Methods: We tested the effects of the assembly and binning processes on population genome reconstruction using 105 marine metagenomes from 4 projects. Reconstructed genomes were obtained from each project using 3 assemblers (IDBA, MetaVelvet, and SPAdes) and 2 binning tools (GroopM and MetaBat). We assessed the efficiency of assemblers using statistics that including contig continuity and contig chimerism and the effectiveness of binning tools using genome completeness and taxonomic identification. Results: We concluded that SPAdes, assembled more contigs (143,718 ± 124 contigs) of longer length (N50 = 1632 ± 108 bp), and incorporated the most sequences (sequences-assembled = 19.65%). The microbial richness and evenness were maintained across the assembly, suggesting low contig chimeras. SPAdes assembly was responsive to the biological and technological variations within the project, compared with other assemblers. Among binning tools, we conclude that MetaBat produced bins with less variation in GC content (average standard deviation: 1.49), low species richness (4.91 ± 0.66), and higher genome completeness (40.92 ± 1.75) across all projects. MetaBat extracted 115 bins from the 4 projects of which 66 bins were identified as reconstructed metagenome-assembled genomes with sequences belonging to a specific genus. We identified 13 novel genomes, some of which were 100% complete, but show low similarity to genomes within databases. Conclusions: In conclusion, we present a set of biologically relevant parameters for evaluation to select for optimal assembly and binning tools. For the tools we tested, SPAdes assembler and MetaBat binning tools reconstructed quality metagenome-assembled genomes for the four projects. We also conclude that metagenomes from microbial communities that have high coverage of phylogenetically distinct, and low taxonomic diversity results in highest quality metagenome-assembled genomes.}, bibtype = {article}, author = {Papudeshi, Bhavya and Haggerty, J. Matthew and Doane, Michael and Morris, Megan M. and Walsh, Kevin and Beattie, Douglas T. and Pande, Dnyanada and Zaeri, Parisa and Silva, Genivaldo G.Z. and Thompson, Fabiano and Edwards, Robert A. and Dinsdale, Elizabeth A.}, doi = {10.1186/s12864-017-4294-1}, journal = {BMC Genomics}, number = {1} }
@techreport{ title = {Pervasive Technology Institute Annual Report: Research Innovations and Advanced Cyberinfrastructure Services in Support of IU Strategic Goals During FY 2017}, type = {techreport}, year = {2017}, websites = {http://hdl.handle.net/2022/21809}, id = {89f5470c-b7d9-3c3e-bd16-a1d1d6b2cb8b}, created = {2020-09-10T00:01:45.505Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-10T00:01:45.505Z}, read = {true}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Stewart2017}, source_type = {RPRT}, private_publication = {false}, bibtype = {techreport}, author = {Stewart, Craig; and Plale, Beth; and Welch, Von; and Pierce, Marlon; and Fox, Geoffrey C.; and Doak, Thomas G.; Hancock, David Y.; Henschel, Robert; and Link, Matthew R.; and Miller, Therese; and Wernert, Eric; and Boyles, Michael J.; and Fulton, Ben; and Weakley, Le Mai; and Ping, Robert; and Gniady, Tassie; and Snapp-Childs, Winona;} }
@techreport{ title = {Summary of the Survey of Field/Marine Station Directors and Managers}, type = {techreport}, year = {2017}, keywords = {Technical Report}, websites = {http://hdl.handle.net/2022/21835}, month = {7}, day = {31}, id = {ee37e686-dda2-3b98-b173-2459b85fe79e}, created = {2020-09-11T16:55:39.193Z}, accessed = {2020-09-11}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-11T16:55:39.193Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, bibtype = {techreport}, author = {Doak, Thomas G.; Stewart, Craig A.; Wernert, Julie; Hancock, David Y.; Miller, Therese;} }
@article{ title = {Genomic and metagenomic analysis of diversity-generating retroelements associated with Treponema denticola}, type = {article}, year = {2016}, keywords = {Article,amino acid substitution,bacterial genom,lipoprotein}, pages = {pp 852}, volume = {7}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84980008617&doi=10.3389%2Ffmicb.2016.00852&partnerID=40&md5=60c153d3e939419432ed9b21aa570c92,https://www.frontiersin.org/articles/10.3389/fmicb.2016.00852/full}, publisher = {Frontiers Research Foundation}, id = {d2d89c6d-77f0-34b5-b83f-6f654b57cd7d}, created = {2018-02-27T18:07:46.251Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:54:06.509Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Nimkulrat2016}, source_type = {article}, notes = {cited By 1}, private_publication = {false}, abstract = {Diversity-generating retroelements (DGRs) are genetic cassettes that can produce massive protein sequence variation in prokaryotes. Presumably DGRs confer selective advantages to their hosts (bacteria or viruses) by generating variants of target genes-typically resulting in target proteins with altered ligand-binding specificity-through a specialized error-prone reverse transcription process. The only extensively studied DGR system is from the Bordetella phage BPP-1, although DGRs are predicted to exist in other species. Using bioinformatics analysis, we discovered that the DGR system associated with the Treponema denticola species (a human oral-associated periopathogen) is dynamic (with gains/losses of the system found in the isolates) and diverse (with multiple types found in isolated genomes and the human microbiota). The T. denticola DGR is found in only nine of the 17 sequenced T. denticola strains. Analysis of the DGR-associated template regions and reverse transcriptase gene sequences revealed two types of DGR systems in T. denticola: The ATCC35405-type shared by seven isolates including ATCC35405; and the SP32-type shared by two isolates (SP32 and SP33), suggesting multiple DGR acquisitions. We detected additional variants of the T. denticola DGR systems in the human microbiomes, and found that the SP32-type DGR is more abundant than the ATCC35405-type in the healthy human oral microbiome, although the latter is found in more sequenced isolates. This is the first comprehensive study to characterize the DGRs associated with T. denticola in individual genomes as well as human microbiomes, demonstrating the importance of utilizing both individual genomes and metagenomes for characterizing the elements, and for analyzing their diversity and distribution in human populations. © 2016 Nimkulrat, Lee, Doak and Ye.}, bibtype = {article}, author = {Nimkulrat, S and Lee, H and Doak, T G and Ye, Y}, doi = {10.3389/fmicb.2016.00852}, journal = {Frontiers in Microbiology}, number = {JUN} }
@article{ title = {Disentangling the taxonomy of Rickettsiales and description of two novel symbionts ("Candidatus Bealeia paramacronuclearis" and "Candidatus Fokinia cryptica") sharing the cytoplasm of the ciliate protist Paramecium biaurelia}, type = {article}, year = {2016}, keywords = {Alphaproteobacteria; Anaplasmataceae; Bacteria (m,Bacteria,Cells; Cytology; Oligonucleotides; RNA,Endosymbiotic; Gram-negative bacteria; Molecular,bacterium; cells and cell components; cytoplasm;}, pages = {7236-7247}, volume = {82}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84997402854&doi=10.1128%2FAEM.02284-16&partnerID=40&md5=73a151d55bc8d5e37294b554f26a6128}, publisher = {American Society for Microbiology}, id = {d7ce88f9-44f3-340a-9ff9-fe5d3818d6da}, created = {2018-02-27T18:07:46.989Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.989Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Szokoli20167236}, source_type = {article}, notes = {cited By 1}, private_publication = {false}, abstract = {In the past 10 years, the number of endosymbionts described within the bacterial order Rickettsiales has constantly grown. Since 2006, 18 novel Rickettsiales genera inhabiting protists, such as ciliates and amoebae, have been described. In this work, we characterize two novel bacterial endosymbionts from Paramecium collected near Bloomington, IN. Both endosymbiotic species inhabit the cytoplasm of the same host. The Gram-negative bacterium "Candidatus Bealeia paramacronuclearis" occurs in clumps and is frequently associated with the host macronucleus. With its electron-dense cytoplasm and a distinct halo surrounding the cell, it is easily distinguishable from the second smaller symbiont, "Candidatus Fokinia cryptica," whose cytoplasm is electron lucid, lacks a halo, and is always surrounded by a symbiontophorous vacuole. For molecular characterization, the small-subunit rRNA genes were sequenced and used for taxonomic assignment as well as the design of species-specific oligonucleotide probes. Phylogenetic analyses revealed that "Candidatus Bealeia paramacronuclearis" clusters with the so-called "basal" Rickettsiales, and "Candidatus Fokinia cryptica" belongs to "Candidatus Midichloriaceae." We obtained tree topologies showing a separation of Rickettsiales into at least two groups: one represented by the families Rickettsiaceae, Anaplasmataceae, and "Candidatus Midichloriaceae" (RAM clade), and the other represented by "basal Rickettsiales," including "Candidatus Bealeia paramacronuclearis." Therefore, and in accordance with recent publications, we propose to limit the order Rickettsiales to the RAM clade and to raise "basal Rickettsiales" to an independent order, Holosporales ord. nov., inside Alphaproteobacteria, which presently includes four family-level clades. Additionally, we define the family "Candidatus Hepatincolaceae" and redefine the family Holosporaceae. © 2016, American Society for Microbiology. All Rights Reserved.}, bibtype = {article}, author = {Szokoli, F and Castelli, M and Sabaneyeva, E and Schrallhammer, M and Krenek, S and Doak, T G and Berendonk, T U and Petroni, G}, doi = {10.1128/AEM.02284-16}, journal = {Applied and Environmental Microbiology}, number = {24} }
@article{ title = {Insertion sequence-caused large-scale rearrangements in the genome of Escherichia coli}, type = {article}, year = {2016}, keywords = {Article; bacterial genome; controlled study; DNA f,Bacterial; Mutagenesis,Base Sequence; DNA Transposable Elements; Escheri,Insertional,Molecular; Genome,transposon}, pages = {7109-7119}, volume = {44}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84988377984&doi=10.1093%2Fnar%2Fgkw647&partnerID=40&md5=8bf10db5b54055c6f322feff9d7a4dc2}, publisher = {Oxford University Press}, id = {efc0498c-b371-31fb-ba87-ae4d840aed53}, created = {2018-02-27T18:07:48.646Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.646Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Lee20167109}, source_type = {article}, notes = {cited By 7}, private_publication = {false}, abstract = {A majority of large-scale bacterial genome rearrangements involve mobile genetic elements such as insertion sequence (IS) elements. Here we report novel insertions and excisions of IS elements and recombination between homologous IS elements identified in a large collection of Escherichia coli mutation accumulation lines by analysis of whole genome shotgun sequencing data. Based on 857 identified events (758 IS insertions, 98 recombinations and 1 excision), we estimate that the rate of IS insertion is 3.5 × 10-4 insertions per genome per generation and the rate of IS homologous recombination is 4.5 × 10-5 recombinations per genome per generation. These events are mostly contributed by the IS elements IS1, IS2, IS5 and IS186. Spatial analysis of new insertions suggest that transposition is biased to proximal insertions, and the length spectrum of IS-caused deletions is largely explained by local hopping. For any of the ISs studied there is no region of the circular genome that is favored or disfavored for new insertions but there are notable hotspots for deletions. Some elements have preferences for non-coding sequence or for the beginning and end of coding regions, largely explained by target site motifs. Interestingly, transposition and deletion rates remain constant across the wild-type and 12 mutant E. coli lines, each deficient in a distinct DNA repair pathway. Finally, we characterized the target sites of four IS families, confirming previous results and characterizing a highly specific pattern at IS186 target-sites, 5′-GGGG(N6/N7)CCCC-3′. We also detected 48 long deletions not involving IS elements. © 2016 The Author(s) 2016. Published by Oxford University Press on behalf of Nucleic Acids Research.}, bibtype = {article}, author = {Lee, H and Doak, T G and Popodi, E and Foster, P L and Tang, H}, doi = {10.1093/nar/gkw647}, journal = {Nucleic Acids Research}, number = {15} }
@article{ title = {The Rate and Spectrum of Spontaneous Mutations in Mycobacterium smegmatis, a Bacterium Naturally Devoid of the Postreplicative Mismatch Repair Pathway.}, type = {article}, year = {2016}, keywords = {GC bias,Mycobacteria,mutation accumulation}, pages = {2157-63}, volume = {6}, websites = {http://www.ncbi.nlm.nih.gov/pubmed/27194804,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4938668}, day = {7}, id = {3a810353-c372-3316-b64f-a9715d64721b}, created = {2019-08-20T15:04:53.430Z}, accessed = {2019-08-20}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-20T15:04:53.430Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {Mycobacterium smegmatis is a bacterium that is naturally devoid of known postreplicative DNA mismatch repair (MMR) homologs, mutS and mutL, providing an opportunity to investigate how the mutation rate and spectrum has evolved in the absence of a highly conserved primary repair pathway. Mutation accumulation experiments of M. smegmatis yielded a base-substitution mutation rate of 5.27 × 10(-10) per site per generation, or 0.0036 per genome per generation, which is surprisingly similar to the mutation rate in MMR-functional unicellular organisms. Transitions were found more frequently than transversions, with the A:T→G:C transition rate significantly higher than the G:C→A:T transition rate, opposite to what is observed in most studied bacteria. We also found that the transition-mutation rate of M. smegmatis is significantly lower than that of other naturally MMR-devoid or MMR-knockout organisms. Two possible candidates that could be responsible for maintaining high DNA fidelity in this MMR-deficient organism are the ancestral-like DNA polymerase DnaE1, which contains a highly efficient DNA proofreading histidinol phosphatase (PHP) domain, and/or the existence of a uracil-DNA glycosylase B (UdgB) homolog that might protect the GC-rich M. smegmatis genome against DNA damage arising from oxidation or deamination. Our results suggest that M. smegmatis has a noncanonical Dam (DNA adenine methylase) methylation system, with target motifs differing from those previously reported. The mutation features of M. smegmatis provide further evidence that genomes harbor alternative routes for improving replication fidelity, even in the absence of major repair pathways.}, bibtype = {article}, author = {Kucukyildirim, Sibel and Long, Hongan and Sung, Way and Miller, Samuel F and Doak, Thomas G and Lynch, Michael}, doi = {10.1534/g3.116.030130}, journal = {G3: Genes, Genomes, Genetics}, number = {7} }
@inproceedings{ title = {The advanced cyberinfrastructure research and education facilitators virtual residency: Toward a national cyberinfrastructure workforce}, type = {inproceedings}, year = {2016}, keywords = {Cyberinfrastructure,Train the trainer,Workforce development}, volume = {17-21-July-2016}, month = {7}, publisher = {Association for Computing Machinery}, day = {17}, id = {9b064219-8d77-32af-90cb-95a9c452bf18}, created = {2019-08-27T17:46:19.500Z}, accessed = {2019-08-27}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T17:46:19.602Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, abstract = {An Advanced Cyberinfrastructure Research and Education Facilitator (ACI-REF) works directly with researchers to advance the computing- and data-intensive aspects of their research, helping them to make effective use of Cyberinfrastructure (CI). The University of Oklahoma (OU) is leading a national "virtual residency" program to prepare ACI-REFs to provide CI facilitation to the diverse populations of Science, Technology, Engineering and Mathematics (STEM) researchers that they serve. Until recently, CI Facilitators have had no education or training program; the Virtual Residency program addresses this national need by providing: (1) training, specifically (a) summer workshops and (b) third party training opportunity alerts; (2) a community of CI Facilitators, enabled by (c) a biweekly conference call and (d) a mailing list.}, bibtype = {inproceedings}, author = {Neeman, Henry and Ganote, Carrie and Kalescky, Robert and Ramadugu, Sai Kumar and Sherman, Andrew H. and Bergstrom, Aaron and Gray, Zane and Lemley, Evan and Romanella, Alana and Stengel, Brian and Brunson, Dana and Guilfoos, Brian and Moore, Brian G. and Rush, Johnathan and Voss, Dan}, doi = {10.1145/2949550.2949584}, booktitle = {Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale (XSEDE16)} }
@article{ title = {Draft genome sequence of Caedibacter varicaedens, a kappa killer endosymbiont bacterium of the ciliate Paramecium biaurelia}, type = {article}, year = {2015}, volume = {3}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-85009471729&doi=10.1128%2FgenomeA.01310-15&partnerID=40&md5=f7f264dbe6b611814ea0d1ba9b3423e5}, publisher = {American Society for Microbiology}, id = {d39e3efe-d6ab-3ebf-b762-7d601270b228}, created = {2018-02-27T18:07:45.770Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.770Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Suzuki2015}, source_type = {article}, notes = {cited By 0}, private_publication = {false}, abstract = {Caedibacter varicaedens is a kappa killer endosymbiont bacterium of the ciliate Paramecium biaurelia. Here, we present the draft genome sequence of C. varicaedens. © 2015 Suzuki et al.}, bibtype = {article}, author = {Suzuki, H and Dapper, A L and Jackson, C E and Lee, H and Pejaver, V and Doak, T G and Lynch, M and Preer J.R., Jr.}, doi = {10.1128/genomeA.01310-15}, journal = {Genome Announcements}, number = {6} }
@article{ title = {Subtractive assembly for comparative metagenomics, and its application to type 2 diabetes metagenomes}, type = {article}, year = {2015}, keywords = {Diabetes Mellitus,Type 2; Gastrointestinal Tract; Humans; Metagenom,gastrointestinal tract; genetics; human; metagenom}, volume = {16}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84955647881&doi=10.1186%2Fs13059-015-0804-0&partnerID=40&md5=9dff4ceb8c224cd11f569d2f3102ccf2}, publisher = {BioMed Central Ltd.}, id = {5f4e175f-73ab-3932-87cc-906d6f0de4c5}, created = {2018-02-27T18:07:45.774Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.774Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Wang2015}, source_type = {article}, notes = {cited By 2}, private_publication = {false}, abstract = {Comparative metagenomics remains challenging due to the size and complexity of metagenomic datasets. Here we introduce subtractive assembly, a de novo assembly approach for comparative metagenomics that directly assembles only the differential reads that distinguish between two groups of metagenomes. Using simulated datasets, we show it improves both the efficiency of the assembly and the assembly quality of the differential genomes and genes. Further, its application to type 2 diabetes (T2D) metagenomic datasets reveals clear signatures of the T2D gut microbiome, revealing new phylogenetic and functional features of the gut microbial communities associated with T2D. © 2015 Wang et al.}, bibtype = {article}, author = {Wang, M and Doak, T G and Ye, Y}, doi = {10.1186/s13059-015-0804-0}, journal = {Genome Biology}, number = {1} }
@inproceedings{ title = {Cyberinfrastructure resources enabling creation of the loblolly pine reference transcriptome}, type = {inproceedings}, year = {2015}, pages = {1-6}, volume = {2015-July}, websites = {http://hdl.handle.net/2022/20488,http://dl.acm.org/citation.cfm?doid=2792745.2792748}, month = {7}, publisher = {ACM Press}, city = {New York, New York, USA}, id = {e1a62bd6-4514-3118-9d29-a840e9182040}, created = {2018-02-27T18:07:45.777Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-09-11T16:09:52.340Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {inproceedings}, private_publication = {false}, abstract = {Today's genomics technologies generate more sequence data than ever before possible, and at substantially lower costs, serving researchers across biological disciplines in transformative ways. Building transcriptome assemblies from RNA sequencing reads is one application of next-generation sequencing (NGS) that has held a central role in biological discovery in both model and non-model organisms, with and without whole genome sequence references. A major limitation in effective building of transcriptome references is no longer the sequencing data generation itself, but the computing infrastructure and expertise needed to assemble, analyze and manage the data. Here we describe a currently available resource dedicated to achieving such goals, and its use for extensive RNA assembly of up to 1.3 billion reads representing the massive transcriptome of loblolly pine, using four major assembly software installations. The Mason cluster, an XSEDE second tier resource at Indiana University, provides the necessary fast CPU cycles, large memory, and high I/O throughput for conducting large-scale genomics research. The National Center for Genome Analysis Support, or NCGAS, provides technical support in using HPC systems, bioinformatic support for determining the appropriate method to analyze a given dataset, and practical assistance in running computations. We demonstrate that a sufficient supercomputing resource and good workflow design are elements that are essential to large eukaryotic genomics and transcriptomics projects such as the complex transcriptome of loblolly pine, gene expression data that inform annotation and functional interpretation of the largest genome sequence reference to date.}, bibtype = {inproceedings}, author = {Wu, Le-Shin and Ganote, Carrie L. and Doak, Thomas G and Barnett, William and Mockaitis, Keithanne and Stewart, Craig A}, doi = {10.1145/2792745.2792748}, booktitle = {Proceedings of the 2015 XSEDE Conference on Scientific Advancements Enabled by Enhanced Cyberinfrastructure - XSEDE '15} }
@article{ title = {Describing and predicting developmental profiles of externalizing problems from childhood to adulthood}, type = {article}, year = {2015}, id = {3ee7b520-852f-3207-afe3-e11d430d91b6}, created = {2018-02-27T18:07:45.872Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.872Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {pbdlp15}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Petersen, I T and Bates, J E and Dodge, K A and Lansford, J E and Pettit, G S}, doi = {10.1017/S0954579414000789.}, journal = {DEVELOPMENT AND PSYCHOPATHOLOGY} }
@inproceedings{ title = {XCBC and XNIT - Tools for cluster implementation and management in research and training}, type = {inproceedings}, year = {2015}, volume = {2015-Octob}, id = {54429c7e-5f8c-3cb2-8a3b-f03e13b466d0}, created = {2018-02-27T18:07:46.335Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.335Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, abstract = {© 2015 IEEE. The Extreme Science and Engineering Discovery Environment has created a suite of software collectively known as the XSEDE-compatible basic cluster (XCBC). It has been distributed as a Rocks Roll for some time. The same scientific and supporting packages are available as individual RPM packages as the XSEDE National Integration Toolkit (XNIT), so they can be downloaded and installed in portions as appropriate on existing clusters. In this paper, we examine using the LittleFe design created by the Earlham College Cluster Computing Group as a teaching tool to show the deployment of XCBC from Rocks. In addition, the demonstration of the commercial Limulus HPC200 Deskside Cluster solution is shown as a viable, off-the-shelf cluster that can be adapted to become an XSEDE-like cluster through the use of the XNIT repository. The goal is to demonstrate building practical XCBCs while showing that an XCBC need not be an expensive resource to be useful.}, bibtype = {inproceedings}, author = {Fischer, J. and Knepper, R. and Coulter, E. and Peck, C. and Stewart, C.A.}, doi = {10.1109/CLUSTER.2015.143}, booktitle = {Proceedings - IEEE International Conference on Cluster Computing, ICCC} }
@article{ title = {Background mutational features of the radiation-resistant bacterium deinococcus radiodurans}, type = {article}, year = {2015}, keywords = {Article; bacterial strain; Deinococcus radioduran,Bacterial Proteins; Deinococcus; DNA Damage; DNA,Bacterial; Genes,Bacterial; Genetic Drift; Mutagenesis,Insertional; Mutation Rate; Plasmids; Point Mutat,adenine; cytosine; DNA; uracil DNA glycosidase; ba}, pages = {2383-2392}, volume = {32}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84943608703&doi=10.1093%2Fmolbev%2Fmsv119&partnerID=40&md5=43f71482fe288975f38f8e279f12baa6}, publisher = {Oxford University Press}, id = {b0d886b2-116a-38f1-a455-8c3020d43725}, created = {2018-02-27T18:07:46.506Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.506Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Long20152383}, source_type = {article}, notes = {cited By 14}, private_publication = {false}, abstract = {Deinococcus bacteria are extremely resistant to radiation, oxidation, and desiccation. Resilience to these factors has been suggested to be due to enhanced damage prevention and repair mechanisms, as well as highly efficient antioxidant protection systems. Here, using mutation-accumulation experiments, we find that the GC-rich Deinococcus radiodurans has an overall background genomicmutation rate similar to that of E. coli, but differs inmutation spectrum, with the A/T to G/C mutation rate (based on a total count of 88 A:T→G:C transitions and 82 A:T→C:G transversions) per site per generation higher than that in the other direction (based on a total count of 157 G:C→A:T transitions and 33 G:C→T:A transversions).We propose that this unique spectrumis shaped mainly by the abundant uracil DNA glycosylases reducing G:C→A:T transitions, adenine methylation elevating A:T→C:G transversions, and absence of cytosine methylation decreasing G:C→A:T transitions. As opposed to the greater than 100 elevation of the mutation rate in MMR (DNA Mismatch Repair deficient) strains of most other organisms,MMR D. radiodurans only exhibits a 4-fold elevation, raising the possibility that other DNA repair mechanisms compensate for a relatively low-efficiency DNA MMR pathway. As D. radiodurans has plentiful insertion sequence (IS) elements in the genome and the activities of IS elements are rarely directly explored, we also estimated the insertion (transposition) rate of the IS elements to be 2.50×103 per genome per generation in the wild-type strain; knocking out MMR did not elevate the IS element insertion rate in this organism. © 2015 The Author.}, bibtype = {article}, author = {Long, H and Kucukyildirim, S and Sung, W and Williams, E and Lee, H and Ackerman, M S and Doak, T G and Tang, H and Lynch, M}, doi = {10.1093/molbev/msv119}, journal = {Molecular Biology and Evolution}, number = {9} }
@article{ title = {Strand-specific community RNA-seq reveals prevalent and dynamic antisense transcription in human gut microbiota}, type = {article}, year = {2015}, keywords = {Article,antisense transcription,bacterial geneti}, volume = {6}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84946746270&doi=10.3389%2Ffmicb.2015.00896&partnerID=40&md5=9bf77043bc0a78dec2df20aed340acc6,https://www.frontiersin.org/articles/10.3389/fmicb.2015.00896/full}, publisher = {Frontiers Research Foundation}, id = {a5cfe378-07dd-3747-b34f-9bbacb84757f}, created = {2018-02-27T18:07:46.542Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T18:05:51.453Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Bao2015}, source_type = {article}, notes = {cited By 4}, private_publication = {false}, abstract = {Metagenomics and other meta-omics approaches (including metatranscriptomics) provide insights into the composition and function of microbial communities living in different environments or animal hosts. Metatranscriptomics research provides an unprecedented opportunity to examine gene regulation for many microbial species simultaneously, and more importantly, for the majority that are unculturable microbial species, in their natural environments (or hosts). Current analyses of metatranscriptomic datasets focus on the detection of gene expression levels and the study of the relationship between changes of gene expression and changes of environment. As a demonstration of utilizing metatranscriptomics beyond these common analyses, we developed a computational and statistical procedure to analyze the antisense transcripts in strand-specific metatranscriptomic datasets. Antisense RNAs encoded on the DNA strand opposite a gene's CDS have the potential to form extensive base-pairing interactions with the corresponding sense RNA, and can have important regulatory functions. Most studies of antisense RNAs in bacteria are rather recent, are mostly based on transcriptome analysis, and have been applied mainly to single bacterial species. Application of our approaches to human gut-associated metatranscriptomic datasets allowed us to survey antisense transcription for a large number of bacterial species associated with human beings. The ratio of protein coding genes with antisense transcription ranges from 0 to 35.8% (median = 10.0%) among 47 species. Our results show that antisense transcription is dynamic, varying between human individuals. Functional enrichment analysis revealed a preference of certain gene functions for antisense transcription, and transposase genes are among the most prominent ones (but we also observed antisense transcription in bacterial house-keeping genes). © 2015 Bao, Wang, Doak and Ye.}, bibtype = {article}, author = {Bao, G and Wang, M and Doak, T G and Ye, Y}, doi = {10.3389/fmicb.2015.00896}, journal = {Frontiers in Microbiology}, number = {SEP} }
@article{ title = {The spontaneous mutation rate in the fission yeast Schizosaccharomyces pombe}, type = {article}, year = {2015}, keywords = {5 methylcytosine; cytosine; DNA methyltransferase;,Amino Acid Sequence; DNA; Gene Expression Regulat,Fungal; Haploidy; INDEL Mutation; Mutation; Mutat,allele; Article; budding; cell adhesion; cell div}, pages = {737-744}, volume = {201}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84941668361&doi=10.1534%2Fgenetics.115.177329&partnerID=40&md5=046524c96924e58d08868a2ec9930ce8}, publisher = {Genetics}, id = {0f37b22f-68a5-3fab-a3ee-baff49d84d4d}, created = {2018-02-27T18:07:47.378Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.378Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Farlow2015737}, source_type = {article}, notes = {cited By 18}, private_publication = {false}, abstract = {The rate at which new mutations arise in the genome is a key factor in the evolution and adaptation of species. Here we describe the rate and spectrum of spontaneous mutations for the fission yeast Schizosaccharomyces pombe, a key model organism with many similarities to higher eukaryotes. We undertook an 1700-generation mutation accumulation (MA) experiment with a haploid S. pombe, generating 422 single-base substitutions and 119 insertion-deletion mutations (indels) across the 96 replicates. This equates to a base-substitution mutation rate of 2.00 3 10210 mutations per site per generation, similar to that reported for the distantly related budding yeast Saccharomyces cerevisiae. However, these two yeast species differ dramatically in their spectrum of base substitutions, the types of indels (S. pombe is more prone to insertions), and the pattern of selection required to counteract a strong AT-biased mutation rate. Overall, our results indicate that GC-biased gene conversion does not play a major role in shaping the nucleotide composition of the S. pombe genome and suggest that the mechanisms of DNA maintenance may have diverged significantly between fission and budding yeasts. Unexpectedly, CpG sites appear to be excessively liable to mutation in both species despite the likely absence of DNA methylation. © 2015 by the Genetics Society of America.}, bibtype = {article}, author = {Farlow, A and Long, H and Arnoux, S and Sung, W and Doak, T G and Nordborg, M and Lynch, M}, doi = {10.1534/genetics.115.177329}, journal = {Genetics}, number = {2} }
@inproceedings{ title = {NCBI-BLAST programs optimization on XSEDE resources for sustainable aquaculture}, type = {inproceedings}, year = {2015}, id = {cf607a3d-5fdc-3f14-891e-23863e4d1a58}, created = {2018-02-27T18:07:48.370Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-29T19:56:48.833Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {sgphbs15}, source_type = {inproceedings}, private_publication = {false}, abstract = {The development of genomic resources of non-model organisms is now becoming commonplace as the cost of sequencing continues to decrease. The Genome Informatics Facility in collaboration with the Southwest Fisheries Science Center (SWFSC), NOAA is creating these resources for sustainable aquaculture in Seriola lalandi. Gene prediction and annotation are common steps in the pipeline to generate genomic resources, which are computationally intense and time consuming. In our steps to create genomic resources for Seriola lalandi, we found BLAST to be one of our most rate limiting steps. Therefore, we took advantage of our XSEDE Extended Collaborative Support Services (ECSS) to reduce the amount of time required to process our transcriptome data by 300 percent. In this paper, we describe an optimized method for the BLAST tool on the Stampede cluster, which works with any existing datasets or database, without any modification. At modest core counts, our results are similar to the MPI-enabled BLAST algorithm (mpiBLAST), but also allow the much needed and improved flexibility of output formats that the latest versions of BLAST provide. Reducing this time-consuming bottleneck in BLAST will be broadly applicable to the annotation of large sequencing datasets for any organism.}, bibtype = {inproceedings}, author = {Seetharam, Arun and Gomez, Antonio and Purcell, Catherine M and Hyde, John R and Blood, Philip D and Severin, Andrew J}, doi = {http://dx.doi.org/10.1145/2792745.2792749}, booktitle = {Proceedings of the 2015 XSEDE Conference: Scientific Advancements Enabled by Enhanced Cyberinfrastructure (XSEDE '15)} }
@article{ title = {Mutation rate, spectrum, topology and context-dependency in the DNA mismatch repair (MMR) deficient Pseudomonas fluorescens Migula ATCC948}, type = {article}, year = {2015}, pages = {262-271}, volume = {23}, websites = {http://gbe.oxfordjournals.org/content/7/1/262.full.pdf+html?sid=e5570fd3-bf72-4c6c-a744-975adcdccdda}, id = {0875d946-c159-30c2-8ebd-50f683d1fba3}, created = {2018-02-27T18:07:48.479Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.479Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {lsmadl15}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Long, H and Sung, W and Miller, S F and Ackerman, M S and Doak, T G and Lynch, M}, journal = {GENOME BIOLOGY AND EVOLUTION} }
@article{ title = {Saccharide breakdown and fermentation by the honey bee gut microbiome}, type = {article}, year = {2015}, pages = {796-815}, volume = {17}, month = {3}, publisher = {Blackwell Publishing Ltd}, day = {1}, id = {fa3ff76a-2563-398e-b26e-d8904bc74325}, created = {2019-08-27T18:07:08.863Z}, accessed = {2019-08-27}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T18:07:08.938Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, abstract = {The honey bee, the world's most important agricultural pollinator, relies exclusively on plant-derived foods for nutrition. Nectar and pollen collected by honey bees are processed and matured within the nest through the activities of honey bee-derived microbes and enzymes. In order to better understand the contribution of the microbial community to food processing in the honey bee, we generated a metatranscriptome of the honey bee gut microbiome. The function of the microbial community in the honey bee, as revealed by metatranscriptome sequencing, resembles that of other animal guts and food-processing environments. We identified three major bacterial classes that are active in the gut (γ-Proteobacteria, Bacilli and Actinobacteria), all of which are predicted to participate in the breakdown of complex macromolecules (e.g. polysaccharides and polypeptides), the fermentation of component parts of these macromolecules, and the generation of various fermentation products, such as short-chain fatty acids and alcohol. The ability of the microbial community to metabolize these carbon-rich food sources was confirmed through the use of community-level physiological profiling. Collectively, these findings suggest that the gut microflora of the honey bee harbours bacterial members with unique roles, which ultimately can contribute to the processing of plant-derived food for colonies.}, bibtype = {article}, author = {Lee, Fredrick J. and Rusch, Douglas B. and Stewart, Frank J. and Mattila, Heather R. and Newton, Irene L.G.}, doi = {10.1111/1462-2920.12526}, journal = {Environmental Microbiology}, number = {3} }
@article{ title = {Physiological effects of heat stress on Hawaiian picture-wing Drosophila: Genome-wide expression patterns and stress-related traits}, type = {article}, year = {2015}, keywords = {Gene expression,Hawaiian Drosophila,Local adaptation,Microarray,Sperm mobility,Temperature tolerance}, volume = {3}, publisher = {Oxford University Press}, id = {af6bebd4-6737-3aa5-9dc3-087f06a23177}, created = {2019-08-29T19:56:37.368Z}, accessed = {2019-08-29}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-29T19:56:37.470Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, abstract = {Two Hawaiian picture-wing Drosophila differ in their temperature tolerances with the ecologically rare species, D. silvestris, showing reduced survival, reduced sperm mobility and greater gene expression changes at high temperatures compared to the common D. sproati. Thus the rare species may have reduced capacity to adapt to future climate changes.}, bibtype = {article}, author = {Uy, Karen L. and LeDuc, R. and Ganote, C. and Price, Donald K.}, doi = {10.1093/conphys/cou062}, journal = {Conservation Physiology}, number = {1} }
@article{ title = {Assessment and improvement of Indian-origin rhesus macaque and Mauritian-origin cynomolgus macaque genome annotations using deep transcriptome sequencing data}, type = {article}, year = {2014}, id = {c0f3f90c-3b42-3ec0-a5f7-49fd58eda6fd}, created = {2018-02-27T18:07:45.875Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.875Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {ppxgjrsmpk14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Peng, Xinxia and Pipes, Lenore and Xiong, Hao and Green, Richard R and Jones, Daniel C and Ruzzo, Walter L and Schroth, Gary P and Mason, Christopher E and Palermo, Robert E and Katze, Michael G}, doi = {10.1111/jmp.12125}, journal = {JOURNAL OF MEDICAL PRIMATOLOGY} }
@article{ title = {The architecture of a scrambled genome reveals massive levels of genomic rearrangement during development}, type = {article}, year = {2014}, keywords = {Cell Nucleus; Chromosomes; Gene Rearrangement; Ge,Protozoan; Molecular Sequence Data; Oxytricha,article; chromosome; development; DNA sequence; DN,development and aging; metabolism; molecular gene}, pages = {1187-1198}, volume = {158}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84907350409&doi=10.1016%2Fj.cell.2014.07.034&partnerID=40&md5=686c2e1d011edce98709b7410dc154f4}, publisher = {Cell Press}, id = {f9c8a513-b440-3686-b393-0532b50c2b31}, created = {2018-02-27T18:07:45.966Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:45.966Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Chen20141187}, source_type = {article}, notes = {cited By 34}, private_publication = {false}, abstract = {Programmed DNA rearrangements in the single-celled eukaryote Oxytricha trifallax completely rewire its germline into a somatic nucleus during development. This elaborate, RNA-mediated pathway eliminates noncoding DNA sequences that interrupt gene loci and reorganizes the remaining fragments by inversions and permutations to produce functional genes. Here, we report the Oxytricha germline genome and compare it to the somatic genome to present a global view of its massive scale of genome rearrangements. The remarkably encrypted genome architecture contains >3,500 scrambled genes, as well as >800 predicted germline-limited genes expressed, and some posttranslationally modified, during genome rearrangements. Gene segments for different somatic loci often interweave with each other. Single gene segments can contribute to multiple, distinct somatic loci. Terminal precursor segments from neighboring somatic loci map extremely close to each other, often overlapping. This genome assembly provides a draft of a scrambled genome and a powerful model for studies of genome rearrangement. © 2014 Elsevier Inc.}, bibtype = {article}, author = {Chen, X and Bracht, J R and Goldman, A D and Dolzhenko, E and Clay, D M and Swart, E C and Perlman, D H and Doak, T G and Stuart, A and Amemiya, C T and Sebra, R P and Landweber, L F}, doi = {10.1016/j.cell.2014.07.034}, journal = {Cell}, number = {5} }
@article{ title = {Expanding the catalog of cas genes with metagenomes}, type = {article}, year = {2014}, keywords = {Bacterial; Genome,Bacterial; Humans; Metagenome; Metagenomics; Micr,CRISPR-Associated Proteins; CRISPR-Cas Systems; F,adaptive immunity; article; bacterial gene; bacte,antitoxin; bacterial RNA; cellular apoptosis susce}, pages = {2448-2459}, volume = {42}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84895793652&doi=10.1093%2Fnar%2Fgkt1262&partnerID=40&md5=f0505ec2d9e968fd5f75be28c5a0012c}, id = {1d769630-b9d3-30e0-87c6-ab4bb1eadede}, created = {2018-02-27T18:07:46.036Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.036Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Zhang20142448}, source_type = {article}, notes = {cited By 7}, private_publication = {false}, abstract = {The CRISPR (clusters of regularly interspaced short palindromic repeats)-Cas adaptive immune system is an important defense system in bacteria, providing targeted defense against invasions of foreign nucleic acids. CRISPR-Cas systems consist of CRISPR loci and cas (CRISPR-associated) genes: sequence segments of invaders are incorporated into host genomes at CRISPR loci to generate specificity, while adjacent cas genes encode proteins that mediate the defense process. We pursued an integrated approach to identifying putative cas genes from genomes and metagenomes, combining similarity searches with genomic neighborhood analysis. Application of our approach to bacterial genomes and human microbiome datasets allowed us to significantly expand the collection of cas genes: the sequence space of the Cas9 family, the key player in the recently engineered RNA-guided platforms for genome editing in eukaryotes, is expanded by at least two-fold with metagenomic datasets. We found genes in cas loci encoding other functions, for example, toxins and antitoxins, confirming the recently discovered potential of coupling between adaptive immunity and the dormancy/suicide systems. We further identified 24 novel Cas families; one novel family contains 20 proteins, all identified from the human microbiome datasets, illustrating the importance of metagenomics projects in expanding the diversity of cas genes. © 2013 The Author(s). Published by Oxford University Press.}, bibtype = {article}, author = {Zhang, Q and Doak, T G and Ye, Y}, doi = {10.1093/nar/gkt1262}, journal = {Nucleic Acids Research}, number = {4} }
@article{ title = {The Encrypted Germline Genome of the Ciliate Oxytricha: A Paragon of Genome Rearrangement}, type = {article}, year = {2014}, id = {951bbaec-8b12-37af-9517-d98dc02f44f8}, created = {2018-02-27T18:07:46.093Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.093Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {cbgdscpdsal14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Chen, X., Bracht, J.R., Goldman, A.D., Dolzhenko, E., Swart, E.C., Clay, D.M., Perlman, D.H., Doak, T.G., Stuart, A., Amemiya, C.T, Landweber, L.F and Chen, X and Bracht, J R and Goldman, A D and Dolzhenko, E and Swart, E C and Clay, D M and Perlman, D H and Doak, T G and Stuart, A and Amemiya, C T and Landweber, L F}, journal = {MIC} }
@article{ title = {Mutation rate, spectrum, topology, and context-dependency in the DNA mismatch repair-deficient Pseudomonas fluorescens ATCC948}, type = {article}, year = {2014}, keywords = {Bacteria (microorganisms); Pseudomonas; Pseudomona,Bacterial; Genetic Variation; Host-Pathogen Inter,DNA Mismatch Repair; DNA Replication; Drug Resist,antibiotic resistance; DNA replication; genetic v}, pages = {262-271}, volume = {7}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84928236984&doi=10.1093%2Fgbe%2Fevu284&partnerID=40&md5=2bcdb70cefe6468d2c3bd80ecda61654}, publisher = {Oxford University Press}, id = {95813379-d9f2-3544-abb7-85359330afda}, created = {2018-02-27T18:07:46.433Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.433Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Long2014262}, source_type = {article}, notes = {cited By 14}, private_publication = {false}, abstract = {High levels of genetic diversity exist among natural isolates of the bacterium Pseudomonas fluorescens, and are especially elevated around the replication terminus of the genome, where strain-specific genes are found. In an effort to understand the role of genetic variation in the evolution of Pseudomonas, we analyzed 31,106 base substitutions from 45 mutation accumulation lines of P. fluorescens ATCC948, naturally deficient for mismatch repair, yielding a base-substitution mutation rate of 2.34×10-8 per site per generation (SE: 0.01×10-8) and a small-insertion-deletion mutation rate of 1.65×10-9 per site per generation (SE: 0.03×10-9). We find that the spectrum of mutations in prophage regions, which often contain virulence factors and antibiotic resistance, is highly similar to that in the intergenic regions of the host genome. Our results show that themutation rate varies around the chromosome, with the lowest mutation rate foundnear the originof replication. Consistent with observations fromother studies, wefind that site-specificmutation rates are heavily influenced by the immediately flanking nucleotides, indicating thatmutations are context dependent. © 2014 The Author(s).}, bibtype = {article}, author = {Long, H and Sung, W and Miller, S F and Ackerman, M S and Doak, T G and Lynch, M}, doi = {10.1093/gbe/evu284}, journal = {Genome Biology and Evolution}, number = {1} }
@article{ title = {Unique Features of the Loblolly Pine (Pinus taeda L.) Megagenome Revealed Through Sequence Annotation}, type = {article}, year = {2014}, pages = {891-909}, volume = {196}, id = {5cf5d614-7759-34cb-ab45-3900bc395117}, created = {2018-02-27T18:07:46.466Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.466Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {wlswlvdlzmh14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Wegrzyn, Jill L and Liechty, John D and Stevens, Kristian A and Wu, Le-Shin and Loopstra, Carol A and Vasquez-Gross, Hans A and Dougherty, William M and Lin, Brian Y and Zieve, Jacob J and Mart\'\inez-Garc\'\ia, Pedro J and Holt, Carson and Y, undefined}, doi = {10.1534/genetics.113.159996}, journal = {Genetics} }
@article{ title = {The mitochondrial genome of a Solanaceae cybrid plant is highly chimeric and retains a single form of most genes}, type = {article}, year = {2014}, id = {7443c5bb-d5ce-316c-a375-2b1d1c96babe}, created = {2018-02-27T18:07:46.781Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.781Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {szp14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Sanchez-Puerta, M V and Zubko, M and Palmer, J D}, journal = {GENOME RESEARCH} }
@article{ title = {Decoding the massive genome of loblolly pine using haploid DNA and novel assembly strategies}, type = {article}, year = {2014}, volume = {15}, id = {f2b1b972-dd74-3165-b820-068a07ae11e4}, created = {2018-02-27T18:07:46.853Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.853Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {nwszpcckmlgglz14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Neale, David and Wegrzyn, Jill and Stevens, Kristian and Zimin, Aleksey and Puiu, Daniela and Crepeau, Marc and Cardeno, Charis and Koriabine, Maxim and Morris, Ann H and Liechty, John and Garcia, Pedro M and Gross, Hans V and Lin, Brian and Zieve, Jac}, doi = {10.1186/gb-2014-15-3-r59}, journal = {GENOME BIOLOGY} }
@article{ title = {The C-score: a bayesian framework to sharply improve proteoform scoring in high-throughput top down proteomics.}, type = {article}, year = {2014}, pages = {3231-3324}, volume = {13}, id = {e2fef33e-ac33-3940-9a04-d91bd5df794c}, created = {2018-02-27T18:07:46.854Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.854Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {lfegtk14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {LeDuc, Richard D and Fellers, Ryan T and Early, Bryan P and Greer, Joseph B and Thomas, Paul M and Kelleher, Neil L}, doi = {1535-3907}, journal = {JOURNAL OF PROTEOME RESEARCH} }
@techreport{ title = {National Center for Genome Analysis Program Year 2 Report - September 15, 2012 - September 14, 2013}, type = {techreport}, year = {2014}, websites = {http://hdl.handle.net/2022/17387}, institution = {NATIONAL CENTER FOR GENOME ANALYSIS}, id = {608c1d18-78c9-3fdb-bad2-a900339c0655}, created = {2018-02-27T18:07:47.004Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-10T21:08:10.363Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {bls14}, source_type = {techreport}, private_publication = {false}, bibtype = {techreport}, author = {Barnett, William K and LeDuc, R. D. and Stewart, Craig A.} }
@article{ title = {Insights into three whole-genome duplications gleaned from the Paramecium caudatum genome sequence}, type = {article}, year = {2014}, keywords = {Base Composition; Chromosome Mapping; Evolution,DNA; Sequence Analysis,Genetic; Paramecium caudatum; Phylogeny; Sequence,Molecular; Gene Duplication; Genome,Protozoan; Models,RNA,article; DNA base composition; duplicate gene; ev,cytosine; guanine}, pages = {1417-1428}, volume = {197}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84905641351&doi=10.1534%2Fgenetics.114.163287&partnerID=40&md5=37f37936cc89404f95d88b37cc5c20ed}, publisher = {Genetics}, id = {42e5078c-279e-378a-991a-c34b7983fbfc}, created = {2018-02-27T18:07:47.020Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.020Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {McGrath20141417}, source_type = {article}, notes = {cited By 16}, private_publication = {false}, abstract = {Paramecium has long been a model eukaryote. The sequence of the Paramecium tetraurelia genome reveals a history of three successive whole-genome duplications (WGDs), and the sequences of P. biaurelia and P. sexaurelia suggest that these WGDs are shared by all members of the aurelia species complex. Here, we present the genome sequence of P. caudatum, a species closely related to the P. aurelia species group. P. caudatum shares only the most ancient of the three WGDs with the aurelia complex. We found that P. caudatum maintains twice as many paralogs from this early event as the P. aurelia species, suggesting that post-WGD gene retention is influenced by subsequent WGDs and supporting the importance of selection for dosage in gene retention. The availability of P. caudatum as an outgroup allows an expanded analysis of the aurelia intermediate and recent WGD events. Both the Guanine+Cytosine (GC) content and the expression level of preduplication genes are significant predictors of duplicate retention. We find widespread asymmetrical evolution among aurelia paralogs, which is likely caused by gradual pseudogenization rather than by neofunctionalization. Finally, cases of divergent resolution of intermediate WGD duplicates between aurelia species implicate this process acts as an ongoing reinforcement mechanism of reproductive isolation long after a WGD event. © 2014 by the Genetics Society of America.}, bibtype = {article}, author = {McGrath, C L and Gout, J.-F. and Doak, T G and Yanagi, A and Lynch, M}, doi = {10.1534/genetics.114.163287}, journal = {Genetics}, number = {4} }
@article{ title = {De Novo Assembly of a Transcriptome for Calanus finmarchicus (Crustacea, Copepoda) -- The Dominant Zooplankter of the North Atlantic Ocean}, type = {article}, year = {2014}, volume = {9}, id = {e172b8d5-fb93-3366-98bf-8586081d799a}, created = {2018-02-27T18:07:47.396Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.396Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {lrhwchc14}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Lenz, Petra H and Roncalli, Vittoria and Hassett, R Patrick and Wu, Le-Shin and Cieslak, Matthew C and Hartline, Daniel K and Christie, Andrew E}, doi = {10.1371/journal.pone.0088589}, journal = {PLOS ONE} }
@article{ title = {Differential retention and divergent resolution of duplicate genes following whole-genome duplication}, type = {article}, year = {2014}, keywords = {Evolution,Molecular; Gene Conversion; Gene Duplication; Gen,Protozoan; Paramecium aurelia; Phylogeny; Sequenc,allopolyploidy; Article; autopolyploidy; chromoso,ribosome protein; transcription factor}, pages = {1665-1675}, volume = {24}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84907528769&doi=10.1101%2Fgr.173740.114&partnerID=40&md5=168c2d55a6a6ce5e4de46a201456f54b}, publisher = {Cold Spring Harbor Laboratory Press}, id = {82214d85-430d-3b1d-875c-daebb43e8158}, created = {2018-02-27T18:07:47.851Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.851Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {McGrath20141665}, source_type = {article}, notes = {cited By 25}, private_publication = {false}, abstract = {The Paramecium aurelia complex is a group of 15 species that share at least three past whole-genome duplications (WGDs). The macronuclear genome sequences of P. biaurelia and P. sexaurelia are presented and compared to the published sequence of P. tetraurelia. Levels of duplicate-gene retention from the recent WGD differ by >10% across species, with P. sexaurelia losing significantly more genes than P. biaurelia or P. tetraurelia. In addition, historically high rates of gene conversion have homogenized WGD paralogs, probably extending the paralogs' lifetimes. The probability of duplicate retention is positively correlated with GC content and expression level; ribosomal proteins, transcription factors, and intracellular signaling proteins are overrepresented among maintained duplicates. Finally, multiple sources of evidence indicate that P. sexaurelia diverged from the two other lineages immediately following, or perhaps concurrent with, the recentWGD, with approximately half of gene losses between P. tetraurelia and P. sexaurelia representing divergent gene resolutions (i.e., silencing of alternative paralogs), as expected for random duplicate loss between these species. Additionally, though P. biaurelia and P. tetraurelia diverged from each other much later, there are still more than 100 cases of divergent resolution between these two species. Taken together, these results indicate that divergent resolution of duplicate genes between lineages acts to reinforce reproductive isolation between species in the Paramecium aurelia complex. © 2014 Ivanauskiene et al.}, bibtype = {article}, author = {McGrath, C L and Gout, J.-F. and Johri, P and Doak, T G and Lynch, M}, doi = {10.1101/gr.173740.114}, journal = {Genome Research}, number = {10} }
@inproceedings{ title = {Galaxy based BLAST submission to distributed national high throughput computing resources}, type = {inproceedings}, year = {2014}, keywords = {Bioinformatics; Cost effectiveness; Throughput,Cost-effective solutions; Cyber infrastructures;,Galaxies}, volume = {23-28-Marc}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84976271088&partnerID=40&md5=ea9c8364e53276d64fa78ae4c984171f}, publisher = {Proceedings of Science (PoS)}, id = {87a86671-fd69-3dd1-b1fe-921cc7ad723f}, created = {2018-02-27T18:07:47.915Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.915Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Hayashi2014}, source_type = {conference}, notes = {cited By 1; Conference of International Symposium on Grids and Clouds, ISGC 2014 ; Conference Date: 23 March 2014 Through 28 March 2014; Conference Code:121995}, private_publication = {false}, abstract = {To assist the bioinformatic community in leveraging the national cyberinfrastructure, the National Center for Genomic Analysis Support (NCGAS) along with Indiana University's High Throughput Computing (HTC) group have engineered a method to use the Galaxy to submit BLAST jobs to the Open Science Grid (OSG). OSG is a collaboration of resource providers that utilize opportunistic cycles at more than 100 universities and research centers in the US. BLAST jobs make a significant portion of the research conducted on NCGAS resources, moving jobs that are conducive to an HTC environment to the national cyberinfrastructure would alleviate load on resources at NCGAS and provide a cost effective solution for getting more cycles to reduce the unmet needs of bioinformatic researchers. To this point researchers have tackled this issue by purchasing additional resources or enlisting collaborators doing the same type of research while HTC experts have focused on expanding the number of resources available to historically HTC friendly science workflows. In this paper, we bring together expertise from both areas to address how a bioinformatics researcher using their normal interface, Galaxy, can seamlessly access the OSG which routinely supplies researchers with millions of compute hours daily. Efficient use of these results will supply additional compute time to researcher and help provide a yet unmet need for BLAST computing cycles. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-ShareAlike Licence.}, bibtype = {inproceedings}, author = {Hayashi, S and Gesing, S and Quick, R and Teige, S and Ganote, C and Wu, L.-S. and Prout, E}, booktitle = {Proceedings of Science} }
@book{ title = {Diversity and dynamics of the Drosophila transcriptome}, type = {book}, year = {2014}, series = {NATURE}, id = {f8e9d122-9016-3ff9-b6a3-0988d851647e}, created = {2018-02-27T18:07:48.497Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.497Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {bbemsdbwpswyzc14}, source_type = {book}, private_publication = {false}, bibtype = {book}, author = {Brown, James B and Boley, Nathan and Eisman, Robert and May, Gemma E and Stoiber, Marcus H and Duff, Michael O and Booth, Ben W and Wen, Jiayu and Park, Soo and Suzuki, Ana M and Wan, Kenneth H and Yu, Charles and Zhang, Dayu and Carlson, Joseph W}, doi = {10.1038/nature12962} }
@book{ title = {Development of Single Nucleotide Polymorphism (SNP) Markers from the Mango (Mangifera indica ) Transcriptome for Mapping and Estimation of Genetic Diversity}, type = {book}, year = {2014}, websites = {https://pag.confex.com/pag/xxii/webprogram/Paper11012.html}, publisher = {PLANT AND ANIMAL GENOME XXII CONFERENCE}, id = {eb1a673b-87f2-3a9c-9e52-1aa5ea02c78f}, created = {2018-02-27T18:07:48.631Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.631Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {kdiwm14}, source_type = {book}, private_publication = {false}, bibtype = {book}, author = {Kuhn, D N and Dillon, N L and Innes, D J and Wu, L S and Mockaitis, K} }
@inproceedings{ title = {Large-scale Sequencing and Assembly of Cereal Genomes Using Blacklight}, type = {inproceedings}, year = {2014}, id = {d6d1c6ad-999f-3272-b64f-a75bed4a289c}, created = {2018-02-27T18:07:48.804Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.804Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {bms14}, source_type = {inproceedings}, private_publication = {false}, bibtype = {inproceedings}, author = {Blood, Philip D and Marcus, Shoshana and Schatz, Michael C}, booktitle = {XSEDE 14 CONFERENCE PROCEEDINGS} }
@article{ title = {Leveraging the national cyberinfrastructure for biomedical research}, type = {article}, year = {2014}, pages = {195-199}, volume = {21}, id = {04d60f97-2000-3b6a-8d29-08951293863c}, created = {2019-09-12T19:43:44.465Z}, accessed = {2019-09-12}, file_attached = {true}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-09-12T19:43:44.544Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, abstract = {In the USA, the national cyberinfrastructure refers to a system of research supercomputer and other IT facilities and the high speed networks that connect them. These resources have been heavily leveraged by scientists in disciplines such as high energy physics, astronomy, and climatology, but until recently they have been little used by biomedical researchers. We suggest that many of the 'Big Data' challenges facing the medical informatics community can be efficiently handled using nationalscale cyberinfrastructure. Resources such as the Extreme Science and Discovery Environment, the Open Science Grid, and Internet2 provide economical and proven infrastructures for Big Data challenges, but these resources can be difficult to approach. Specialized web portals, support centers, and virtual organizations can be constructed on these resources to meet defined computational challenges, specifically for genomics. We provide examples of how this has been done in basic biology as an illustration for the biomedical informatics community.}, bibtype = {article}, author = {LeDuc, Richard and Vaughn, Matthew and Fonner, John M. and Sullivan, Michael and Williams, James G. and Blood, Philip D. and Taylor, James and Barnett, William}, doi = {10.1136/amiajnl-2013-002059}, journal = {Journal of the American Medical Informatics Association}, number = {2} }
@techreport{ title = {National Center for Genome Analysis Program Year 3 Report - September 15, 2013 - September 14, 2014}, type = {techreport}, year = {2014}, keywords = {Blacklight,Dublin Core metadata,Mason,NCGAS,Rockhopper,Stampede,XSEDE,community genomics,consulting,genomics,metagenomics/transcriptomics,phylogenetics,transcriptome- and genome-level assembly}, volume = {3}, websites = {http://hdl.handle.net/2022/18513}, id = {30a12452-7e4b-3a66-a859-126c0d2b4e18}, created = {2020-09-10T21:08:09.090Z}, accessed = {2020-09-10}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-10T21:24:50.972Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {On September 15, 2011, Indiana University (IU) received three years of support to establish the National Center for Genome Analysis Support (NCGAS). This technical report describes the activities of the third 12 months of NCGAS.}, bibtype = {techreport}, author = {Barnett, William K and Doak, Thomas G and Stewart, Craig A} }
@techreport{ title = {National Center for Genome Analysis Program Year 1 Report - September 15, 2011 - September 14, 2012}, type = {techreport}, year = {2013}, keywords = {2013,pti}, websites = {http://hdl.handle.net/2022/15340}, id = {a5c29cfa-9695-3842-9127-4087e7185af4}, created = {2018-02-27T18:07:46.117Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-10T21:24:50.961Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {techreport}, private_publication = {false}, abstract = {On September 15, 2011, Indiana University (IU) received three years of support to establish the National Center for Genome Analysis Support (NCGAS). This technical report describes the activities of the first 12 months of NCGAS, during which time NCGAS brought online a large-RAM computational cluster, recruited 25 NSF-funded genomics projects to use the resource, responded to 502 requests for support, and processed 28,523 computational jobs representing a total of 136.83 core years of computing. NCGAS also laid the framework for creating a truly national-scale center supporting genomics research. By coordinating effort between multiple supercomputing centers, NCGAS is creating a service-oriented computational infrastructure – one that is designed to be approachable by end-users unaccustomed to using traditional supercomputing resources. The benefits of such inter-institutional coordination can be seen from events such as the NCGAS co-hosted Daphnia Genomics Jamboree. At this gathering, dozens of scientists from across the US and Europe spent five days accelerating the completion of the Daphnia manga genome. NCGAS-supported staff from both Texas Advanced Computing Center (TACC) and IU gave presentations early in the Jamboree before participants broke into small teams and used NCGAS clusters to perform their analyses. NCGAS also established a Galaxy web portal to allow researchers to use our large-RAM cluster with a familiar web interface, and we worked to increase the computational efficiency of the best-in-class Trinity application for RNA-sequence assembly.}, bibtype = {techreport}, author = {Barnett, William and Ganote, Carrie and Vaughn, Matthew and LeDuc, Richard D and Stewart, Craig A} }
@article{ title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis}, type = {article}, year = {2013}, keywords = {Base Sequence,Gene Expression Profiling,RNA,Sc,Software,Transcriptome,accuracy,article,clinical protocol,data analys,transcriptome}, pages = {1494-1512}, volume = {8}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84880266648&doi=10.1038%2Fnprot.2013.084&partnerID=40&md5=4b1c5151feb7cf22e24b0aa2a10a5bdb}, series = {NATURE PROTOCOLS}, id = {a05da594-f2cf-341d-a153-b3779675b001}, created = {2018-02-27T18:07:46.283Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.283Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {hpygbbcellmoopswwwdh14}, source_type = {article}, notes = {<b>From Duplicate 1 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; MacManes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A; others)<br/></b><br/><b>From Duplicate 2 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; Macmanes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A)<br/></b><br/>cited By 1139<br/><br/><b>From Duplicate 2 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B., Papanicolaou, A., Yassour, M., Grabherr, M., Blood, P., Bowden, J., Couger, M., Eccles, D., Li, B., Lieber, M., MacManes, M., Ott, M., Orvis, J., Pochet, N., Strozzi, F., Weeks, N., Westerman, R., William, T., Dewey, C., Henschel, R., et al; Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; Macmanes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A; others)<br/></b><br/><b>From Duplicate 2 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; Macmanes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A)<br/></b><br/>cited By 1139<br/><br/><b>From Duplicate 3 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; MacManes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A; others)<br/></b><br/><b>From Duplicate 2 (<i>De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis</i> - Haas, B J; Papanicolaou, A; Yassour, M; Grabherr, M; Blood, P D; Bowden, J; Couger, M B; Eccles, D; Li, B; Lieber, M; Macmanes, M D; Ott, M; Orvis, J; Pochet, N; Strozzi, F; Weeks, N; Westerman, R; William, T; Dewey, C N; Henschel, R; Leduc, R D; Friedman, N; Regev, A)<br/></b><br/>cited By 1139}, private_publication = {false}, abstract = {De novo assembly of RNA-seq data enables researchers to study transcriptomes without the need for a genome sequence; this approach can be usefully applied, for instance, in research on 'non-model organisms' of ecological and evolutionary importance, cancer samples or the microbiome. In this protocol we describe the use of the Trinity platform for de novo transcriptome assembly from RNA-seq data in non-model organisms. We also present Trinity-supported companion utilities for downstream applications, including RSEM for transcript abundance estimation, R/Bioconductor packages for identifying differentially expressed transcripts across samples and approaches to identify protein-coding genes. In the procedure, we provide a workflow for genome-independent transcriptome analysis leveraging the Trinity platform. The software, documentation and demonstrations are freely available from http://trinityrnaseq.sourceforge.net. The run time of this protocol is highly dependent on the size and complexity of data to be analyzed. The example data set analyzed in the procedure detailed herein can be processed in less than 5 h.}, bibtype = {article}, author = {Haas, B., Papanicolaou, A., Yassour, M., Grabherr, M., Blood, P., Bowden, J., Couger, M., Eccles, D., Li, B., Lieber, M., MacManes, M., Ott, M., Orvis, J., Pochet, N., Strozzi, F., Weeks, N., Westerman, R., William, T., Dewey, C., Henschel, R., et al and Haas, B J and Papanicolaou, A and Yassour, M and Grabherr, M and Blood, P D and Bowden, J and Couger, M B and Eccles, D and Li, B and Lieber, M and Macmanes, M D and Ott, M and Orvis, J and Pochet, N and Strozzi, F and Weeks, N and Westerman, R and William, T and Dewey, C N and Henschel, R and Leduc, R D and Friedman, N and Regev, A and others, undefined}, doi = {10.1038/nprot.2013.084}, journal = {Nature Protocols}, number = {8} }
@article{ title = {The non-human primate reference transcriptome resource (NHPRTR) for comparative functional genomics}, type = {article}, year = {2013}, pages = {D906-14}, volume = {41}, websites = {http://www.ncbi.nlm.nih.gov/pubmed/23203872}, id = {c8ebeeae-43c8-3daf-b6a3-3044a944e4b1}, created = {2018-02-27T18:07:46.314Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.314Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {plbppbkwttzcsmk13}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Pipes, Lenore and Li, Sheng and Bozinoski, Marjan and Palermo, Robert and Peng, Xinxia and Blood, Phillip and Kelly, Sara and Weiss, Jeffrey M and Thierry-Mieg, Jean and Thierry-Mieg, Danielle and Zumbo, P and Chen, R and Schroth, G P and Mason, C E and Katze, M G}, doi = {10.1093/nar/gks1268}, journal = {NUCLEIC ACIDS RES} }
@inproceedings{ title = {Statistical Consideration for Identification and Quantification in Top-Down Proteomics}, type = {inproceedings}, year = {2013}, city = { St. Pete Beach, FL}, id = {8e96624d-389c-3a7b-9925-ee2c3271343b}, created = {2018-02-27T18:07:46.378Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.378Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, bibtype = {inproceedings}, author = {LeDuc, Richard}, booktitle = {American Society for Mass Spectrometry, Sanibel Conference 2013} }
@techreport{ title = {Services and support for IU School of Medicine and Clinical Affairs Schools by the in FY 2013 - Extended Version}, type = {techreport}, year = {2013}, institution = {UITS/PTI Advanced Biomedical Information Technology Core and Research Technologies Division}, id = {f849d713-caeb-34ba-bc67-ce43c373a6f1}, created = {2018-02-27T18:07:46.565Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.565Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {sblsmmhbwq13}, source_type = {techreport}, private_publication = {false}, bibtype = {techreport}, author = {Stewart, C A and Barnett, W K and Link, M R and Shankar, G and Miller, T and Michael, S and Henschel, R and Boyles, M J and Wernert, E and Quick, R} }
@article{ title = {Peptidergic signaling in Calanus finmarchicus (Crustacea, Copepoda): In silico identification of putative peptide hormones and their receptors using a de novo assembled transcriptome}, type = {article}, year = {2013}, keywords = {2013,bioinformatics,illumina,neurohormone,neuropeptide,pti,sequencing,trinity}, pages = {117-135}, volume = {187}, websites = {http://dx.doi.org/10.1016/j.ygcen.2013.03.018}, chapter = {117}, id = {b8bb018e-4323-3aad-83a5-7efec0c8f27a}, created = {2018-02-27T18:07:46.580Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.580Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Christie, A.E., Roncalli, V., Wu, L.-S., Ganote, C.L., Doak, T.G., Lenz, P.H. and Christie, Andrew E and Roncalli, Vittoria and Wu, Le-Shin and Ganote, Carrie L and Doak, Thomas and Lenz, Petra H}, doi = {10.1016/j.ygcen.2013.03.018}, journal = {General and Comparative Endocrinology} }
@article{ title = {Spliced DNA sequences in the Paramecium germline: Their properties and evolutionary potential}, type = {article}, year = {2013}, keywords = {Base Sequence; Conserved Sequence; DNA,Molecular; Gene Rearrangement; Genes,Protozoan; Evolution,Protozoan; Paramecium; Sequence Inversion,chromosome inversion; gene; gene rearrangement; g,ciliated protozoa; developmentally regulated geno,protozoal DNA; protozoal DNA}, pages = {1200-1211}, volume = {5}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84891615810&doi=10.1093%2Fgbe%2Fevt087&partnerID=40&md5=71eff744a629efd134f8285bd39ae022}, id = {1d099dcc-0f72-3896-b785-db567cfa5096}, created = {2018-02-27T18:07:46.612Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.612Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Catania20131200}, source_type = {article}, notes = {cited By 6}, private_publication = {false}, abstract = {Despite playing a crucial role in germline-soma differentiation, the evolutionary significance of developmentally regulated genome rearrangements (DRGRs) has received scant attention. An example of DRGR is DNA splicing, a process that removes segments of DNA interrupting genic and/or intergenic sequences. Perhaps, best known for shaping immune-system genes in vertebrates, DNA splicing plays a central role in the life of ciliated protozoa, where thousands of germline DNA segments are eliminated after sexual reproduction to regenerate a functional somatic genome. Here, we identify and chronicle the properties of 5,286 sequences that putatively undergo DNA splicing (i.e., internal eliminated sequences [IESs]) across the genomes of three closely related species of the ciliate Paramecium (P. tetraurelia, P. biaurelia, and P. sexaurelia). The study reveals that these putative IESs share several physical characteristics. Although our results are consistent with excision events being largely conserved between species, episodes of differential IES retention/excision occur, may have a recent origin, and frequently involve coding regions. Our findings indicate interconversion between somatic-often coding-DNA sequences and noncoding IESs, and provide insights into the role of DNA splicing in creating potentially functional genetic innovation. © The Author(s) 2013.}, bibtype = {article}, author = {Catania, F and McGrath, C L and Doak, T G and Lynch, M}, doi = {10.1093/gbe/evt087}, journal = {Genome Biology and Evolution}, number = {6} }
@article{ title = {Effect of storage conditions on the stability and fermentability of enzymatic lignocellulosic hydrolysate}, type = {article}, year = {2013}, pages = {212-220}, volume = {147}, id = {67b1fc6b-3f97-3a2b-9d1d-d567d819017e}, created = {2018-02-27T18:07:46.713Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.713Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {jbasr13}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Jin, Mingjie and Bothfeld, William and Austin, Samantha and Sato, Trey K and Alex, La Reau and Li, Haibo and Foston, Marcus and Gunawan, Christa and LeDuc, Richard D and Quensen, John F and McGee, Mick and Uppugundla, Nirmal and Higbee, Alan and Ranatu, undefined}, doi = {1873-2976}, journal = {BIORESOURCE TECHNOLOGY} }
@article{ title = {The genome of the anaerobic fungus Orpinomyces sp. strain C1A reveals the unique evolutionary history of a remarkable plant biomass degrader}, type = {article}, year = {2013}, pages = {4620-4634}, volume = {79}, id = {a6f2c2e7-b5d6-3aba-b0f7-68ebda343161}, created = {2018-02-27T18:07:46.742Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:46.742Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {ycslpnawe13}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Youssef, N H and Couger, M B and Struchtemeyer, C G and Liggenstoffer, A S and Prade, R A and Najar, F Z and Atiyeh, H K and Wilkins, M R and Elshahed, M S}, doi = {10.1128/aem.00821-13}, journal = {APPL ENVIRON MICROBIOL} }
@article{ title = {Candidate Genes and Genetic Architecture of Symbiotic and Agronomic Traits Revealed by Whole-Genome, Sequence-Based Association Genetics in Medicago truncatula}, type = {article}, year = {2013}, volume = {8}, id = {1023b59b-74a7-306f-be7b-82e193e4132a}, created = {2018-02-27T18:07:47.203Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.203Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {spebymbfzdmey13}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Stanton-Geddes, John and Paape, Timothy and Epstein, Brendan and Briskine, Roman and Yoder, Jeremy and Mudge, Joann and Bharti, Arvind K and Farmer, Andrew D and Zhou, Peng and Denny, Roxanne and May, Gregory D and Erlandson, Stephanie and Yakub, Moham}, doi = {10.1371/journal.pone.0065688}, journal = {PLOS ONE} }
@article{ title = {A genomic survey of reb homologs suggests widespread occurrence of r-bodies in proteobacteria}, type = {article}, year = {2013}, keywords = {Bacteria (microorganisms); Caedibacter; Eukaryota,alga; article; Azorhizobium caulinodans; Azospiri,amino acid; bacterial protein; protein; r body; re}, pages = {505-516}, volume = {3}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84883242414&doi=10.1534%2Fg3.112.005231&partnerID=40&md5=1707fe585940d8f58a3fda48d636dea6}, publisher = {Genetics Society of America}, id = {60494587-f207-3f9c-b890-a157ebed0683}, created = {2018-02-27T18:07:47.204Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.204Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Raymann2013505}, source_type = {article}, notes = {cited By 6}, private_publication = {false}, abstract = {Bacteria and eukaryotes are involved in many types of interaction in nature, with important ecological consequences. However, the diversity, occurrence, and mechanisms of these interactions often are not fully known. The obligate bacterial endosymbionts of Paramecium provide their hosts with the ability to kill sensitive Paramecium strains through the production of R-bodies, highly insoluble coiled protein ribbons. R-bodies have been observed in a number of free-living bacteria, where their function is unknown. We have performed an exhaustive survey of genes coding for homologs of Reb proteins (R-body components) in complete bacterial genomes. We found that reb genes are much more widespread than previously thought, being present in representatives of major Proteobacterial subdivisions, including many free-living taxa, as well as taxa known to be involved in various kinds of interactions with eukaryotes, from mutualistic associations to pathogenicity. Reb proteins display very good conservation at the sequence level, suggesting that they may produce functional R-bodies. Phylogenomic analysis indicates that reb genes underwent a complex evolutionary history and allowed the identification of candidates potentially involved in R-body assembly, functioning, regulation, or toxicity. Our results strongly suggest that the ability to produce R-bodies is likely widespread in Proteobacteria. The potential involvement of R-bodies in as yet unexplored interactions with eukaryotes and the consequent ecological implications are discussed. © 2013 Raymann et al.}, bibtype = {article}, author = {Raymann, K and Bobay, L.-M. and Doak, T G and Lynch, M and Gribaldo, S}, doi = {10.1534/g3.112.005231}, journal = {G3: Genes, Genomes, Genetics}, number = {3} }
@article{ title = {CRISPR-Cas systems target a diverse collection of invasive mobile genetic elements in human microbiomes}, type = {article}, year = {2013}, keywords = {Bacteria; CRISPR-Cas Systems; Genes,Microbial; Humans; Interspersed Repetitive Sequen,bacteriophage; CRISPR Cas system; feces; human; jo}, volume = {14}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84876800205&doi=10.1186%2Fgb-2013-14-4-r40&partnerID=40&md5=df73488fce6b2a1762b9a99d32d39189}, publisher = {BioMed Central Ltd.}, id = {e55f9475-2c80-38ec-9965-b2ce1ee5d482}, created = {2018-02-27T18:07:47.413Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.413Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Zhang2013}, source_type = {article}, notes = {cited By 16}, private_publication = {false}, abstract = {Background: Bacteria and archaea develop immunity against invading genomes by incorporating pieces of the invaders' sequences, called spacers, into a clustered regularly interspaced short palindromic repeats (CRISPR) locus between repeats, forming arrays of repeat-spacer units. When spacers are expressed, they direct CRISPR-associated (Cas) proteins to silence complementary invading DNA. In order to characterize the invaders of human microbiomes, we use spacers from CRISPR arrays that we had previously assembled from shotgun metagenomic datasets, and identify contigs that contain these spacers' targets. Results: We discover 95,000 contigs that are putative invasive mobile genetic elements, some targeted by hundreds of CRISPR spacers. We find that oral sites in healthy human populations have a much greater variety of mobile genetic elements than stool samples. Mobile genetic elements carry genes encoding diverse functions: only 7% of the mobile genetic elements are similar to known phages or plasmids, although a much greater proportion contain phage- or plasmid-related genes. A small number of contigs share similarity with known integrative and conjugative elements, providing the first examples of CRISPR defenses against this class of element. We provide detailed analyses of a few large mobile genetic elements of various types, and a relative abundance analysis of mobile genetic elements and putative hosts, exploring the dynamic activities of mobile genetic elements in human microbiomes. A joint analysis of mobile genetic elements and CRISPRs shows that protospacer-adjacent motifs drive their interaction network; however, some CRISPR-Cas systems target mobile genetic elements lacking motifs. Conclusions: We identify a large collection of invasive mobile genetic elements in human microbiomes, an important resource for further study of the interaction between the CRISPR-Cas immune system and invaders. © 2013 BioMed Central Ltd.}, bibtype = {article}, author = {Zhang, Q and Rho, M and Tang, H and Doak, T G and Ye, Y}, doi = {10.1186/gb-2013-14-4-r40}, journal = {Genome Biology}, number = {4} }
@article{ title = {The genome sequence of the most widely cultivated cacao type and its use to identify candidate genes regulating traits: pod color as an example"}, type = {article}, year = {2013}, volume = {14}, id = {1d088847-b64d-3cd5-94c5-196cdfed66c7}, created = {2018-02-27T18:07:47.612Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.612Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {mms13}, source_type = {article}, private_publication = {false}, bibtype = {article}, author = {Motamayor, J. C., Mockaitis, K., Schmutz, J., et al. (Cacao Genome Group) and Motamayor, Juan C and Mockaitis, Keithanne and Schmutz, Jeremy and Haiminen, Nina and Donald, undefined and Cornejo, Omar and Findley, Seth and Zheng, Ping and Utro, Filippo and Royaert, Stefan and Saski, Christopher and Jenkins, Jerry and Podicheti, Ram and Zhao, Me and Motamayor, J. C., Mockaitis, K., Schmutz, J., et al. (Cacao Genome Group) and Motamayor, Juan C and Mockaitis, Keithanne and Schmutz, Jeremy and Haiminen, Nina and Donald, undefined and Cornejo, Omar and Findley, Seth and Zheng, Ping and Utro, Filippo and Royaert, Stefan and Saski, Christopher and Jenkins, Jerry and Podicheti, Ram and Zhao, Me and others, undefined}, doi = {10.1186/gb-2013-14-6-r53}, journal = {Genome Biology} }
@article{ title = {The Oxytricha trifallax Macronuclear Genome: A Complex Eukaryotic Genome with 16,000 Tiny Chromosomes}, type = {article}, year = {2013}, keywords = {Base Sequence,DNA,DNA Copy Number Variations,DNA Fr,Gene Amplification,Gene Rearrangement,Genetic Variation,Genome,Macronucleus,Messenger,Molecular Sequence Data,Protozoan,Sequence Analysis,Telomere,article,bacterial strain,cell expansion,contro,transposase}, volume = {11}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84873111080&doi=10.1371%2Fjournal.pbio.1001473&partnerID=40&md5=7a33622779b1184e80f91a5af464e96f}, id = {f18c1249-5b7c-3955-a47a-73b7aabe29c5}, created = {2018-02-27T18:07:47.715Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-29T20:14:54.723Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Swart2013}, source_type = {article}, notes = {cited By 63}, private_publication = {false}, abstract = {The macronuclear genome of the ciliate Oxytricha trifallax displays an extreme and unique eukaryotic genome architecture with extensive genomic variation. During sexual genome development, the expressed, somatic macronuclear genome is whittled down to the genic portion of a small fraction (~5%) of its precursor "silent" germline micronuclear genome by a process of "unscrambling" and fragmentation. The tiny macronuclear "nanochromosomes" typically encode single, protein-coding genes (a small portion, 10%, encode 2-8 genes), have minimal noncoding regions, and are differentially amplified to an average of ~2,000 copies. We report the high-quality genome assembly of ~16,000 complete nanochromosomes (~50 Mb haploid genome size) that vary from 469 bp to 66 kb long (mean ~3.2 kb) and encode ~18,500 genes. Alternative DNA fragmentation processes ~10% of the nanochromosomes into multiple isoforms that usually encode complete genes. Nucleotide diversity in the macronucleus is very high (SNP heterozygosity is ~4.0%), suggesting that Oxytricha trifallax may have one of the largest known effective population sizes of eukaryotes. Comparison to other ciliates with nonscrambled genomes and long macronuclear chromosomes (on the order of 100 kb) suggests several candidate proteins that could be involved in genome rearrangement, including domesticated MULE and IS1595-like DDE transposases. The assembly of the highly fragmented Oxytricha macronuclear genome is the first completed genome with such an unusual architecture. This genome sequence provides tantalizing glimpses into novel molecular biology and evolution. For example, Oxytricha maintains tens of millions of telomeres per cell and has also evolved an intriguing expansion of telomere end-binding proteins. In conjunction with the micronuclear genome in progress, the O. trifallax macronuclear genome will provide an invaluable resource for investigating programmed genome rearrangements, complementing studies of rearrangements arising during evolution and disease. © 2013 Swart et al.}, bibtype = {article}, author = {Swart, E C and Bracht, J R and Magrini, V and Minx, P and Chen, X and Zhou, Y and Khurana, J S and Goldman, A D and Nowacki, M and Schotanus, K and Jung, S and Fulton, R S and Ly, A and McGrath, S and Haub, K and Wiggins, J L and Storton, D and Matese, J C and Parsons, L and Chang, W.-J. and Bowen, M S and Stover, N A and Jones, T A and Eddy, S R and Herrick, G A and Doak, T G and Wilson, R K and Mardis, E R and Landweber, L F}, doi = {10.1371/journal.pbio.1001473}, journal = {PLoS Biology}, number = {1} }
@article{ title = {The gain and loss of chromosomal integron systems in the Treponema species}, type = {article}, year = {2013}, keywords = {Bacteria (microorganisms); Isoptera; Spirochaetal,Bacterial; Integrases; Integrons; Phylogeny; Reco,Evolution,Genetic; Treponema,Molecular; Genome,article; bacterial genome; classification; geneti,bacterium; chromosome; common ancestry; genetic ma,integrase}, volume = {13}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84872443209&doi=10.1186%2F1471-2148-13-16&partnerID=40&md5=94be39c7b25e688033f3c0988e676bce}, id = {7aa24e9f-dc56-3a38-bb40-d994e7396d73}, created = {2018-02-27T18:07:47.825Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.825Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Wu2013}, source_type = {article}, notes = {cited By 3}, private_publication = {false}, abstract = {Background: Integron systems are now recognized as important agents of bacterial evolution and are prevalent in most environments. One of the human pathogens known to harbor chromosomal integrons, the Treponema spirochetes are the only clade among spirochete species found to carry integrons. With the recent release of many new Treponema genomes, we were able to study the distribution of chromosomal integrons in this genus. Results: We find that the Treponema spirochetes implicated in human periodontal diseases and those isolated from cow and swine intestines contain chromosomal integrons, but not the Treponema species isolated from termite guts. By examining the species tree of selected spirochetes (based on 31 phylogenetic marker genes) and the phylogenetic tree of predicted integron integrases, and assisted by our analysis of predicted integron recombination sites, we found that all integron systems identified in Treponema spirochetes are likely to have evolved from a common ancestor - a horizontal gain into the clade. Subsequent to this event, the integron system was lost in the branch leading to the speciation of T. pallidum and T. phagedenis (the Treponema sps. implicated in sexually transmitted diseases). We also find that the lengths of the integron attC sites shortened through Treponema speciation, and that the integron gene cassettes of T. denticola are highly strain specific. Conclusions: This is the first comprehensive study to characterize the chromosomal integron systems in Treponema species. By characterizing integron distribution and cassette contents in the Treponema sps., we link the integrons to the speciation of the various species, especially to the pathogens T. pallidum and T. phagedenis. © 2013 Wu et al.; licensee BioMed Central Ltd.}, bibtype = {article}, author = {Wu, Y.-W. and Doak, T G and Ye, Y}, doi = {10.1186/1471-2148-13-16}, journal = {BMC Evolutionary Biology}, number = {1} }
@article{ title = {Polynucleobacter necessarius, a model for genome reduction in both free-living and symbiotic bacteria}, type = {article}, year = {2013}, keywords = {Amino Acid Sequence; Base Sequence; Burkholderiac,Bacterial; Molecular Sequence Annotation; Molecul,Burkholderiales; genome streamlining; nonsynonymo,DNA; Symbiosis,Molecular; Genome Size; Genome,article; Betaproteobacteria; Burkholderiales; ero,fresh water}, pages = {18590-18595}, volume = {110}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84887493719&doi=10.1073%2Fpnas.1316687110&partnerID=40&md5=ed62b2e4db69f701238c434431aebd49}, id = {b115f88a-e080-3a5f-8faf-585272d9a0ec}, created = {2018-02-27T18:07:48.101Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.101Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Boscaro201318590}, source_type = {article}, notes = {cited By 21}, private_publication = {false}, abstract = {We present the complete genomic sequence of the essential symbiont Polynucleobacter necessarius ( Betaproteobacteria), which is a valuable case study for several reasons. First, it is hosted by a ciliated protist, Euplotes; bacterial symbionts of ciliates are still poorly known because of a lack of extensive molecular data. Second, the single species P. necessarius contains both symbiotic and free-living strains, allowing for a comparison between closely related organisms with different ecologies. Third, free-living P. necessarius strains are exceptional by themselves because of their small genome size, reduced metabolic flexibility, and high worldwide abundance in freshwater systems. We provide a comparative analysis of P. necessarius metabolism and explore the peculiar features of a genome reduction that occurred on an already streamlined genome. We compare this unusual system with current hypotheses for genome erosion in symbionts and free-living bacteria, propose modifications to the presently accepted model, and discuss the potential consequences of translesion DNA polymerase loss.}, bibtype = {article}, author = {Boscaro, V and Felletti, M and Vannini, C and Ackerman, M S and Chain, P S G and Malfatti, S and Vergez, L M and Shin, M and Doak, T G and Lynch, M and Petroni, G}, doi = {10.1073/pnas.1316687110}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, number = {46} }
@article{ title = {Expanding the Catalog of Cas Proteins by Metagenomes}, type = {article}, year = {2013}, id = {dbb74050-7891-34f2-ba46-2649930b38ce}, created = {2018-02-27T18:07:48.467Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.467Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, bibtype = {article}, author = {Zhang, Q., Doak, T.G., Rho, M., Ye, Y.}, journal = {PLoS CB} }
@inproceedings{ title = {National center for genome analysis support leverages XSEDE to support life science research}, type = {inproceedings}, year = {2013}, keywords = {Bioinformatics,Cyber infrastructures,Genes,Genome analysis,Information management,Life scien}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84883075756&doi=10.1145%2F2484762.2484790&partnerID=40&md5=48e61b39bea9eec2bfe4e92793659683}, city = {San Diego, CA}, id = {f4d0a793-714e-3715-ad41-6c74c936b677}, created = {2018-02-27T18:07:48.627Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T19:31:59.795Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Leduc2013}, source_type = {conference}, notes = {<b>From Duplicate 2 (<i>National center for genome analysis support leverages XSEDE to support life science research</i> - Leduc, R D; Wu, L.-S.; Ganote, C L; Doak, T; Blood, P D; Vaughn, M)<br/></b><br/>cited By 0; Conference of Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2013 ; Conference Date: 22 July 2013 Through 25 July 2013; Conference Code:98539}, private_publication = {false}, abstract = {The National Center for Genome Analysis Support (NCGAS) is a response to the concern that NSF-funded life scientists were underutilizing the national cyberinfrastructure, because there has been little effort to tailor these resources to the life scientist communities needs. NCGAS is a multi- institutional service center that provides computational re- sources, specialized systems support to both the end-user and systems administrators, curated sets of applications, and most importantly scientific consultations for domain scientists unfamiliar with next generation DNA sequence data analysis. NCGAS is a partnership between Indiana University Pervasive Technology Institute, Texas Advanced Computing Center, San Diego Supercomputing Center, and the Pittsburgh Supercomputing Center. NCGAS provides hardened bioinformatic applications and user support on all aspects of a user's data analysis, including data management, systems usage, bioinformatics, and biostatistics related issues. © 2013 by the Association for Computing Machinery, Inc.}, bibtype = {inproceedings}, author = {Leduc, R D and Wu, L.-S. and Ganote, C L and Doak, T and Blood, P D and Vaughn, M and LeDuc, R., Wu, L.-S., Ganote, C., Doak, T., Blood, P., Vaughn, M., and Williams, B.}, doi = {10.1145/2484762.2484790}, booktitle = {Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery (XSEDE '13)} }
@article{ title = {Reply to massey: Drift does influence mutation-rate evolution}, type = {article}, year = {2013}, keywords = {Biological Evolution; Chlamydomonas reinhardtii;,Genetic; Mutation Rate; Reproductive Isolation,cell division; effective population size; evolutio}, pages = {E860}, volume = {110}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84874588658&doi=10.1073%2Fpnas.1220650110&partnerID=40&md5=cd3779ebb56fa9e6f03a050dce2075df}, id = {f20854af-0db1-3f55-99a9-6fa8fb49bdf9}, created = {2018-02-27T18:07:48.905Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.905Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Sung2013}, source_type = {article}, notes = {cited By 4}, private_publication = {false}, bibtype = {article}, author = {Sung, W and Ackerman, M S and Miller, S F and Doak, T G and Lynch, M}, doi = {10.1073/pnas.1220650110}, journal = {Proceedings of the National Academy of Sciences of the United States of America}, number = {10} }
@inproceedings{ title = {Towards Virtual Computational Facilities for Genomics Research: How 100 Gbps Networking Will Change Bioinformatics}, type = {inproceedings}, year = {2013}, city = {Beijing, China}, id = {8a7bd079-a31b-357a-b64f-ff51a31d0cb2}, created = {2018-02-27T18:07:48.914Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.914Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, bibtype = {inproceedings}, author = {Barnett, W., Michael, S., Wu, L.-S., LeDuc, R., Doak, T.G.}, booktitle = {eScience 2013} }
@inproceedings{ title = {Making campus bridging work for researchers: A case study with mlRho}, type = {inproceedings}, year = {2013}, keywords = {Application programs,Bigjob,Employment,Genes,Genetics,High-throughput,Job analysis,MlRho,Optimization,Performa,Re}, pages = {8}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84882383550&doi=10.1145%2F2484762.2484803&partnerID=40&md5=67cc69a3e36848a9909f0d5b80ef338c}, city = {San Diego, CA}, id = {cdff2e2f-539a-3c3c-9974-d91671da0d62}, created = {2019-08-26T19:07:36.629Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-26T19:07:36.629Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Thota2013}, source_type = {conference}, notes = {cited By 0; Conference of Conference on Extreme Science and Engineering Discovery Environment, XSEDE 2013 ; Conference Date: 22 July 2013 Through 25 July 2013; Conference Code:98539}, private_publication = {false}, abstract = {An increasing number of biologists' computational demands have outgrown the capacity of desktop workstations and they are turning to supercomputers to run their simulations and calculations. Many of today's computational problems, however, require larger resource commitments than even individual universities can provide. XSEDE is one of the first places researchers turn to when they outgrow their campus resources. XSEDE machines are far larger (by at least an order of magnitude) than what most universities offer. Transitioning from a campus resource to an XSEDE resource is seldom a trivial task. XSEDE has taken many steps to make this easier, including the Campus Bridging initiative, the Campus Champions program, the Extended Collaborative Support Service (ECSS) [1] program, and through education and outreach. In this paper, our team of biologists and application support analysts (including a Campus Champion) dissect a computationally intensive biology project and share the insights we gain to help strengthen the programs mentioned above. We worked on a project to calculate population mutation and recombination rates of tens of genome profiles using mlRho [2], a serial, open-source, genome analysis code. For the initial investigation, we estimated that we would need 6.3 million service units (SUs) on the Ranger system. Three of the most important places where the biologists needed help in transitioning to XSEDE were (i) preparing the proposal for 6.3 million SUs on XSEDE, (ii) scaling up the existing workow to hundreds of cores and (iii) performance optimization. The Campus Bridging initiative makes all of these tasks easier by providing tools and a consistent software stack across centers. Ideally, Campus Champions are able to provide support on (i), (ii) and (iii), while ECSS staff can assist with (ii) and (iii). But (i), (ii) and (iii) are often not part of a Campus Champion's regular job description. To someone writing an XSEDE proposal for the first time, a link to the guidelines and a few pointers may not always be enough for a successful application. In this paper we describe a new role for a campus bridging expert to play in closing the gaps between existing programs and present mlRho as a case study. © 2013 by the Association for Computing Machinery, Inc.}, bibtype = {inproceedings}, author = {Thota, A and Michael, S and Xu, S and Haubold, B and Doak, T and Henschel, R}, doi = {10.1145/2484762.2484803}, booktitle = {Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery (XSEDE '13)} }
@inproceedings{ title = {Trinity RNA-Seq assembler performance optimization}, type = {inproceedings}, year = {2012}, keywords = {Application performance,Biological materials,Critical parts,DNA seque,Management,Optimization,RNA}, websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84865314650&doi=10.1145%2F2335755.2335842&partnerID=40&md5=30fc3625a3985dfa9953003f6cd44c42}, city = {Chicago, IL}, id = {86161a59-572f-39e5-b77f-e419c8b2382b}, created = {2018-02-27T18:07:47.211Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.211Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {Henschel2012}, source_type = {conference}, notes = {<b>From Duplicate 2 (<i>Trinity RNA-Seq assembler performance optimization</i> - Henschel, R; Nista, P M; Lieber, M; Haas, B J; Wu, L.-S.; Leduc, R D)<br/></b><br/>cited By 0; Conference of 1st Conference of the Extreme Science and Engineering Discovery Environment: Bridging from the eXtreme to the Campus and Beyond, XSEDE12 ; Conference Date: 16 July 2012 Through 19 July 2012; Conference Code:92061}, private_publication = {false}, abstract = {RNA-sequencing is a technique to study RNA expression in biological material. It is quickly gaining popularity in the field of transcriptomics. Trinity is a software tool that was developed for efficient de novo reconstruction of transcriptomes from RNA-Seq data. In this paper we first conduct a performance study of Trinity and compare it to previously published data from 2011. The version from 2011 is much slower than many other de novo assemblers and biologists have thus been forced to choose between quality and speed. We examine the runtime behavior of Trinity as a whole as well as its individual components and then optimize the most performance critical parts. We find that standard best practices for HPC applications can also be applied to Trinity, especially on systems with large amounts of memory. When combining best practices for HPC applications along with our specific performance optimization, we can decrease the runtime of Trinity by a factor of 3.9. This brings the runtime of Trinity in line with other de novo assemblers while maintaining superior quality. The purpose of this paper is to describe a series of improvements to Trinity, quantify the execution improvements achieved, and document the new version of the software. © 2012 ACM.}, bibtype = {inproceedings}, author = {Henschel, R and Nista, P M and Lieber, M and Haas, B J and Wu, L.-S. and Leduc, R D and Henschel, R., Lieber, M., Wu, L-S, Nista, P. M., Haas, B.J., and LeDuc, R.D}, doi = {10.1145/2335755.2335842}, booktitle = {ACM International Conference Proceeding Series} }
@techreport{ title = {2012 Annual Report on Training, Education, and Outreach Activities of the Indiana University Pervasive Technology Institute and affiliated organizations}, type = {techreport}, year = {2012}, institution = {2012 ANNUAL REPORT ON TRAINING, EDUCATION, AND OUTREACH ACTIVITIES OF THE INDIANA UNIVERSITY PERVASIVE TECHNOLOGY INSTITUTE AND AFFILIATED ORGANIZATIONS, v p..}, id = {00ae9d53-ab1c-3c22-b2d7-7bc256b312f8}, created = {2018-02-27T18:07:47.644Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:47.644Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, citation_key = {mpps12}, source_type = {techreport}, private_publication = {false}, bibtype = {techreport}, author = {Miller, T and Ping, R J and Plale, B and Stewart, CA A} }
@techreport{ title = {Indiana University Pervasive Technology Institute – Research Technologies: XSEDE Service Provider and XSEDE subcontract report (PY1: 1 July 2011 to 30 June 2012)}, type = {techreport}, year = {2012}, websites = {http://hdl.handle.net/2022/14702}, institution = {Indiana University}, id = {e99bacbd-a75e-391e-90a4-136e74b49747}, created = {2018-02-27T18:07:48.253Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2019-08-27T19:22:42.068Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, abstract = {Annual report on IU's XSEDE activitiesThis document is a summary of the activities of the Research Technologies division of UITS, a Service & Cyberinfrastructure Center affiliated with the Indiana University Pervasive Technology Institute, as part of the eXtreme Science and Engineering Discovery Environment (XSEDE) during XSEDE Program Year 1 (1 July 2011 – 30 June 2012). This document consists of three parts: - Section 2 of this document describes IU’s activities as an XSEDE Service Provider, using the format prescribed by XSEDE for reporting such activities. - Section 3 of this document describes IU’s activities as part of XSEDE management, operations, and support activities funded under a subcontract from the National Center for Supercomputer Applications (NCSA), the lead organization for XSEDE. This section is organized by the XSEDE Work Breakdown Structure (WBS) plan. - Appendix 1 is a summary table of IU’s education, outreach, and training events funded and supported in whole or in part by IU’s subcontract from NCSA as part of XSEDE.}, bibtype = {techreport}, author = {Stewart, C.A. and Miller, T and Hancock, D.Y and Marru, S and Peirce, M and Link, M and Simms, SC and Sieffert, K and Wernert, J and Bolte, J} }
@inproceedings{ title = {Genomics, Transcriptomics, and Proteomics: Engaging Biologists (Workshop)}, type = {inproceedings}, year = {2012}, city = {Chicago, IL.}, id = {7100f8e3-cbba-3871-91e6-d44f76a29961}, created = {2018-02-27T18:07:48.680Z}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2018-02-27T18:07:48.680Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {false}, hidden = {false}, private_publication = {false}, bibtype = {inproceedings}, author = {LeDuc, Richard D}, booktitle = { eScience 2012} }
@techreport{ title = {2012 Annual Report - Advanced Biomedical Information Technology Core}, type = {techreport}, year = {2012}, keywords = {Technical Report}, websites = {https://scholarworks.iu.edu/dspace/handle/2022/15229}, id = {d8ccc33c-8b65-3fd9-ae78-c2bde9418836}, created = {2020-09-10T21:44:59.652Z}, accessed = {2020-09-10}, file_attached = {false}, profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d}, group_id = {f5b9ee19-654f-3d16-8c8d-62e8c4f73340}, last_modified = {2020-09-10T21:44:59.652Z}, read = {false}, starred = {false}, authored = {false}, confirmed = {true}, hidden = {false}, private_publication = {false}, bibtype = {techreport}, author = {Barnett, William K and Shankar, Ganesh and Hancock, David Y and Allen, Matt and Seiffert, Kurt and Boyles, Mike and Rogers, Jeffrey L and Wernert, Eric and Link, Matthew R and Stewart, Craig A and Barnett, W K and Shankar, G and Hancock, D Y and Allen, M and Seiffert, K and Boyles, M and Rogers, J L and Wernert, E and Link, M R and Stewart, C A} }