@article{novichkov_2012,

title = {RegPrecise web services interface: programmatic access to the transcriptional regulatory interactions in bacteria reconstructed by comparative genomics.},

author = {Pavel S Novichkov and Thomas S Brettin and Elena S Novichkova and Paramvir S Dehal and Adam P Arkin and Inna Dubchak and Dmitry A Rodionov},

url = {http://dx.doi.org/10.1093/nar/gks562},

doi = {10.1093/nar/gks562},

year  = {2012},

date = {2012-07-01},

urldate = {2021-05-25},

journal = {Nucleic Acids Research},

volume = {40},

number = {Web Server issue},

pages = {W604-8},

abstract = {Web services application programming interface (API) was developed to provide a programmatic access to the regulatory interactions accumulated in the RegPrecise database (http://regprecise.lbl.gov), a core resource on transcriptional regulation for the microbial domain of the Department of Energy (DOE) Systems Biology Knowledgebase. RegPrecise captures and visualize regulogs, sets of genes controlled by orthologous regulators in several closely related bacterial genomes, that were reconstructed by comparative genomics. The current release of RegPrecise 2.0 includes textgreater1400 regulogs controlled either by protein transcription factors or by conserved ribonucleic acid regulatory motifs in textgreater250 genomes from 24 taxonomic groups of bacteria. The reference regulons accumulated in RegPrecise can serve as a basis for automatic annotation of regulatory interactions in newly sequenced genomes. The developed API provides an efficient access to the RegPrecise data by a comprehensive set of 14 web service resources. The RegPrecise web services API is freely accessible at http://regprecise.lbl.gov/RegPrecise/services.jsp with no login requirements.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{clark_2012,

title = {Transcriptomic and proteomic analyses of Desulfovibrio vulgaris biofilms: carbon and energy flow contribute to the distinct biofilm growth state.},

author = {Melinda E Clark and Zhili He and Alyssa M Redding and Marcin P Joachimiak and Jay D Keasling and Jizhong Z Zhou and Adam P Arkin and Aindrila Mukhopadhyay and Matthew W Fields},

url = {http://dx.doi.org/10.1186/1471-2164-13-138},

doi = {10.1186/1471-2164-13-138},

year  = {2012},

date = {2012-04-16},

urldate = {2021-05-25},

journal = {BMC Genomics},

volume = {13},

pages = {138},

abstract = {BACKGROUND: Desulfovibrio vulgaris Hildenborough is a sulfate-reducing bacterium (SRB) that is intensively studied in the context of metal corrosion and heavy-metal bioremediation, and SRB populations are commonly observed in pipe and subsurface environments as surface-associated populations. In order to elucidate physiological changes associated with biofilm growth at both the transcript and protein level, transcriptomic and proteomic analyses were done on mature biofilm cells and compared to both batch and reactor planktonic populations. The biofilms were cultivated with lactate and sulfate in a continuously fed biofilm reactor, and compared to both batch and reactor planktonic populations. RESULTS: The functional genomic analysis demonstrated that biofilm cells were different compared to planktonic cells, and the majority of altered abundances for genes and proteins were annotated as hypothetical (unknown function), energy conservation, amino acid metabolism, and signal transduction. Genes and proteins that showed similar trends in detected levels were particularly involved in energy conservation such as increases in an annotated ech hydrogenase, formate dehydrogenase, pyruvate:ferredoxin oxidoreductase, and rnf oxidoreductase, and the biofilm cells had elevated formate dehydrogenase activity. Several other hydrogenases and formate dehydrogenases also showed an increased protein level, while decreased transcript and protein levels were observed for putative coo hydrogenase as well as a lactate permease and hyp hydrogenases for biofilm cells. Genes annotated for amino acid synthesis and nitrogen utilization were also predominant changers within the biofilm state. Ribosomal transcripts and proteins were notably decreased within the biofilm cells compared to exponential-phase cells but were not as low as levels observed in planktonic, stationary-phase cells. Several putative, extracellular proteins (DVU1012, 1545) were also detected in the extracellular fraction from biofilm cells. CONCLUSIONS: Even though both the planktonic and biofilm cells were oxidizing lactate and reducing sulfate, the biofilm cells were physiologically distinct compared to planktonic growth states due to altered abundances of genes/proteins involved in carbon/energy flow and extracellular structures. In addition, average expression values for multiple rRNA transcripts and respiratory activity measurements indicated that biofilm cells were metabolically more similar to exponential-phase cells although biofilm cells are structured differently. The characterization of physiological advantages and constraints of the biofilm growth state for sulfate-reducing bacteria will provide insight into bioremediation applications as well as microbially-induced metal corrosion.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{mosher_2012,

title = {Microbial community succession during lactate amendment and electron acceptor limitation reveals a predominance of metal-reducing Pelosinus spp.},

author = {Jennifer J Mosher and Tommy J Phelps and Mircea Podar and Richard A Hurt and James H Campbell and Meghan M Drake and James G Moberly and Christopher W Schadt and Steven D Brown and Terry C Hazen and Adam P Arkin and Anthony V Palumbo and Boris A Faybishenko and Dwayne A Elias},

url = {http://dx.doi.org/10.1128/AEM.07165-11},

doi = {10.1128/AEM.07165-11},

year  = {2012},

date = {2012-04-01},

urldate = {2021-05-25},

journal = {Applied and Environmental Microbiology},

volume = {78},

number = {7},

pages = {2082-2091},

abstract = {The determination of the success of in situ bioremediation strategies is complex. By using controlled laboratory conditions, the influence of individual variables, such as U(VI), Cr(VI), and electron donors and acceptors on community structure, dynamics, and the metal-reducing potential can be studied. Triplicate anaerobic, continuous-flow reactors were inoculated with Cr(VI)-contaminated groundwater from the Hanford, WA, 100-H area, amended with lactate, and incubated for 95 days to obtain stable, enriched communities. The reactors were kept anaerobic with N(2) gas (9 ml/min) flushing the headspace and were fed a defined medium amended with 30 mM lactate and 0.05 mM sulfate with a 48-h generation time. The resultant diversity decreased from 63 genera within 12 phyla to 11 bacterial genera (from 3 phyla) and 2 archaeal genera (from 1 phylum). Final communities were dominated by Pelosinus spp. and to a lesser degree, Acetobacterium spp., with low levels of other organisms, including methanogens. Four new strains of Pelosinus were isolated, with 3 strains being capable of Cr(VI) reduction while one also reduced U(VI). Under limited sulfate, it appeared that the sulfate reducers, including Desulfovibrio spp., were outcompeted. These results suggest that during times of electron acceptor limitation in situ, organisms such as Pelosinus spp. may outcompete the more-well-studied organisms while maintaining overall metal reduction rates and extents. Finally, lab-scale simulations can test new strategies on a smaller scale while facilitating community member isolation, so that a deeper understanding of community metabolism can be revealed.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{zhou_2012,

title = {Functional characterization of Crp/Fnr-type global transcriptional regulators in Desulfovibrio vulgaris Hildenborough.},

author = {Aifen Zhou and Yunyu I Chen and Grant M Zane and Zhili He and Christopher L Hemme and Marcin P Joachimiak and Jason K Baumohl and Qiang He and Matthew W Fields and Adam P Arkin and Judy D Wall and Terry C Hazen and Jizhong Zhou},

url = {http://dx.doi.org/10.1128/AEM.05666-11},

doi = {10.1128/AEM.05666-11},

year  = {2012},

date = {2012-02-01},

urldate = {2021-05-25},

journal = {Applied and Environmental Microbiology},

volume = {78},

number = {4},

pages = {1168-1177},

abstract = {Crp/Fnr-type global transcriptional regulators regulate various metabolic pathways in bacteria and typically function in response to environmental changes. However, little is known about the function of four annotated Crp/Fnr homologs (DVU0379, DVU2097, DVU2547, and DVU3111) in Desulfovibrio vulgaris Hildenborough. A systematic study using bioinformatic, transcriptomic, genetic, and physiological approaches was conducted to characterize their roles in stress responses. Similar growth phenotypes were observed for the crp/fnr deletion mutants under multiple stress conditions. Nevertheless, the idea of distinct functions of Crp/Fnr-type regulators in stress responses was supported by phylogeny, gene transcription changes, fitness changes, and physiological differences. The four D. vulgaris Crp/Fnr homologs are localized in three subfamilies (HcpR, CooA, and cc). The crp/fnr knockout mutants were well separated by transcriptional profiling using detrended correspondence analysis (DCA), and more genes significantly changed in expression in a DeltaDVU3111 mutant (JW9013) than in the other three paralogs. In fitness studies, strain JW9013 showed the lowest fitness under standard growth conditions (i.e., sulfate reduction) and the highest fitness under NaCl or chromate stress conditions; better fitness was observed for a DeltaDVU2547 mutant (JW9011) under nitrite stress conditions and a DeltaDVU2097 mutant (JW9009) under air stress conditions. A higher Cr(VI) reduction rate was observed for strain JW9013 in experiments with washed cells. These results suggested that the four Crp/Fnr-type global regulators play distinct roles in stress responses of D. vulgaris. DVU3111 is implicated in responses to NaCl and chromate stresses, DVU2547 in nitrite stress responses, and DVU2097 in air stress responses.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{deutschbauer_2011,

title = {Evidence-based annotation of gene function in Shewanella oneidensis MR-1 using genome-wide fitness profiling across 121 conditions.},

author = {Adam Deutschbauer and Morgan N Price and Kelly M Wetmore and Wenjun Shao and Jason K Baumohl and Zhuchen Xu and Michelle Nguyen and Raquel Tamse and Ronald W Davis and Adam P Arkin},

url = {http://dx.doi.org/10.1371/journal.pgen.1002385},

doi = {10.1371/journal.pgen.1002385},

year  = {2011},

date = {2011-11-17},

urldate = {2021-06-04},

journal = {PLoS Genetics},

volume = {7},

number = {11},

pages = {e1002385},

abstract = {Most genes in bacteria are experimentally uncharacterized and cannot be annotated with a specific function. Given the great diversity of bacteria and the ease of genome sequencing, high-throughput approaches to identify gene function experimentally are needed. Here, we use pools of tagged transposon mutants in the metal-reducing bacterium Shewanella oneidensis MR-1 to probe the mutant fitness of 3,355 genes in 121 diverse conditions including different growth substrates, alternative electron acceptors, stresses, and motility. We find that 2,350 genes have a pattern of fitness that is significantly different from random and 1,230 of these genes (37% of our total assayed genes) have enough signal to show strong biological correlations. We find that genes in all functional categories have phenotypes, including hundreds of hypotheticals, and that potentially redundant genes (over 50% amino acid identity to another gene in the genome) are also likely to have distinct phenotypes. Using fitness patterns, we were able to propose specific molecular functions for 40 genes or operons that lacked specific annotations or had incomplete annotations. In one example, we demonstrate that the previously hypothetical gene SO_3749 encodes a functional acetylornithine deacetylase, thus filling a missing step in S. oneidensis metabolism. Additionally, we demonstrate that the orphan histidine kinase SO_2742 and orphan response regulator SO_2648 form a signal transduction pathway that activates expression of acetyl-CoA synthase and is required for S. oneidensis to grow on acetate as a carbon source. Lastly, we demonstrate that gene expression and mutant fitness are poorly correlated and that mutant fitness generates more confident predictions of gene function than does gene expression. The approach described here can be applied generally to create large-scale gene-phenotype maps for evidence-based annotation of gene function in prokaryotes.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{jajamovich_2011,

title = {Bayesian multiple-instance motif discovery with BAMBI: inference of recombinase and transcription factor binding sites.},

author = {Guido H Jajamovich and Xiaodong Wang and Adam P Arkin and Michael S Samoilov},

url = {http://dx.doi.org/10.1093/nar/gkr745},

doi = {10.1093/nar/gkr745},

year  = {2011},

date = {2011-11-01},

urldate = {2021-06-04},

journal = {Nucleic Acids Research},

volume = {39},

number = {21},

pages = {e146},

abstract = {Finding conserved motifs in genomic sequences represents one of essential bioinformatic problems. However, achieving high discovery performance without imposing substantial auxiliary constraints on possible motif features remains a key algorithmic challenge. This work describes BAMBI-a sequential Monte Carlo motif-identification algorithm, which is based on a position weight matrix model that does not require additional constraints and is able to estimate such motif properties as length, logo, number of instances and their locations solely on the basis of primary nucleotide sequence data. Furthermore, should biologically meaningful information about motif attributes be available, BAMBI takes advantage of this knowledge to further refine the discovery results. In practical applications, we show that the proposed approach can be used to find sites of such diverse DNA-binding molecules as the cAMP receptor protein (CRP) and Din-family site-specific serine recombinases. Results obtained by BAMBI in these and other settings demonstrate better statistical performance than any of the four widely-used profile-based motif discovery methods: MEME, BioProspector with BioOptimizer, SeSiMCMC and Motif Sampler as measured by the nucleotide-level correlation coefficient. Additionally, in the case of Din-family recombinase target site discovery, the BAMBI-inferred motif is found to be the only one functionally accurate from the underlying biochemical mechanism standpoint. C++ and Matlab code is available at http://www.ee.columbia.edu/~guido/BAMBI or http://genomics.lbl.gov/BAMBI/.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{price_2011,

title = {Evidence-based annotation of transcripts and proteins in the sulfate-reducing bacterium Desulfovibrio vulgaris Hildenborough.},

author = {Morgan N Price and Adam M Deutschbauer and Jennifer V Kuehl and Haichuan Liu and Ewa H Witkowska and Adam P Arkin},

url = {http://dx.doi.org/10.1128/JB.05563-11},

doi = {10.1128/JB.05563-11},

year  = {2011},

date = {2011-10-01},

urldate = {2021-06-04},

journal = {Journal of Bacteriology},

volume = {193},

number = {20},

pages = {5716-5727},

abstract = {We used high-resolution tiling microarrays and 5' RNA sequencing to identify transcripts in Desulfovibrio vulgaris Hildenborough, a model sulfate-reducing bacterium. We identified the first nucleotide position for 1,124 transcripts, including 54 proteins with leaderless transcripts and another 72 genes for which a major transcript initiates within the upstream protein-coding gene, which confounds measurements of the upstream gene's expression. Sequence analysis of these promoters showed that D. vulgaris prefers -10 and -35 boxes different from those preferred by Escherichia coli. A total of 549 transcripts ended at intrinsic (rho-independent) terminators, but most of the other transcripts seemed to have variable ends. We found low-level antisense expression of most genes, and the 5' ends of these transcripts mapped to promoter-like sequences. Because antisense expression was reduced for highly expressed genes, we suspect that elongation of nonspecific antisense transcripts is suppressed by transcription of the sense strand. Finally, we combined the transcript results with comparative analysis and proteomics data to make 505 revisions to the original annotation of 3,531 proteins: we removed 255 (7.5%) proteins, changed 123 (3.6%) start codons, and added 127 (3.7%) proteins that had been missed. Tiling data had higher coverage than shotgun proteomics and hence led to most of the corrections, but many errors probably remain. Our data are available at http://genomics.lbl.gov/supplemental/DvHtranscripts2011/.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{liu_2011,

title = {Microfluidic fluorescence in situ hybridization and flow cytometry (μFlowFISH).},

author = {Peng Liu and Robert J Meagher and Yooli K Light and Suzan Yilmaz and Romy Chakraborty and Adam P Arkin and Terry C Hazen and Anup K Singh},

url = {http://dx.doi.org/10.1039/c1lc20151d},

doi = {10.1039/c1lc20151d},

year  = {2011},

date = {2011-08-21},

urldate = {2021-06-04},

journal = {Lab on A Chip},

volume = {11},

number = {16},

pages = {2673-2679},

abstract = {We describe an integrated microfluidic device (μFlowFISH) capable of performing 16S rRNA fluorescence in situ hybridization (FISH) followed by flow cytometric detection for identifying bacteria in natural microbial communities. The device was used for detection of species involved in bioremediation of Cr(vi) and other metals in groundwater samples from a highly-contaminated environmental site (Hanford, WA, USA). The μFlowFISH seamlessly integrates two components: a hybridization chamber formed between two photopolymerized membranes, where cells and probes are electrophoretically loaded, incubated and washed, and a downstream cross structure for electrokinetically focusing cells into a single-file flow for flow cytometry analysis. The device is capable of analyzing a wide variety of bacteria including aerobic, facultative and anaerobic bacteria and was initially tested and validated using cultured microbes, including Escherichia coli, as well as two strains isolated from Hanford site: Desulfovibrio vulgaris strain RCH1, and Pseudomonas sp.strain RCH2 that are involved in Cr(vi) reduction and immobilization. Combined labeling and detection efficiencies of 74-97% were observed in experiments with simple mixtures of cultured cells, confirming specific labeling. Results obtained were in excellent agreement with those obtained by conventional flow cytometry confirming the accuracy of μFlowFISH. Finally, the device was used for analyzing water samples collected on different dates from the Hanford site. We were able to monitor the numbers of Pseudomonas sp. with only 100-200 cells loaded into the microchip. The μFlowFISH approach provides an automated platform for quantitative detection of microbial cells from complex samples, and is ideally suited for analysis of precious samples with low cell numbers such as those found at extreme environmental niches, bioremediation sites, and the human microbiome. This journal is copyright The Royal Society of Chemistry 2011},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{price_2010,

title = {FastTree 2 — approximately maximum-likelihood trees for large alignments.},

author = {Morgan N Price and Paramvir S Dehal and Adam P Arkin},

url = {http://dx.doi.org/10.1371/journal.pone.0009490},

doi = {10.1371/journal.pone.0009490},

year  = {2010},

date = {2010-03-10},

urldate = {2017-12-18},

journal = {Plos One},

volume = {5},

number = {3},

pages = {e9490},

abstract = {BACKGROUND: We recently described FastTree, a tool for inferring phylogenies for alignments with up to hundreds of thousands of sequences. Here, we describe improvements to FastTree that improve its accuracy without sacrificing scalability. METHODOLOGY/PRINCIPAL FINDINGS: Where FastTree 1 used nearest-neighbor interchanges (NNIs) and the minimum-evolution criterion to improve the tree, FastTree 2 adds minimum-evolution subtree-pruning-regrafting (SPRs) and maximum-likelihood NNIs. FastTree 2 uses heuristics to restrict the search for better trees and estimates a rate of evolution for each site (the "CAT" approximation). Nevertheless, for both simulated and genuine alignments, FastTree 2 is slightly more accurate than a standard implementation of maximum-likelihood NNIs (PhyML 3 with default settings). Although FastTree 2 is not quite as accurate as methods that use maximum-likelihood SPRs, most of the splits that disagree are poorly supported, and for large alignments, FastTree 2 is 100-1,000 times faster. FastTree 2 inferred a topology and likelihood-based local support values for 237,882 distinct 16S ribosomal RNAs on a desktop computer in 22 hours and 5.8 gigabytes of memory. CONCLUSIONS/SIGNIFICANCE: FastTree 2 allows the inference of maximum-likelihood phylogenies for huge alignments. FastTree 2 is freely available at http://www.microbesonline.org/fasttree.},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}

@article{ning2020quantitative,

title = {A quantitative framework reveals the ecological drivers of grassland soil microbial community assembly in response to warming},

author = {Daliang Ning

, Mengting Yuan

, Linwei Wu

, Ya Zhang

, Xue Guo,

, Xishu Zhou , Yunfeng

Yang

, Adam P. Arkin

, Mary K. Firestone

, and Jizhong Zhou},

keywords = {enigma},

pubstate = {published},

tppubtype = {article}

}