@article{
 title = {Modeling of the Coral Microbiome: the Influence of Temperature and Microbial Network},
 type = {article},
 year = {2020},
 volume = {11},
 websites = {http://mbio.asm.org/lookup/doi/10.1128/mBio.02691-19},
 month = {3},
 publisher = {American Society for Microbiology},
 day = {3},
 id = {9a8187a7-31ae-3901-b654-7705770f24a6},
 created = {2020-04-29T21:56:56.535Z},
 accessed = {2020-03-06},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.636Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {<p> Host-associated microbial communities are shaped by extrinsic and intrinsic factors to the holobiont organism. Environmental factors and microbe-microbe interactions act simultaneously on the microbial community structure, making the microbiome dynamics challenging to predict. The coral microbiome is essential to the health of coral reefs and sensitive to environmental changes. Here, we develop a dynamic model to determine the microbial community structure associated with the surface mucus layer (SML) of corals using temperature as an extrinsic factor and microbial network as an intrinsic factor. The model was validated by comparing the predicted relative abundances of microbial taxa to the relative abundances of microbial taxa from the sample data. The SML microbiome from <named-content content-type="genus-species">Pseudodiploria strigosa</named-content> was collected across reef zones in Bermuda, where inner and outer reefs are exposed to distinct thermal profiles. A shotgun metagenomics approach was used to describe the taxonomic composition and the microbial network of the coral SML microbiome. By simulating the annual temperature fluctuations at each reef zone, the model output is statistically identical to the observed data. The model was further applied to six scenarios that combined different profiles of temperature and microbial network to investigate the influence of each of these two factors on the model accuracy. The SML microbiome was best predicted by model scenarios with the temperature profile that was closest to the local thermal environment, regardless of the microbial network profile. Our model shows that the SML microbiome of <italic>P. strigosa</italic> in Bermuda is primarily structured by seasonal fluctuations in temperature at a reef scale, while the microbial network is a secondary driver. </p>},
 bibtype = {article},
 author = {Lima, Laís F. O. and Weissman, Maya and Reed, Micheal and Papudeshi, Bhavya and Alker, Amanda T. and Morris, Megan M. and Edwards, Robert A. and de Putron, Samantha J. and Vaidya, Naveen K. and Dinsdale, Elizabeth A.},
 editor = {Medina, Monica and McFall-Ngai, Margaret J.},
 doi = {10.1128/mBio.02691-19},
 journal = {mBio},
 number = {2}
}

Host-associated microbial communities are shaped by extrinsic and intrinsic factors to the holobiont organism. Environmental factors and microbe-microbe interactions act simultaneously on the microbial community structure, making the microbiome dynamics challenging to predict. The coral microbiome is essential to the health of coral reefs and sensitive to environmental changes. Here, we develop a dynamic model to determine the microbial community structure associated with the surface mucus layer (SML) of corals using temperature as an extrinsic factor and microbial network as an intrinsic factor. The model was validated by comparing the predicted relative abundances of microbial taxa to the relative abundances of microbial taxa from the sample data. The SML microbiome from Pseudodiploria strigosa was collected across reef zones in Bermuda, where inner and outer reefs are exposed to distinct thermal profiles. A shotgun metagenomics approach was used to describe the taxonomic composition and the microbial network of the coral SML microbiome. By simulating the annual temperature fluctuations at each reef zone, the model output is statistically identical to the observed data. The model was further applied to six scenarios that combined different profiles of temperature and microbial network to investigate the influence of each of these two factors on the model accuracy. The SML microbiome was best predicted by model scenarios with the temperature profile that was closest to the local thermal environment, regardless of the microbial network profile. Our model shows that the SML microbiome of P. strigosa in Bermuda is primarily structured by seasonal fluctuations in temperature at a reef scale, while the microbial network is a secondary driver.

@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 = {71dfdcaa-eae3-336c-b59c-d39d75b9c938},
 created = {2020-04-29T21:56:56.670Z},
 accessed = {2019-08-09},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.752Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 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}
}

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.

@article{
 title = {Stilbenoid prenyltransferases define key steps in the diversification of peanut phytoalexins},
 type = {article},
 year = {2018},
 id = {d1c73d84-134d-3d83-b71e-470ccf572cf0},
 created = {2020-04-29T21:56:56.527Z},
 accessed = {2019-08-09},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.639Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {© 2018 by The American Society for Biochemistry and Molecular Biology, Inc. 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 stilbenoidspecific, 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 = {Journal of Biological Chemistry}
}

© 2018 by The American Society for Biochemistry and Molecular Biology, Inc. 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 stilbenoidspecific, advancing our understanding of this specialized enzyme family and shedding critical light onto the biosynthesis of bioactive stilbenoids.

@article{
 title = {Escherichia coli cultures maintain stable subpopulation structure during long-term evolution},
 type = {article},
 year = {2018},
 pages = {E4642-E4650},
 volume = {115},
 id = {124ad696-a1ad-347a-b98f-eb5de4545da3},
 created = {2020-04-29T21:56:56.545Z},
 accessed = {2019-08-09},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.631Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 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 ( ∆mutL ) Escherichia coli populations have evolved over 3 y in a spatially heterogeneous and nutritionally complex environment. Metagenomic 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 uropathogenic 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.},
 bibtype = {article},
 author = {Behringer, Megan G. and Choi, Brian I. and Miller, Samuel F. and Doak, Thomas G. and Karty, Jonathan A. and Guo, Wanfeng and Lynch, Michael},
 doi = {10.1073/pnas.1708371115},
 journal = {Proceedings of the National Academy of Sciences},
 number = {20}
}

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 ( ∆mutL ) Escherichia coli populations have evolved over 3 y in a spatially heterogeneous and nutritionally complex environment. Metagenomic 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 uropathogenic 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.

@article{
 title = {Limited Mutation-Rate Variation within Paramecium aurelia species complex},
 type = {article},
 year = {2018},
 pages = {2532-2526},
 volume = {8},
 websites = {https://doi.org/10.1534/g3.118.200420},
 id = {6a38f690-49d9-3c5c-8c3b-e55c057b7ceb},
 created = {2020-04-29T21:56:56.772Z},
 accessed = {2018-11-03},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.840Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {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., Doak, G, Thomas., Lynch, Michael.},
 doi = {10.1534/g3.118.200420},
 journal = {G3:Gene, Genome, Genetics},
 number = {7}
}

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.

@article{
 title = {Diversity and universality of endosymbiotic Rickettsia in the fish parasite Ichthyophthirius multifiliis},
 type = {article},
 year = {2017},
 keywords = {Alphaproteobacteria,Ciliophora,Hyperparasitism,Phagocytosis,Sphingobacteria,Symbiosis},
 pages = {189},
 volume = {8},
 id = {b2144e94-c37a-3076-a217-5012fde61313},
 created = {2020-04-29T21:56:56.521Z},
 accessed = {2019-08-09},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.597Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 private_publication = {false},
 abstract = {© 2017 Zaila, Doak, Ellerbrock, Tung, Martins, Kolbin, Yao, Cassidy-Hanley, Clark and Chang. 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.},
 bibtype = {article},
 author = {Zaila, Kassandra E. and Doak, Thomas G. and Ellerbrock, Hannah and Tung, Che Huang and Martins, Mauricio L. and Kolbin, Daniel and Yao, Meng Chao and Cassidy-Hanley, Donna M. and Clark, Theodore G. and Chang, Wei Jen},
 doi = {10.3389/fmicb.2017.00189},
 journal = {Frontiers in Microbiology}
}

© 2017 Zaila, Doak, Ellerbrock, Tung, Martins, Kolbin, Yao, Cassidy-Hanley, Clark and Chang. 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.

@article{
 title = {STAR-Fusion: Fast and Accurate Fusion Transcript Detection from RNA-Seq},
 type = {article},
 year = {2017},
 websites = {http://biorxiv.org/content/early/2017/03/24/120295.abstract},
 month = {3},
 day = {24},
 id = {56692a90-d89a-3d56-be64-bd4460842c60},
 created = {2020-04-29T21:56:57.281Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.366Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Haas2017},
 source_type = {JOUR},
 private_publication = {false},
 abstract = {Motivation: Fusion genes created by genomic rearrangements can be potent drivers of tumorigenesis. However, accurate identification of functionally fusion genes from genomic sequencing requires whole genome sequencing, since exonic sequencing alone is often insufficient. Transcriptome sequencing provides a direct, highly effective alternative for capturing molecular evidence of expressed fusions in the precision medicine pipeline, but current methods tend to be inefficient or insufficiently accurate, lacking in sensitivity or predicting large numbers of false positives. Here, we describe STAR-Fusion, a method that is both fast and accurate in identifying fusion transcripts from RNA-Seq data. Results: We benchmarked STAR-Fusion's fusion detection accuracy using both simulated and genuine Illumina paired-end RNA-Seq data, and show that it has superior performance compared to popular alternative fusion detection methods. Availability and implementation: STAR-Fusion is implemented in Perl, freely available as open source software at http://star-fusion.github.io, and supported on Linux.},
 bibtype = {article},
 author = {Haas, Brian and Dobin, Alexander and Stransky, Nicolas and Li, Bo and Yang, Xiao and Tickle, Timothy and Bankapur, Asma and Ganote, Carrie and Doak, Thomas and Pochet, Natalie and Sun, Jing and Wu, Catherine and Gingeras, Thomas and Regev, Aviv},
 journal = {bioRxiv},
 keywords = {PY7}
}

Motivation: Fusion genes created by genomic rearrangements can be potent drivers of tumorigenesis. However, accurate identification of functionally fusion genes from genomic sequencing requires whole genome sequencing, since exonic sequencing alone is often insufficient. Transcriptome sequencing provides a direct, highly effective alternative for capturing molecular evidence of expressed fusions in the precision medicine pipeline, but current methods tend to be inefficient or insufficiently accurate, lacking in sensitivity or predicting large numbers of false positives. Here, we describe STAR-Fusion, a method that is both fast and accurate in identifying fusion transcripts from RNA-Seq data. Results: We benchmarked STAR-Fusion's fusion detection accuracy using both simulated and genuine Illumina paired-end RNA-Seq data, and show that it has superior performance compared to popular alternative fusion detection methods. Availability and implementation: STAR-Fusion is implemented in Perl, freely available as open source software at http://star-fusion.github.io, and supported on Linux.

@article{
 title = {Population Genomics of Paramecium Species.},
 type = {article},
 year = {2017},
 pages = {1194-1216},
 volume = {34},
 month = {5},
 id = {a1f4014c-10fb-3402-9cb1-9605e50ae575},
 created = {2020-04-29T21:56:57.435Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.629Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Johri2017},
 source_type = {Journal Article},
 language = {eng},
 country = {United States},
 patent_owner = {NLM},
 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 approximately 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 approximately 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.},
 bibtype = {article},
 author = {Johri, Parul and Krenek, Sascha and Marinov, Georgi K and Doak, Thomas G and Berendonk, Thomas U and Lynch, Michael},
 doi = {10.1093/molbev/msx074},
 journal = {Molecular biology and evolution},
 number = {5},
 keywords = {PY7}
}

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 approximately 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 approximately 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.

@article{
 title = {Investigating biogeographic boundaries of the Sunda shelf: A phylogenetic analysis of two island populations of Macaca fascicularis},
 type = {article},
 year = {2017},
 id = {9ce82f22-5286-3304-b09a-ab24fabe84b9},
 created = {2020-04-29T21:56:57.553Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.641Z},
 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},
 journal = {American Journal of Physical Anthropology},
 keywords = {PY7}
}

@inproceedings{
 title = {A voice for bioinformatics},
 type = {inproceedings},
 year = {2017},
 keywords = {PY7},
 volume = {Part F1287},
 id = {01546887-e0fd-398b-92d0-567e91586ddd},
 created = {2020-04-29T21:56:57.637Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.727Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Ganote2017},
 private_publication = {false},
 abstract = {© 2017 ACM. 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.},
 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 = {ACM International Conference Proceeding Series}
}

© 2017 ACM. 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.

@article{
 title = {Estimating Seven Coefficients of Pairwise Relatedness Using Population Genomic Data},
 type = {article},
 year = {2017},
 websites = {http://www.genetics.org/content/early/2017/03/21/genetics.116.190660},
 id = {54fe2778-cd55-3760-a8c3-f89a9bb0eaf8},
 created = {2020-04-29T21:56:57.807Z},
 accessed = {2017-08-31},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.891Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ackerman2017},
 private_publication = {false},
 bibtype = {article},
 author = {Ackerman, Matthew S. and Johri, Parul and Spitze, Ken and Xu, Sen and Doak, Thomas G. and Young, Kimberly and Lynch, Michael},
 journal = {Genetics},
 keywords = {PY7}
}

@article{
 title = {Optimizing and evaluating the reconstruction of Metagenome-assembled microbial genomes},
 type = {article},
 year = {2017},
 id = {c18bc112-bd24-3caf-865d-fee7cc2f2257},
 created = {2020-04-29T21:56:58.661Z},
 accessed = {2019-08-09},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.770Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {© 2017 The Author(s). 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}
}

© 2017 The Author(s). 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.

@article{
 title = {Critical Assessment of Metagenome Interpretation − a benchmark of computational metagenomics software},
 type = {article},
 year = {2017},
 keywords = {PY7},
 pages = {099127+},
 websites = {http://dx.doi.org/10.1101/099127},
 month = {1},
 publisher = {Cold Spring Harbor Labs Journals},
 id = {16b16465-2f77-3c31-992b-b73e77b37440},
 created = {2020-04-29T21:56:59.407Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.492Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {citeulike:14357255},
 source_type = {article},
 private_publication = {false},
 abstract = {bioRxiv - the preprint server for biology, operated by Cold Spring Harbor Laboratory, a research and educational institution},
 bibtype = {article},
 author = {Sczyrba, Alexander and Hofmann, Peter and Belmann, Peter and Koslicki, David and Janssen, Stefan and Droege, Johannes and Gregor, Ivan and Majda, Stephan and Fiedler, Jessika and Dahms, Eik and Bremges, Andreas and Fritz, Adrian and Garrido-Oter, Ruben and Jorgensen, Tue S and Shapiro, Nicole and Blood, Philip D and Gurevich, Alexey and Bai, Yang and Turaev, Dmitrij and DeMaere, Matthew Z and Chikhi, Rayan and Nagarajan, Niranjan and Quince, Christopher and Hansen, Lars H and Sorensen, Soren J and Chia, Burton K H and Denis, Bertrand and Froula, Jeff L and Wang, Zhong and Egan, Robert and Kang, Dongwan D and Cook, Jeffrey J and Deltel, Charles and Beckstette, Michael and Lemaitre, Claire and Peterlongo, Pierre and Rizk, Guillaume and Lavenier, Dominique and Wu, Yu-Wei and Singer, Steven W and Jain, Chirag and Strous, Marc and Klingenberg, Heiner and Meinicke, Peter and Barton, Michael and Lingner, Thomas and Lin, Hsin-Hung and Liao, Yu-Chieh and Gueiros, Genivaldo and Cuevas, Daniel A and Edwards, Robert A and Saha, Surya and Piro, Vitor C and Renard, Bernhard Y and Pop, Mihai and Klenk, Hans-Peter and Goeker, Markus and Kyrpides, Nikos and Woyke, Tanja and Vorholt, Julia A and Schulze-Lefert, Paul and Rubin, Edward M and Darling, Aaron E and Rattei, Thomas and McHardy, Alice C},
 doi = {10.1101/099127},
 journal = {bioRxiv}
}

bioRxiv - the preprint server for biology, operated by Cold Spring Harbor Laboratory, a research and educational institution

@inproceedings{
 title = {The Advanced Cyberinfrastructure Research and Education Facilitators Virtual Residency: Toward a National Cyberinfrastructure Workforce},
 type = {inproceedings},
 year = {2016},
 keywords = {PY6},
 pages = {57:1--57:8},
 websites = {http://doi.acm.org/10.1145/2949550.2949584},
 publisher = {ACM},
 city = {New York, NY, USA},
 series = {XSEDE16},
 id = {cb9454a6-a961-3835-aa7f-777a081c9706},
 created = {2020-04-29T21:56:57.031Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.109Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Neeman:2016:ACR:2949550.2949584},
 source_type = {inproceedings},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Neeman, Henry and Bergstrom, Aaron and Brunson, Dana and Ganote, Carrie and Gray, Zane and Guilfoos, Brian and Kalescky, Robert and Lemley, Evan and Moore, Brian G and Ramadugu, Sai Kumar and Romanella, Alana and Rush, Johnathan and Sherman, Andrew H and Stengel, Brian and Voss, Dan},
 doi = {10.1145/2949550.2949584},
 booktitle = {Proceedings of the XSEDE16 Conference on Diversity, Big Data, and Science at Scale}
}

@inproceedings{
 title = {Computational Considerations in Transcriptome Assemblies and Their Evaluation, using High Quality Human RNA-Seq data},
 type = {inproceedings},
 year = {2016},
 keywords = {PY6},
 pages = {1-4},
 websites = {http://dl.acm.org/citation.cfm?doid=2949550.2949572},
 publisher = {ACM Press},
 city = {New York, New York, USA},
 id = {0835ed0a-61ec-3f6e-a63d-9b209cdd06a3},
 created = {2020-04-29T21:56:57.285Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.382Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ghaffari2016},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Ghaffari, Noushin and Abante, Jordi and Singh, Raminder and Blood, Philip D. and Johnson, Charles D.},
 doi = {10.1145/2949550.2949572},
 booktitle = {Proceedings of the XSEDE16 on Diversity, Big Data, and Science at Scale - XSEDE16}
}

@article{
 title = {TCGA Expedition: A Data Acquisition and Management System for TCGA Data},
 type = {article},
 year = {2016},
 pages = {e0165395},
 volume = {11},
 websites = {http://dx.plos.org/10.1371/journal.pone.0165395},
 month = {10},
 publisher = {Public Library of Science},
 day = {27},
 id = {7b09b41f-7796-39c4-9097-2b21db648ce1},
 created = {2020-04-29T21:56:57.359Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.621Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Chandran2016},
 private_publication = {false},
 bibtype = {article},
 author = {Chandran, Uma R. and Medvedeva, Olga P. and Barmada, M. Michael and Blood, Philip D. and Chakka, Anish and Luthra, Soumya and Ferreira, Antonio and Wong, Kim F. and Lee, Adrian V. and Zhang, Zhihui and Budden, Robert and Scott, J. Ray and Berndt, Annerose and Berg, Jeremy M. and Jacobson, Rebecca S.},
 editor = {Ebrahimie, Esmaeil},
 doi = {10.1371/journal.pone.0165395},
 journal = {PLOS ONE},
 number = {10},
 keywords = {PY7}
}

@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 = {PY6},
 pages = {2157-2163},
 volume = {6},
 websites = {http://view.ncbi.nlm.nih.gov/pubmed/27194804},
 id = {0a9a54e3-7b0f-3124-b9b2-7732a0ccea75},
 created = {2020-04-29T21:56:57.557Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.624Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {citeulike:14110493},
 source_type = {article},
 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. Copyright \copyright 2016 Kucukyildirim et al.},
 bibtype = {article},
 author = {Kucukyildirim, Sibel and Long, Hongan and Sung, Way and Miller, Samuel F and Doak, Thomas G and Lynch, Michael},
 journal = {G3 (Bethesda, Md.)},
 number = {7}
}

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. Copyright \copyright 2016 Kucukyildirim et al.

@article{
 title = {Integrated bottom-up and top-down proteomics of patient-derived breast tumor xenografts},
 type = {article},
 year = {2016},
 websites = {http://www.mcponline.org/content/15/1/45.short},
 id = {9b43823e-e659-3608-90f0-7b8d09f29cd6},
 created = {2020-04-29T21:56:58.370Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.560Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Ntai2016},
 private_publication = {false},
 bibtype = {article},
 author = {Ntai, I and LeDuc, RD and Fellers, RT},
 journal = {Molecular & Cellular},
 keywords = {PY7}
}

@article{
 title = {Genomic and Metagenomic Analysis of Diversity-Generating Retroelements Associated with Treponema denticola.},
 type = {article},
 year = {2016},
 keywords = {PY5},
 pages = {852},
 volume = {7},
 websites = {http://view.ncbi.nlm.nih.gov/pubmed/27375574,http://journal.frontiersin.org/Article/10.3389/fmicb.2016.00852/abstract},
 month = {6},
 publisher = {Frontiers},
 day = {3},
 id = {ff0eb248-87ac-39ef-959b-4950d0cf9f01},
 created = {2020-04-29T21:56:58.958Z},
 accessed = {2017-09-05},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.052Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {citeulike:14110494},
 source_type = {article},
 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.},
 bibtype = {article},
 author = {Nimkulrat, Sutichot and Lee, Heewook and Doak, Thomas G. and Ye, Yuzhen},
 doi = {10.3389/fmicb.2016.00852},
 journal = {Frontiers in microbiology}
}

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.

@article{
 title = {Insertion sequence-caused large-scale rearrangements in the genome of Escherichia coli},
 type = {article},
 year = {2016},
 pages = {7109-7119},
 volume = {44},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/27431326,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC5009759,http://dx.doi.org/10.1093/nar/gkw647},
 month = {9},
 publisher = {Oxford University Press},
 day = {6},
 id = {0eeadcae-0dae-3861-b0cf-6f5506c05e0d},
 created = {2020-04-29T21:56:59.093Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.191Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Lee2016},
 source_type = {JOUR},
 notes = {<b>From Duplicate 3 (<i>Insertion sequence-caused large-scale rearrangements in the genome of Escherichia coli</i> - Lee, Heewook; Doak, Thomas G; Popodi, Ellen; Foster, Patricia L; Tang, Haixu)<br/></b><br/>10.1093/nar/gkw647},
 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.},
 bibtype = {article},
 author = {Lee, Heewook and Doak, Thomas G and Popodi, Ellen and Foster, Patricia L and Tang, Haixu},
 doi = {10.1093/nar/gkw647},
 journal = {Nucleic Acids Research},
 number = {15},
 keywords = {PY7}
}

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.

@article{
 title = {Subtractive assembly for comparative metagenomics, and its application to type 2 diabetes metagenomes.},
 type = {article},
 year = {2015},
 volume = {16},
 websites = {https://genomebiology.biomedcentral.com/articles/10.1186/s13059-015-0804-0,http://view.ncbi.nlm.nih.gov/pubmed/26527161},
 id = {798d236f-e4a2-329c-b76b-4623c9f95a02},
 created = {2020-04-29T21:56:57.369Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.446Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {citeulike:14110496},
 source_type = {article},
 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.},
 bibtype = {article},
 author = {Wang, Mingjie and Doak, TG Thomas G and Ye, Yuzhen},
 journal = {Genome biology},
 keywords = {DvlFinal,PY5}
}

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.

@inproceedings{
 title = {Cyberinfrastructure resources enabling creation of the loblolly pine reference transcriptome},
 type = {inproceedings},
 year = {2015},
 websites = {http://dl.acm.org/citation.cfm?id=2792748},
 id = {2d8fcd24-bf12-3cb1-ad0c-dbe456fab15f},
 created = {2020-04-29T21:56:58.086Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.160Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Wu2015},
 private_publication = {false},
 bibtype = {inproceedings},
 author = {Wu, LS and Ganote, CL and Doak, TG and Barnett, W},
 doi = {10.1145/2792745.2792748},
 booktitle = {Proceedings of the XSEDE Conference: Scientific Advancements Enabled by Enhanced Cyberinfrastructure},
 keywords = {PY3}
}

@article{
 title = {Strand-specific community RNA-seq reveals prevalent and dynamic antisense transcription in human gut microbiota},
 type = {article},
 year = {2015},
 websites = {http://journal.frontiersin.org/article/10.3389/fmicb.2015.00896},
 id = {319e2681-bbbb-3de8-8fe3-648b77345d04},
 created = {2020-04-29T21:56:58.140Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.197Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Bao2015},
 private_publication = {false},
 bibtype = {article},
 author = {Bao, G and Wang, M and Doak, TG and Ye, Y},
 journal = {Frontiers in microbiology},
 keywords = {PY5}
}

@article{
 title = {Saccharide breakdown and fermentation by the honey bee gut microbiome},
 type = {article},
 year = {2015},
 websites = {http://onlinelibrary.wiley.com/doi/10.1111/1462-2920.12526/full},
 id = {1ef427c5-92b1-3611-98f8-29a479fad900},
 created = {2020-04-29T21:56:58.156Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.253Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Lee2015},
 private_publication = {false},
 bibtype = {article},
 author = {Lee, FJ and Rusch, DB and Stewart, FJ},
 journal = {Environmental},
 keywords = {PY4}
}

@inproceedings{
 title = {NCBI-BLAST Programs Optimization on XSEDE Resources for Sustainable Aquaculture},
 type = {inproceedings},
 year = {2015},
 keywords = {DvlFinal,PY4},
 pages = {4:1--4:5},
 websites = {http://dl.acm.org/citation.cfm?doid=2792745.2792749,http://doi.acm.org/10.1145/2792745.2792749},
 publisher = {ACM},
 city = {New York, NY, USA},
 series = {XSEDE '15},
 id = {b2a88a22-df1b-3ca6-84ab-195c35cb70da},
 created = {2020-04-29T21:56:59.005Z},
 accessed = {2017-09-05},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.114Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Seetharam:2015:NPO:2792745.2792749},
 source_type = {inproceedings},
 private_publication = {false},
 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 = {10.1145/2792745.2792749},
 booktitle = {Proceedings of the 2015 XSEDE Conference: Scientific Advancements Enabled by Enhanced Cyberinfrastructure}
}

@article{
 title = {Daphnia magna transcriptome by RNA-Seq across 12 environmental stressors},
 type = {article},
 year = {2015},
 keywords = {PY4},
 pages = {1032-1037},
 volume = {16},
 websites = {https://academic.oup.com/femsec/article-lookup/doi/10.1093/femsec/fiw072,https://www.nature.com/articles/srep46227.pdf,http://view.ncbi.nlm.nih.gov/pubmed/28387369,http://www.ncbi.nlm.nih.gov/pubmed/28387369,http://www.pubmedcentral.nih.gov/articlerender.},
 month = {2},
 publisher = {Public Library of Science},
 day = {1},
 city = {1752 N St., N.W., Washington, DC},
 id = {e4a284de-b35e-3491-8ea5-3dd1746fdce6},
 created = {2020-04-29T21:56:59.418Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.682Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {citeulike:14366768},
 source_type = {article},
 language = {eng},
 country = {England},
 patent_owner = {NLM},
 private_publication = {false},
 abstract = {In the Gulf of Maine, the copepod Calanus finmarchicus co-occurs with the neurotoxin-producing dinoflagellate, Alexandrium fundyense. The copepod is resistant to this toxic alga, but little is known about other effects. Gene expression profiles were used to investigate the physiological response of females feeding for two and five days on a control diet or a diet containing either a low or a high dose of A. fundyense. The physiological responses to the two experimental diets were similar, but changed between the time points. At 5-days the response was characterized by down-regulated genes involved in energy metabolism. Detoxification was not a major component of the response. Instead, genes involved in digestion were consistently regulated, suggesting that food assimilation may have been affected. Thus, predicted increases in the frequency of blooms of A. fundyense could affect C. finmarchicus populations by changing the individuals’ energy budget and reducing their ability to build lipid reserves.},
 bibtype = {article},
 author = {Zhang, Yujia Yuehua and Kong, Weijing and Gao, Yang and Liu, Xiaoyan and Gao, Kai and Xie, Han and Wu, Ye and Zhang, Yujia Yuehua and Wang, Jingmin and Gao, Feng and Wu, Xiru and Jiang, Yuwu and Youssef, N. H. and Couger, M. Brian 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. and Wu, Zhiqiang and Yang, Li and Ren, Xianwen and He, Guimei and Zhang, Junpeng Jin and Yang, Jian and Qian, Zhaohui and Dong, Jie and Sun, Lilian and Zhu, Yafang and Du, Jiang and Yang, Fan and Zhang, Shuyi and Jin, Qi and Uy, KL and LeDuc, R and Ganote, C and Tarpy, David R and Mattila, Heather R and Newton, ILG Irene L G and Subramanian, Sandeep and Chaparala, Srilakshmi and Avali, Viji and Ganapathiraju, Madhavi K. and 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, Mohammed and Sugawara, Masayuki and Sadowsky, Michael J. and Young, Nevin D. and Tiffin, Peter and Sousounis, Konstantinos and Qi, Feng and Yadav, Manisha C and Millan, Jose Luis and Toyama, Fubito and Chiba, Chikafumi and Eguchi, Yukiko and Eguchi, Goro and Tsonis, Panagiotis A and Roncalli, Vittoria and Cieslak, Matthew C MC and Lenz, PH Petra H and Rokop, Z P and Horton, Melissa A and Newton, ILG Irene L G and Raborn, RT Taylor and Spitze, Ken and Brendel, Volker P VP and Lynch, Michael and Qin, Xiaomei and Huang, Sheng and Liu, Yanqing and Bian, Mingdi and Shi, Wuliang and Zuo, Zecheng and Yang, Zhenming and Pipes, Lenore and Li, Sheng and Bozinoski, Marjan and Palermo, Robert E. and Peng, Xinxia and Blood, Philip D. Phillip and Kelly, Sara and Weiss, Jeffrey M. and Thierry-Mieg, Jean and Thierry-Mieg, Danielle and Zumbo, Paul and Chen, Ronghua and Schroth, Gary P. and Mason, Christopher E. and Katze, Michael G. and Phuong, Mark Anthony and Mahardika, Gusti N and Peterson, M and Malloy, J and Buonaccorsi, V and Marden, J and Petersen, Isaac T. and Bates, John E. and Dodge, Kenneth A. and Lansford, Jennifer E. and Pettit, Gregory S. and 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. and Orsini, Luisa and Gilbert, Donald and Podicheti, Ram and Jansen, Mieke and Brown, James B and Solari, Omid Shams and Spanier, Katina I and Colbourne, John K and Rush, Douglas and Decaestecker, Ellen and Asselman, Jana and De Schamphelaere, Karel A C and Ebert, Dieter and Haag, Christoph R and Kvist, Jouni and Laforsch, Christian and Petrusek, Adam and Beckerman, Andrew P and Little, Tom J and Chaturvedi, Anurag and Pfrender, Michael E and De Meester, Luc and Frilander, Mikko J and Newton, ILG Irene L G and Sheehan, KB Kathy B and Motamayor, Juan C and Mockaitis, Keithanne and Schmutz, Jeremy and Haiminen, Niina and III, Donald Livingstone and Cornejo, Omar and Findley, Seth D and Zheng, Ping and Utro, Filippo and Royaert, Stefan and Saski, Christopher and Jenkins, Jerry and Podicheti, Ram and Zhao, Meixia and Scheffler, Brian E and Stack, Joseph C and Feltus, Frank A and Mustiga, Guiliana M and Amores, Freddy and Phillips, Wilbert and Marelli, Jean Philippe and May, Gregory D. and Shapiro, Howard and Ma, Jianxin and Bustamante, Carlos D and Schnell, Raymond J and Main, Dorrie and Gilbert, Donald and Parida, Laxmi and Kuhn, DN David N and McGrath, Casey L. CL and Gout, Jean-Francois JF and Johri, P and Doak, Thomas G. TG and Yanagi, Akira and Lynch, Michael and Martínez, Teresa and Ropelewski, Alexander J and González-Mendez, Ricardo and Vázquez, Guillermo J and Robledo, Iraida E. and Martinez, Teresa and Aquino, Edna E. and Robledo, Iraida E. and Martinez, Idali and Vazquez, Guillermo J. and Aquino, Edna E. and Robledo, Iraida E. and Lipovich, Leonard and Hou, Zhuo-Cheng and Jia, Hui and Sinkler, Christopher and McGowen, Michael and Sterner, Kirstin N. and Weckle, Amy and Sugalski, Amara B. and Pipes, Lenore and Gatti, Domenico L. and Mason, Christopher E. and Sherwood, Chet C. and Hof, Patrick R. and Kuzawa, Christopher W. and Grossman, Lawrence I. and Goodman, Morris and Wildman, Derek E. and Kuhn, DN David N and Dillon, NL and Innes, DJ and Wu, LS and Krishnakumar, Raga and Chen, Amy F and Pantovich, Marisol G and Danial, Muhammad and Parchem, Ronald J and Labosky, Patricia A and Blelloch, Robert and Jin, M and Bothfeld, W and Austin, S and Sato, TK and Reau, A La and Huth, Troy J and Place, Sean P and Horton, Melissa A and Oliver, Randy and Newton, ILG Irene L G and Gulia-Nuss, Monika and Nuss, Andrew B and Meyer, Jason M and Sonenshine, Daniel E and Roe, R Michael and Waterhouse, Robert M and Sattelle, David B and de la Fuente, Jose and Ribeiro, Jose M and Megy, Karine and Thimmapuram, Jyothi and Miller, Jason R and Walenz, Brian P and Koren, Sergey and Hostetler, Jessica B and Thiagarajan, Mathangi and Joardar, Vinita S and Hannick, Linda I and Bidwell, Shelby and Hammond, Martin P and Young, Sarah and Zeng, Qiandong and Abrudan, Jenica L and Almeida, Francisca C and Ayllon, Nieves and Bhide, Ketaki and Bissinger, Brooke W and Bonzon-Kulichenko, Elena and Buckingham, Steven D and Caffrey, Daniel R and Caimano, Melissa J and Croset, Vincent and Driscoll, Timothy and Gilbert, Donald and Gillespie, Joseph J and Giraldo-Calderon, Gloria I and Grabowski, Jeffrey M and Jiang, David and Khalil, Sayed M S and Kim, Donghun and Kocan, Katherine M and Koci, Juraj and Kuhn, Richard J and Kurtti, Timothy J and Lees, Kristin and Lang, Emma G and Kennedy, Ryan C and Kwon, Hyeogsun and Perera, Rushika and Qi, Yumin and Radolf, Justin D and Sakamoto, Joyce M and Sanchez-Gracia, Alejandro and Severo, Maiara S and Silverman, Neal and Simo, Ladislav and Tojo, Marta and Tornador, Cristian and Van Zee, Janice P and Vazquez, Jesus and Vieira, Filipe G and Villar, Margarita and Wespiser, Adam R and Yang, Yunlong and Zhu, Jiwei and Arensburger, Peter and Pietrantonio, Patricia V and Barker, Stephen C and Shao, Renfu and Zdobnov, Evgeny M and Hauser, Frank and Grimmelikhuijzen, Cornelis J P and Park, Yoonseong and Rozas, Julio and Benton, Richard and Pedra, Joao H F and Nelson, David R and Unger, Maria F and Tubio, Jose M C and Tu, Zhijian and Robertson, Hugh M and Shumway, Martin and Sutton, Granger and Wortman, Jennifer R and Lawson, Daniel and Wikel, Stephen K and Nene, Vishvanath M and Fraser, Claire M and Collins, Frank H and Birren, Bruce and Nelson, Karen E and Caler, Elisabet and Hill, Catherine A and Ghaffari, Noushin and Sanchez-Flores, Alejandro and Doan, Ryan and Garcia-Orozco, Karina D. and Chen, Patricia L. and Ochoa-Leyva, Adrian and Lopez-Zavala, Alonso A. and Carrasco, J. Salvador and Hong, Chris and Brieba, Luis G. and Rudiño-Piñera, Enrique and Blood, Philip D. Phillip and Sawyer, Jason E. and Johnson, Charles D. and Dindot, Scott V. and Sotelo-Mundo, Rogerio R. and Criscitiello, Michael F. and Gao, Kai and Tankovic, Anel and Zhang, Yujia Yuehua and Kusumoto, Hirofumi and Zhang, Junpeng Jin and Chen, Wenjuan and XiangWei, Wenshu and Shaulsky, Gil H. and Hu, Chun and Traynelis, Stephen F. and Yuan, Hongjie and Jiang, Yuwu and Fergus, Daniel J and Feng, Ni Y and Bass, Andrew H and Fergus, Daniel J and Bass, Andrew H and Duncan, Rebecca P and Feng, Honglin and Nguyen, Douglas M and Wilson, Alex C C and Darris, Carl E and Tyus, James E and Kelley, Gary and Ropelewski, Alexander J and Nicholas, Hugh B and Wang, Xiaofei and Nahashon, Samuel and Nahashon, Samuel and Couger, M. Brian and Pipes, Lenore and Squina, F and Boyd, Bret M. and Allen, Julie M. and Nguyen, Nam and Sweet, Andrew D. and Warnow, Tandy and Shapiro, Michael D. and Villa, Scott M. and Bush, Sarah E. and Clayton, Dale H. and Johnson, Kevin P. and Blood, Philip D. Phillip and Marcus, Shoshana and Schatz, Michael C. and Bahreini, Amir and Levine, Kevin and Santana-Santos, Lucas and Benos, Panayiotis V. and Wang, Peilu and Andersen, Courtney and Oesterreich, Steffi and Lee, Adrian V. and Armstrong, Eric J. and Stillman, Jonathon H. and Arafat, Ahmed and Jing, Peng and Ma, Yuping and Pu, Miao and Nan, Gai and Fang, He and Chen, Chen and Fei, Yin and Almada, Amalia A. and Tarrant, Ann M.},
 editor = {Mothet, Jean-Pierre},
 doi = {10.1002/cne.23843},
 journal = {BMC genomics},
 number = {1}
}

In the Gulf of Maine, the copepod Calanus finmarchicus co-occurs with the neurotoxin-producing dinoflagellate, Alexandrium fundyense. The copepod is resistant to this toxic alga, but little is known about other effects. Gene expression profiles were used to investigate the physiological response of females feeding for two and five days on a control diet or a diet containing either a low or a high dose of A. fundyense. The physiological responses to the two experimental diets were similar, but changed between the time points. At 5-days the response was characterized by down-regulated genes involved in energy metabolism. Detoxification was not a major component of the response. Instead, genes involved in digestion were consistently regulated, suggesting that food assimilation may have been affected. Thus, predicted increases in the frequency of blooms of A. fundyense could affect C. finmarchicus populations by changing the individuals’ energy budget and reducing their ability to build lipid reserves.

@article{
 title = {Physiological effects of heat stress on Hawaiian picture-wing Drosophila: genome-wide expression patterns and stress-related traits},
 type = {article},
 year = {2015},
 websites = {http://conphys.oxfordjournals.org/content/3/1/cou062.short},
 id = {f69fb412-f3e9-3605-a307-3b750d0e5fc5},
 created = {2020-04-29T21:57:00.187Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:57:00.295Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Uy2015},
 private_publication = {false},
 bibtype = {article},
 author = {Uy, KL and LeDuc, R and Ganote, C},
 journal = {Conservation},
 keywords = {DvlFinal,PY4}
}

@article{
 title = {Expanding the catalog of cas genes with metagenomes},
 type = {article},
 year = {2014},
 pages = {2448–2459},
 volume = {42},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/24319142,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC3936711,http://nar.oxfordjournals.org/content/42/4/2448.short},
 month = {2},
 publisher = {Oxford University Press},
 id = {f039493c-9feb-3215-a0b1-82a5150f05c3},
 created = {2020-04-29T21:56:56.877Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.962Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Zhang2014},
 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.},
 bibtype = {article},
 author = {Zhang, Quan and Doak, TG Thomas G and Ye, Yuzhen},
 doi = {https://doi.org/10.1093/nar/gkt1262},
 journal = {Nucleic acids research},
 number = {4},
 keywords = {PY3}
}

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.

@article{
 title = {Unique Features of the Loblolly Pine (Pinus taeda L.) Megagenome Revealed Through Sequence Annotation},
 type = {article},
 year = {2014},
 keywords = {PY3},
 pages = {891-909},
 volume = {196},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/24653211,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC3948814,http://www.genetics.org/cgi/doi/10.1534/genetics.113.159996},
 month = {3},
 day = {1},
 id = {6745a60f-3d3d-37dc-912b-f2b706913558},
 created = {2020-04-29T21:56:57.810Z},
 accessed = {2017-08-31},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.890Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Wegrzyn2014},
 private_publication = {false},
 abstract = {The largest genus in the conifer family Pinaceae is Pinus, with over 100 species. The size and complexity of their genomes (∼20-40 Gb, 2n = 24) have delayed the arrival of a well-annotated reference sequence. In this study, we present the annotation of the first whole-genome shotgun assembly of loblolly pine (Pinus taeda L.), which comprises 20.1 Gb of sequence. The MAKER-P annotation pipeline combined evidence-based alignments and ab initio predictions to generate 50,172 gene models, of which 15,653 are classified as high confidence. Clustering these gene models with 13 other plant species resulted in 20,646 gene families, of which 1554 are predicted to be unique to conifers. Among the conifer gene families, 159 are composed exclusively of loblolly pine members. The gene models for loblolly pine have the highest median and mean intron lengths of 24 fully sequenced plant genomes. Conifer genomes are full of repetitive DNA, with the most significant contributions from long-terminal-repeat retrotransposons. In depth analysis of the tandem and interspersed repetitive content yielded a combined estimate of 82%.},
 bibtype = {article},
 author = {Wegrzyn, J. L. and Liechty, J. D. and Stevens, K. A. and Wu, L.-S. and Loopstra, C. A. and Vasquez-Gross, H. A. and Dougherty, W. M. and Lin, B. Y. and Zieve, J. J. and Martinez-Garcia, P. J. and Holt, C. and Yandell, M. and Zimin, A. V. and Yorke, J. A. and Crepeau, M. W. and Puiu, D. and Salzberg, S. L. and de Jong, P. J. and Mockaitis, K. and Main, D. and Langley, C. H. and Neale, D. B.},
 doi = {10.1534/genetics.113.159996},
 journal = {Genetics},
 number = {3}
}

The largest genus in the conifer family Pinaceae is Pinus, with over 100 species. The size and complexity of their genomes (∼20-40 Gb, 2n = 24) have delayed the arrival of a well-annotated reference sequence. In this study, we present the annotation of the first whole-genome shotgun assembly of loblolly pine (Pinus taeda L.), which comprises 20.1 Gb of sequence. The MAKER-P annotation pipeline combined evidence-based alignments and ab initio predictions to generate 50,172 gene models, of which 15,653 are classified as high confidence. Clustering these gene models with 13 other plant species resulted in 20,646 gene families, of which 1554 are predicted to be unique to conifers. Among the conifer gene families, 159 are composed exclusively of loblolly pine members. The gene models for loblolly pine have the highest median and mean intron lengths of 24 fully sequenced plant genomes. Conifer genomes are full of repetitive DNA, with the most significant contributions from long-terminal-repeat retrotransposons. In depth analysis of the tandem and interspersed repetitive content yielded a combined estimate of 82%.

@article{
 title = {The C-score: a Bayesian framework to sharply improve proteoform scoring in high-throughput top down proteomics},
 type = {article},
 year = {2014},
 websites = {http://pubs.acs.org/doi/abs/10.1021/pr401277r},
 id = {353cbe16-9753-3654-9b57-1dbe94167aaa},
 created = {2020-04-29T21:56:58.134Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.210Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {LeDuc2014},
 private_publication = {false},
 bibtype = {article},
 author = {LeDuc, RD and Fellers, RT and Early, BP and Greer, JB},
 journal = {Journal of proteome},
 keywords = {PY3}
}

@article{
 title = {Insights into three whole-genome duplications gleaned from the Paramecium caudatum genome sequence},
 type = {article},
 year = {2014},
 websites = {http://www.genetics.org/content/197/4/1417.short},
 id = {a5b0134e-596c-3b51-b411-f56b85450a14},
 created = {2020-04-29T21:56:58.416Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.470Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {McGrath2014a},
 private_publication = {false},
 bibtype = {article},
 author = {McGrath, CL and Gout, JF and Doak, TG and Yanagi, A},
 journal = {Genetics},
 keywords = {PY3}
}

@article{
 title = {Differential retention and divergent resolution of duplicate genes following whole-genome duplication},
 type = {article},
 year = {2014},
 websites = {http://genome.cshlp.org/content/24/10/1665.short},
 id = {e0bd80f7-2de3-328d-bf97-04d26d997446},
 created = {2020-04-29T21:56:58.424Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.500Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {McGrath2014},
 private_publication = {false},
 bibtype = {article},
 author = {McGrath, CL and Gout, JF and Johri, P and Doak, TG},
 journal = {Genome},
 keywords = {PY3}
}

@article{
 title = {Development of single nucleotide polymorphism (SNP) markers from the mango (Mangifera indica) transcriptome for mapping and estimation of genetic diversity},
 type = {article},
 year = {2014},
 websites = {http://www.actahort.org/books/1111/1111_45.htm},
 id = {bb08291a-fc79-31d3-ab8c-e25007dee1e5},
 created = {2020-04-29T21:56:58.460Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.554Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Kuhn2014},
 private_publication = {false},
 bibtype = {article},
 author = {Kuhn, DN and Dillon, NL and Innes, DJ and Wu, LS},
 journal = {Lives, Livelihoods and …},
 keywords = {PY3}
}

@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},
 websites = {http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0088589},
 id = {ae8479f1-0c74-31a5-9f78-387b3d872db6},
 created = {2020-04-29T21:56:58.535Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.627Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Lenz2014},
 private_publication = {false},
 bibtype = {article},
 author = {Lenz, PH and Roncalli, V and Hassett, RP and Wu, LS and Cieslak, MC},
 journal = {PloS one},
 keywords = {PY3}
}

@article{
 title = {Diversity and dynamics of the Drosophila transcriptome},
 type = {article},
 year = {2014},
 pages = {393-399},
 volume = {512},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/24670639,http://www.pubmedcentral.nih.gov/articlerender.fcgi?artid=PMC4152413,http://www.nature.com/doifinder/10.1038/nature12962},
 month = {3},
 day = {16},
 id = {36b7a308-f0d3-3c90-9e7d-1ebe6a9141ca},
 created = {2020-04-29T21:56:59.700Z},
 accessed = {2017-08-31},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.797Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Brown2014},
 private_publication = {false},
 abstract = {Animal transcriptomes are dynamic, with each cell type, tissue and organ system expressing an ensemble of transcript isoforms that give rise to substantial diversity. Here we have identified new genes, transcripts and proteins using poly(A)+ RNA sequencing from Drosophila melanogaster in cultured cell lines, dissected organ systems and under environmental perturbations. We found that a small set of mostly neural-specific genes has the potential to encode thousands of transcripts each through extensive alternative promoter usage and RNA splicing. The magnitudes of splicing changes are larger between tissues than between developmental stages, and most sex-specific splicing is gonad-specific. Gonads express hundreds of previously unknown coding and long non-coding RNAs (lncRNAs), some of which are antisense to protein-coding genes and produce short regulatory RNAs. Furthermore, previously identified pervasive intergenic transcription occurs primarily within newly identified introns. The fly transcriptome is substantially more complex than previously recognized, with this complexity arising from combinatorial usage of promoters, splice sites and polyadenylation sites.},
 bibtype = {article},
 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 Maria and Wan, Kenneth H. and Yu, Charles and Zhang, Dayu and Carlson, Joseph W. and Cherbas, Lucy and Eads, Brian D. and Miller, David and Mockaitis, Keithanne and Roberts, Johnny and Davis, Carrie A. and Frise, Erwin and Hammonds, Ann S. and Olson, Sara and Shenker, Sol and Sturgill, David and Samsonova, Anastasia A. and Weiszmann, Richard and Robinson, Garret and Hernandez, Juan and Andrews, Justen and Bickel, Peter J. and Carninci, Piero and Cherbas, Peter and Gingeras, Thomas R. and Hoskins, Roger A. and Kaufman, Thomas C. and Lai, Eric C. and Oliver, Brian and Perrimon, Norbert and Graveley, Brenton R. and Celniker, Susan E.},
 doi = {10.1038/nature12962},
 journal = {Nature},
 number = {7515},
 keywords = {PY3}
}

Animal transcriptomes are dynamic, with each cell type, tissue and organ system expressing an ensemble of transcript isoforms that give rise to substantial diversity. Here we have identified new genes, transcripts and proteins using poly(A)+ RNA sequencing from Drosophila melanogaster in cultured cell lines, dissected organ systems and under environmental perturbations. We found that a small set of mostly neural-specific genes has the potential to encode thousands of transcripts each through extensive alternative promoter usage and RNA splicing. The magnitudes of splicing changes are larger between tissues than between developmental stages, and most sex-specific splicing is gonad-specific. Gonads express hundreds of previously unknown coding and long non-coding RNAs (lncRNAs), some of which are antisense to protein-coding genes and produce short regulatory RNAs. Furthermore, previously identified pervasive intergenic transcription occurs primarily within newly identified introns. The fly transcriptome is substantially more complex than previously recognized, with this complexity arising from combinatorial usage of promoters, splice sites and polyadenylation sites.

@article{
 title = {Leveraging the national cyberinfrastructure for biomedical research},
 type = {article},
 year = {2014},
 websites = {http://jamia.oxfordjournals.org/content/21/2/195.short},
 id = {bfafd652-05ff-3f58-a92a-5dc1e4ad07ec},
 created = {2020-04-29T21:56:59.822Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.871Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {LeDuc2014a},
 private_publication = {false},
 bibtype = {article},
 author = {LeDuc, R and Vaughn, M and Fonner, JM},
 journal = {Journal of the},
 keywords = {PY3}
}

@article{
 title = {The architecture of a scrambled genome reveals massive levels of genomic rearrangement during development},
 type = {article},
 year = {2014},
 websites = {http://www.sciencedirect.com/science/article/pii/S0092867414009842},
 id = {af600bcf-bb00-3f13-8809-72f27c469c09},
 created = {2020-04-29T21:56:59.963Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:57:00.038Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Chen2014},
 private_publication = {false},
 bibtype = {article},
 author = {Chen, X and Bracht, JR and Goldman, AD and Dolzhenko, E},
 journal = {Cell},
 keywords = {PY3}
}

@inproceedings{
 title = {National Center for Genome Analysis Support Leverages XSEDE to Support Life Science Research},
 type = {inproceedings},
 year = {2013},
 keywords = {PY2},
 pages = {13:1--13:7},
 websites = {http://dl.acm.org/citation.cfm?id=2484790,http://doi.acm.org/10.1145/2484762.2484790,https://scholarworks.iu.edu/dspace/handle/2022/16402},
 publisher = {ACM},
 city = {New York, NY, USA},
 series = {XSEDE '13},
 id = {723e1829-fcf7-3dd8-b65a-f985d1cc995f},
 created = {2020-04-29T21:56:56.946Z},
 accessed = {2017-05-12},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.059Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {LeDuc:2013:NCG:2484762.2484790},
 source_type = {inproceedings},
 private_publication = {false},
 abstract = {To be presented at XSEDE Conference 2013, San Diego, CA},
 bibtype = {inproceedings},
 author = {LeDuc, Richard D. RD Richard D and Wu, LS Le-Shin and Ganote, Carrie L. and Doak, Thomas and Blood, Philip D. PD Philip D and Vaughn, Matthew and Wu, LS Le-Shin and Blood, Philip D. PD Philip D and Ganote, Carrie L. and Vaughn, Matthew},
 doi = {10.1145/2484762.2484790},
 booktitle = {Proceedings of the Conference on Extreme Science and Engineering Discovery Environment: Gateway to Discovery}
}

To be presented at XSEDE Conference 2013, San Diego, CA

@article{
 title = {The Oxytricha trifallax Macronuclear Genome: A Complex Eukaryotic Genome with 16,000 Tiny Chromosomes},
 type = {article},
 year = {2013},
 pages = {e1001473},
 volume = {11},
 websites = {http://dx.plos.org/10.1371/journal.pbio.1001473},
 month = {1},
 publisher = {Public Library of Science},
 day = {29},
 id = {43a4aab1-8318-3935-baaf-556887fa587c},
 created = {2020-04-29T21:56:57.839Z},
 accessed = {2017-08-31},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.948Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Swart2013},
 private_publication = {false},
 bibtype = {article},
 author = {Swart, Estienne C. and Bracht, John R. and Magrini, Vincent and Minx, Patrick and Chen, Xiao and Zhou, Yi and Khurana, Jaspreet S. and Goldman, Aaron D. and Nowacki, Mariusz and Schotanus, Klaas and Jung, Seolkyoung and Fulton, Robert S. and Ly, Amy and McGrath, Sean and Haub, Kevin and Wiggins, Jessica L. and Storton, Donna and Matese, John C. and Parsons, Lance and Chang, Wei-Jen and Bowen, Michael S. and Stover, Nicholas A. and Jones, Thomas A. and Eddy, Sean R. and Herrick, Glenn A. and Doak, Thomas G. and Wilson, Richard K. and Mardis, Elaine R. and Landweber, Laura F.},
 editor = {Eisen, Jonathan A.},
 doi = {10.1371/journal.pbio.1001473},
 journal = {PLoS Biology},
 number = {1},
 keywords = {PY2}
}

@article{
 title = {Polynucleobacter necessarius, a model for genome reduction in both free-living and symbiotic bacteria},
 type = {article},
 year = {2013},
 pages = {18590-18595},
 volume = {110},
 websites = {http://www.pnas.org/content/110/46/18590.abstract},
 month = {11},
 day = {12},
 id = {878a9b50-2a99-3809-913a-1dffb66e8916},
 created = {2020-04-29T21:56:57.901Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:57.979Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Boscaro2013a},
 source_type = {JOUR},
 notes = {10.1073/pnas.1316687110},
 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, Vittorio and Felletti, Michele and Vannini, Claudia and Ackerman, Matthew S and Chain, Patrick S G and Malfatti, Stephanie and Vergez, Lisa M and Shin, Maria and Doak, Thomas G and Lynch, Michael and Petroni, Giulio},
 journal = {Proceedings of the National Academy of Sciences},
 number = {46},
 keywords = {PY3}
}

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.

@article{
 title = {De novo transcript sequence reconstruction from RNA-seq using the Trinity platform for reference generation and analysis},
 type = {article},
 year = {2013},
 volume = {8},
 websites = {https://doi.org/10.1038/nprot.2013.084},
 id = {2803c5b4-b0bb-3a5e-854c-a7f047c18096},
 created = {2020-04-29T21:56:59.165Z},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.302Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 citation_key = {Haas2013},
 source_type = {article},
 private_publication = {false},
 bibtype = {article},
 author = {Haas, Brian J and Papanicolaou, Alexie and Yassour, Moran and Grabherr, Manfred and Blood, Philip D and Bowden, Joshua and Couger, Matthew Brian and Eccles, David and Li, Bo and Lieber, Matthias and Matthew D MacManes, Michael Ott and Orvis, Joshua and Pochet, Nathalie and Strozzi, Francesco and Weeks, Nathan and Westerman, Rick and William, Thomas and Dewey, Colin N and Henschel, Robert and LeDuc, Richard D and Friedman, Nir and Regev, Aviv},
 doi = {10.1038/nprot.2013.084},
 journal = {Nat Protocols},
 keywords = {PY2}
}

@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},
 pages = {117-135},
 volume = {187},
 websites = {http://www.ncbi.nlm.nih.gov/pubmed/23578900,http://linkinghub.elsevier.com/retrieve/pii/S0016648013001500},
 month = {6},
 day = {15},
 id = {b87ac3df-f2f3-31b2-b528-1cb4732be899},
 created = {2020-04-29T21:56:59.737Z},
 accessed = {2017-08-31},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:59.831Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Christie2013},
 private_publication = {false},
 abstract = {The copepod Calanus finmarchicus is the most abundant zooplankton species in the North Atlantic. While the life history of this crustacean is well studied, little is known about its peptidergic signaling systems despite the fact that these pathways are undoubtedly important components of its physiological/behavioral control systems. Here we have generated and used a de novo assembled transcriptome for C. finmarchicus (206,041 sequences in total) to identify peptide precursor proteins and receptors. Using known protein queries, 34 transcripts encoding peptide preprohormones and 18 encoding peptide receptors were identified. Using a combination of online software programs and homology to known arthropod isoforms, 148 mature peptides were predicted from the deduced precursors, including members of the allatostatin-A, allatostatin-B, allatostatin-C, bursicon, crustacean cardioactive peptide (CCAP), crustacean hyperglycemic hormone, diuretic hormone 31 (DH31), diuretic hormone 44 (DH44), FMRFamide-like peptide (myosuppressin, neuropeptide F [NPF] and extended FL/IRFamide subfamilies), leucokinin, neuroparsin, orcokinin, orcomyotropin, periviscerokinin, RYamide and tachykinin-related peptide (TRP) families. The identified receptors included ones for allatostatin-A, allatostatin-C, bursicon, CCAP, DH31, DH44, ecdysis-triggering hormone, NPF, short NPF, FMRFamide, insulin-like peptide, leucokinin, periviscerokinin, pigment dispersing hormone, and TRP. Developmental profiling of the identified transcripts in embryos, early nauplii, late nauplii, early copepodites, late copepodites, and adult females was also undertaken, with all showing the highest expression levels in the naupliar and copepodite stages. Collectively, these data radically expand the catalog of known C. finmarchicus peptidergic signaling proteins and provide a foundation for experiments directed at understanding the physiological roles served by them in this species.},
 bibtype = {article},
 author = {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},
 keywords = {PY2}
}

The copepod Calanus finmarchicus is the most abundant zooplankton species in the North Atlantic. While the life history of this crustacean is well studied, little is known about its peptidergic signaling systems despite the fact that these pathways are undoubtedly important components of its physiological/behavioral control systems. Here we have generated and used a de novo assembled transcriptome for C. finmarchicus (206,041 sequences in total) to identify peptide precursor proteins and receptors. Using known protein queries, 34 transcripts encoding peptide preprohormones and 18 encoding peptide receptors were identified. Using a combination of online software programs and homology to known arthropod isoforms, 148 mature peptides were predicted from the deduced precursors, including members of the allatostatin-A, allatostatin-B, allatostatin-C, bursicon, crustacean cardioactive peptide (CCAP), crustacean hyperglycemic hormone, diuretic hormone 31 (DH31), diuretic hormone 44 (DH44), FMRFamide-like peptide (myosuppressin, neuropeptide F [NPF] and extended FL/IRFamide subfamilies), leucokinin, neuroparsin, orcokinin, orcomyotropin, periviscerokinin, RYamide and tachykinin-related peptide (TRP) families. The identified receptors included ones for allatostatin-A, allatostatin-C, bursicon, CCAP, DH31, DH44, ecdysis-triggering hormone, NPF, short NPF, FMRFamide, insulin-like peptide, leucokinin, periviscerokinin, pigment dispersing hormone, and TRP. Developmental profiling of the identified transcripts in embryos, early nauplii, late nauplii, early copepodites, late copepodites, and adult females was also undertaken, with all showing the highest expression levels in the naupliar and copepodite stages. Collectively, these data radically expand the catalog of known C. finmarchicus peptidergic signaling proteins and provide a foundation for experiments directed at understanding the physiological roles served by them in this species.

@article{
 title = {Diverse CRISPRs Evolving in Human Microbiomes},
 type = {article},
 year = {2012},
 pages = {e1002441},
 volume = {8},
 websites = {http://dx.plos.org/10.1371/journal.pgen.1002441},
 month = {6},
 publisher = {Public Library of Science},
 day = {13},
 id = {a658ab0a-d5a0-3744-8cc4-5390a19a5db9},
 created = {2020-04-29T21:56:56.831Z},
 accessed = {2018-08-10},
 file_attached = {true},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:56.939Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 private_publication = {false},
 abstract = {CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats) loci, together with cas (CRISPR–associated) genes, form the CRISPR/Cas adaptive immune system, a primary defense strategy that eubacteria and archaea mobilize against foreign nucleic acids, including phages and conjugative plasmids. Short spacer sequences separated by the repeats are derived from foreign DNA and direct interference to future infections. The availability of hundreds of shotgun metagenomic datasets from the Human Microbiome Project (HMP) enables us to explore the distribution and diversity of known CRISPRs in human-associated microbial communities and to discover new CRISPRs. We propose a targeted assembly strategy to reconstruct CRISPR arrays, which whole-metagenome assemblies fail to identify. For each known CRISPR type (identified from reference genomes), we use its direct repeat consensus sequence to recruit reads from each HMP dataset and then assemble the recruited reads into CRISPR loci; the unique spacer sequences can then be extracted for analysis. We also identified novel CRISPRs or new CRISPR variants in contigs from whole-metagenome assemblies and used targeted assembly to more comprehensively identify these CRISPRs across samples. We observed that the distributions of CRISPRs (including 64 known and 86 novel ones) are largely body-site specific. We provide detailed analysis of several CRISPR loci, including novel CRISPRs. For example, known streptococcal CRISPRs were identified in most oral microbiomes, totaling ∼8,000 unique spacers: samples resampled from the same individual and oral site shared the most spacers; different oral sites from the same individual shared significantly fewer, while different individuals had almost no common spacers, indicating the impact of subtle niche differences on the evolution of CRISPR defenses. We further demonstrate potential applications of CRISPRs to the tracing of rare species and the virus exposure of individuals. This work indicates the importance of effective identification and characterization of CRISPR loci to the study of the dynamic ecology of microbiomes.},
 bibtype = {article},
 author = {Rho, Mina and Wu, Yu-Wei and Tang, Haixu and Doak, Thomas G. and Ye, Yuzhen},
 editor = {Guttman, David S.},
 doi = {10.1371/journal.pgen.1002441},
 journal = {PLoS Genetics},
 number = {6},
 keywords = {PY1}
}

CRISPR (Clustered Regularly Interspaced Short Palindromic Repeats) loci, together with cas (CRISPR–associated) genes, form the CRISPR/Cas adaptive immune system, a primary defense strategy that eubacteria and archaea mobilize against foreign nucleic acids, including phages and conjugative plasmids. Short spacer sequences separated by the repeats are derived from foreign DNA and direct interference to future infections. The availability of hundreds of shotgun metagenomic datasets from the Human Microbiome Project (HMP) enables us to explore the distribution and diversity of known CRISPRs in human-associated microbial communities and to discover new CRISPRs. We propose a targeted assembly strategy to reconstruct CRISPR arrays, which whole-metagenome assemblies fail to identify. For each known CRISPR type (identified from reference genomes), we use its direct repeat consensus sequence to recruit reads from each HMP dataset and then assemble the recruited reads into CRISPR loci; the unique spacer sequences can then be extracted for analysis. We also identified novel CRISPRs or new CRISPR variants in contigs from whole-metagenome assemblies and used targeted assembly to more comprehensively identify these CRISPRs across samples. We observed that the distributions of CRISPRs (including 64 known and 86 novel ones) are largely body-site specific. We provide detailed analysis of several CRISPR loci, including novel CRISPRs. For example, known streptococcal CRISPRs were identified in most oral microbiomes, totaling ∼8,000 unique spacers: samples resampled from the same individual and oral site shared the most spacers; different oral sites from the same individual shared significantly fewer, while different individuals had almost no common spacers, indicating the impact of subtle niche differences on the evolution of CRISPR defenses. We further demonstrate potential applications of CRISPRs to the tracing of rare species and the virus exposure of individuals. This work indicates the importance of effective identification and characterization of CRISPR loci to the study of the dynamic ecology of microbiomes.

@article{
 title = {Trinity RNA-Seq assembler performance optimization},
 type = {article},
 year = {2012},
 websites = {http://dl.acm.org/citation.cfm?id=2335842},
 id = {fdc5db01-df3e-3232-8410-659f0d852bac},
 created = {2020-04-29T21:56:58.108Z},
 accessed = {2017-05-12},
 file_attached = {false},
 profile_id = {5db6d3e7-562f-3ec2-a249-16ecf1e747e4},
 group_id = {e69a8af9-b9f0-3719-92d7-c9e03d79c259},
 last_modified = {2020-04-29T21:56:58.231Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 citation_key = {Henschel2012},
 private_publication = {false},
 bibtype = {article},
 author = {Henschel, R and Lieber, M and Wu, LS and Nista, PM},
 journal = {Proceedings of the 1st},
 keywords = {PY1}
}