@article{Ning2024,

title = {Environmental stress mediates groundwater microbial community assembly},

author = {Daliang Ning and Yajiao Wang and Yupeng Fan and Jianjun Wang and Joy D. Van Nostrand and Liyou Wu and Ping Zhang and Daniel J. Curtis and Renmao Tian and Lauren Lui and Terry C. Hazen and Eric J. Alm and Matthew W. Fields and Farris Poole and Michael W. W. Adams and Romy Chakraborty and David A. Stahl and Paul D. Adams and Adam P. Arkin and Zhili He and Jizhong Zhou},

doi = {10.1038/s41564-023-01573-x},

issn = {2058-5276},

year  = {2024},

date = {2024-02-00},

urldate = {2024-02-00},

journal = {Nat Microbiol},

volume = {9},

number = {2},

pages = {490--501},

publisher = {Springer Science and Business Media LLC},

keywords = {Applied Microbiology and Biotechnology, Cell Biology, enigma, Genetics, Immunology, Microbiology, Microbiology (medical)},

pubstate = {published},

tppubtype = {article}

}

@article{Park2023b,

title = {A bacterial sensor taxonomy across earth ecosystems for machine learning applications},

author = {Helen Park and Marcin P. Joachimiak and Sean P. Jungbluth and Ziming Yang and William J. Riehl and R. Shane Canon and Adam P. Arkin and Paramvir S. Dehal},

editor = {Babak Momeni},

doi = {10.1128/msystems.00026-23},

issn = {2379-5077},

year  = {2023},

date = {2023-12-11},

urldate = {2023-12-11},

journal = {mSystems},

publisher = {American Society for Microbiology},

abstract = {<jats:title>ABSTRACT</jats:title>

          <jats:p>

            Microbial communities have evolved to colonize all ecosystems of the planet, from the deep sea to the human gut. Microbes survive by sensing, responding, and adapting to immediate environmental cues. This process is driven by signal transduction proteins such as histidine kinases, which use their sensing domains to bind or otherwise detect environmental cues and “transduce” signals to adjust internal processes. We hypothesized that an ecosystem’s unique stimuli leave a sensor “fingerprint,” able to identify and shed insight on ecosystem conditions. To test this, we collected 20,712 publicly available metagenomes from

            <jats:italic>Host-associated</jats:italic>

            ,

            <jats:italic>Environmental</jats:italic>

            , and

            <jats:italic>Engineered</jats:italic>

            ecosystems across the globe. We extracted and clustered the collection’s nearly 18M unique sensory domains into 113,712 similar groupings with MMseqs2. We built gradient-boosted decision tree machine learning models and found we could classify the ecosystem type (accuracy: 87%) and predict the levels of different physical parameters (R2 score: 83%) using the sensor cluster abundance as features. Feature importance enables identification of the most predictive sensors to differentiate between ecosystems which can lead to mechanistic interpretations if the sensor domains are well annotated. To demonstrate this, a machine learning model was trained to predict patient’s disease state and used to identify domains related to oxygen sensing present in a healthy gut but missing in patients with abnormal conditions. Moreover, since 98.7% of identified sensor domains are uncharacterized, importance ranking can be used to prioritize sensors to determine what ecosystem function they may be sensing. Furthermore, these new predictive sensors can function as targets for novel sensor engineering with applications in biotechnology, ecosystem maintenance, and medicine.

          </jats:p>

          <jats:sec>

            <jats:title>IMPORTANCE</jats:title>

            <jats:p>Microbes infect, colonize, and proliferate due to their ability to sense and respond quickly to their surroundings. In this research, we extract the sensory proteins from a diverse range of environmental, engineered, and host-associated metagenomes. We trained machine learning classifiers using sensors as features such that it is possible to predict the ecosystem for a metagenome from its sensor profile. We use the optimized model’s feature importance to identify the most impactful and predictive sensors in different environments. We next use the sensor profile from human gut metagenomes to classify their disease states and explore which sensors can explain differences between diseases. The sensors most predictive of environmental labels here, most of which correspond to uncharacterized proteins, are a useful starting point for the discovery of important environment signals and the development of possible diagnostic interventions.</jats:p>

          </jats:sec>},

keywords = {Behavior and Systematics, Biochemistry, Computer Science Applications, Ecology, Evolution, Genetics, kbase, Microbiology, Modeling and Simulation, Molecular Biology, Physiology},

pubstate = {published},

tppubtype = {article}

}

@article{Price2022,

title = {Interactive Analysis of Functional Residues in Protein Families},

author = {Morgan N. Price and Adam P. Arkin},

editor = {Marnix Medema},

doi = {10.1128/msystems.00705-22},

issn = {2379-5077},

year  = {2022},

date = {2022-12-20},

journal = {mSystems},

volume = {7},

number = {6},

publisher = {American Society for Microbiology},

abstract = {For most microbes of interest, a genome sequence is available, but the function of its proteins is not known. Instead, proteins' functions are predicted from their similarity to other protein sequences.},

keywords = {Behavior and Systematics, Biochemistry, Computer Science Applications, Ecology, Evolution, Genetics, Microbiology, Modeling and Simulation, Molecular Biology, Physiology},

pubstate = {published},

tppubtype = {article}

}

@article{Wood-Charlson2022,

title = {Ten simple rules for getting and giving credit for data},

author = {Elisha M. Wood-Charlson and Zachary Crockett and Chris Erdmann and Adam P. Arkin and Carly B. Robinson},

editor = {Russell Schwartz},

doi = {10.1371/journal.pcbi.1010476},

issn = {1553-7358},

year  = {2022},

date = {2022-09-29},

journal = {PLoS Comput Biol},

volume = {18},

number = {9},

publisher = {Public Library of Science (PLoS)},

keywords = {Behavior and Systematics, Cellular and Molecular Neuroscience, Computational Theory and Mathematics, Ecology, Evolution, Genetics, Modeling and Simulation, Molecular Biology},

pubstate = {published},

tppubtype = {article}

}

@article{Goff2022,

title = {Complete Genome Sequence of Bacillus cereus Strain CPT56D-587-MTF, Isolated from a Nitrate- and Metal-Contaminated Subsurface Environment},

author = {Jennifer L. Goff and Lauren M. Lui and Torben N. Nielsen and Michael P. Thorgersen and Elizabeth G. Szink and John-Marc Chandonia and Farris L. Poole and Jizhong Zhou and Terry C. Hazen and Adam P. Arkin and Michael W. W. Adams},

editor = {Steven R. Gill},

doi = {10.1128/mra.00145-22},

issn = {2576-098X},

year  = {2022},

date = {2022-05-19},

journal = {Microbiol Resour Announc},

volume = {11},

number = {5},

publisher = {American Society for Microbiology},

abstract = {

            Bacillus cereus

            strain CPT56D-587-MTF was isolated from nitrate- and toxic metal-contaminated subsurface sediment at the Oak Ridge Reservation (ORR) (Oak Ridge, TN, USA). Here, we report the complete genome sequence of this strain to provide genomic insight into its strategies for survival at this mixed-waste site.

          },

keywords = {Genetics, Immunology and Microbiology (miscellaneous), Molecular Biology},

pubstate = {published},

tppubtype = {article}

}

@article{Price2022b,

title = {Filling gaps in bacterial catabolic pathways with computation and high-throughput genetics},

author = {Morgan N. Price and Adam M. Deutschbauer and Adam P. Arkin},

editor = {Bernhard O. Palsson},

doi = {10.1371/journal.pgen.1010156},

issn = {1553-7404},

year  = {2022},

date = {2022-04-13},

journal = {PLoS Genet},

volume = {18},

number = {4},

publisher = {Public Library of Science (PLoS)},

abstract = {To discover novel catabolic enzymes and transporters, we combined high-throughput genetic data from 29 bacteria with an automated tool to find gaps in their catabolic pathways. GapMind for carbon sources automatically annotates the uptake and catabolism of 62 compounds in bacterial and archaeal genomes. For the compounds that are utilized by the 29 bacteria, we systematically examined the gaps in GapMind’s predicted pathways, and we used the mutant fitness data to find additional genes that were involved in their utilization. We identified novel pathways or enzymes for the utilization of glucosamine, citrulline, myo-inositol, lactose, and phenylacetate, and we annotated 299 diverged enzymes and transporters. We also curated 125 proteins from published reports. For the 29 bacteria with genetic data, GapMind finds high-confidence paths for 85% of utilized carbon sources. In diverse bacteria and archaea, 38% of utilized carbon sources have high-confidence paths, which was improved from 27% by incorporating the fitness-based annotations and our curation. GapMind for carbon sources is available as a web server (http://papers.genomics.lbl.gov/carbon) and takes just 30 seconds for the typical genome.},

keywords = {Behavior and Systematics, Cancer Research, Ecology, Evolution, Genetics, Genetics (clinical), Molecular Biology},

pubstate = {published},

tppubtype = {article}

}

@article{Peng2022,

title = {Genomic Features and Pervasive Negative Selection in

            \textit{Rhodanobacter}

            Strains Isolated from Nitrate and Heavy Metal Contaminated Aquifer},

author = {Mu Peng and Dongyu Wang and Lauren M. Lui and Torben Nielsen and Renmao Tian and Megan L. Kempher and Xuanyu Tao and Chongle Pan and Romy Chakraborty and Adam M. Deutschbauer and Michael P. Thorgersen and Michael W. W. Adams and Matthew W. Fields and Terry C. Hazen and Adam P. Arkin and Aifen Zhou and Jizhong Zhou},

editor = {Kristen M. DeAngelis},

doi = {10.1128/spectrum.02591-21},

issn = {2165-0497},

year  = {2022},

date = {2022-02-23},

journal = {Microbiol Spectr},

volume = {10},

number = {1},

publisher = {American Society for Microbiology},

abstract = {

            Despite the dominance of

            Rhodanobacter

            species in the subsurface of the contaminated Oak Ridge Reservation (ORR) site, very little is known about the mechanisms underlying their adaptions to the various stressors present at ORR. Recently, multiple

            Rhodanobacter

            strains have been isolated from the ORR groundwater samples from several wells with varying geochemical properties.

          },

keywords = {Cell Biology, Ecology, General Immunology and Microbiology, Genetics, Infectious Diseases, Microbiology (medical), Physiology},

pubstate = {published},

tppubtype = {article}

}

@article{McCausland2022,

title = {Global Analysis of Biomineralization Genes in

            \textit{Magnetospirillum magneticum}

            AMB-1},

author = {Hayley C. McCausland and Kelly M. Wetmore and Adam P. Arkin and Arash Komeili},

editor = {Sarah Glaven},

doi = {10.1128/msystems.01037-21},

issn = {2379-5077},

year  = {2022},

date = {2022-02-22},

journal = {mSystems},

volume = {7},

number = {1},

publisher = {American Society for Microbiology},

abstract = {Magnetotactic bacteria (MTB) are a group of bacteria that can form nano-sized crystals of magnetic minerals. MTB are likely an important part of their ecosystems, because they can account for up to a third of the microbial biomass in an aquatic habitat and consume large amounts of iron, potentially impacting the iron cycle.},

keywords = {Behavior and Systematics, Biochemistry, Computer Science Applications, Ecology, Evolution, Genetics, Microbiology, Modeling and Simulation, Molecular Biology, Physiology},

pubstate = {published},

tppubtype = {article}

}

@article{Skerker2021,

title = {Chromosome assembled and annotated genome sequence of \textit{Aspergillus flavus} NRRL 3357},

author = {Jeffrey M Skerker and Kaila M Pianalto and Stephen J Mondo and Kunlong Yang and Adam P Arkin and Nancy P Keller and Igor V Grigoriev and N Louise Glass},

editor = {J C Dunlap},

doi = {10.1093/g3journal/jkab213},

issn = {2160-1836},

year  = {2021},

date = {2021-08-07},

volume = {11},

number = {8},

publisher = {Oxford University Press (OUP)},

abstract = {Abstract

               Aspergillus flavus is an opportunistic pathogen of crops, including peanuts and maize, and is the second leading cause of aspergillosis in immunocompromised patients. A. flavus is also a major producer of the mycotoxin, aflatoxin, a potent carcinogen, which results in significant crop losses annually. The A. flavus isolate NRRL 3357 was originally isolated from peanut and has been used as a model organism for understanding the regulation and production of secondary metabolites, such as aflatoxin. A draft genome of NRRL 3357 was previously constructed, enabling the development of molecular tools and for understanding population biology of this particular species. Here, we describe an updated, near complete, telomere-to-telomere assembly and re-annotation of the eight chromosomes of A. flavus NRRL 3357 genome, accomplished via long-read PacBio and Oxford Nanopore technologies combined with Illumina short-read sequencing. A total of 13,715 protein-coding genes were predicted. Using RNA-seq data, a significant improvement was achieved in predicted 5’ and 3’ untranslated regions, which were incorporated into the new gene models.},

keywords = {Genetics, Genetics (clinical), Molecular Biology},

pubstate = {published},

tppubtype = {article}

}

@article{Kothari2021,

title = {Ecogenomics of Groundwater Phages Suggests Niche Differentiation Linked to Specific Environmental Tolerance},

author = {Ankita Kothari and Simon Roux and Hanqiao Zhang and Anatori Prieto and Drishti Soneja and John-Marc Chandonia and Sarah Spencer and Xiaoqin Wu and Sara Altenburg and Matthew W. Fields and Adam M. Deutschbauer and Adam P. Arkin and Eric J. Alm and Romy Chakraborty and Aindrila Mukhopadhyay},

editor = {Ileana M. Cristea},

doi = {10.1128/msystems.00537-21},

issn = {2379-5077},

year  = {2021},

date = {2021-06-29},

urldate = {2021-06-29},

journal = {mSystems},

volume = {6},

number = {3},

publisher = {American Society for Microbiology},

abstract = {<jats:p>To our knowledge, this is the first study to identify the bacteriophage distribution in a groundwater ecosystem shedding light on their prevalence and distribution across metal-contaminated and background sites. Our study is uniquely based on selective sequencing of solely the extrachromosomal elements of a microbiome followed by analysis for viral signatures, thus establishing a more focused approach for phage identifications.</jats:p>},

keywords = {Behavior and Systematics, Biochemistry, biodesign, Computer Science Applications, Ecology, Evolution, Genetics, Microbiology, Modeling and Simulation, Molecular Biology, Physiology},

pubstate = {published},

tppubtype = {article}

}

@article{Seaver2020,

title = {The ModelSEED Biochemistry Database for the integration of metabolic annotations and the reconstruction, comparison and analysis of metabolic models for plants, fungi and microbes},

author = {Samuel M D Seaver and Filipe Liu and Qizhi Zhang and James Jeffryes and José P Faria and Janaka N Edirisinghe and Michael Mundy and Nicholas Chia and Elad Noor and Moritz E Beber and Aaron A Best and Matthew DeJongh and Jeffrey A Kimbrel and Patrik D’haeseleer and Sean R McCorkle and Jay R Bolton and Erik Pearson and Shane Canon and Elisha M Wood-Charlson and Robert W Cottingham and Adam P Arkin and Christopher S Henry},

doi = {10.1093/nar/gkaa746},

issn = {1362-4962},

year  = {2021},

date = {2021-01-08},

volume = {49},

number = {D1},

pages = {D575--D588},

publisher = {Oxford University Press (OUP)},

abstract = {AbstractFor over 10 years, ModelSEED has been a primary resource for the construction of draft genome-scale metabolic models based on annotated microbial or plant genomes. Now being released, the biochemistry database serves as the foundation of biochemical data underlying ModelSEED and KBase. The biochemistry database embodies several properties that, taken together, distinguish it from other published biochemistry resources by: (i) including compartmentalization, transport reactions, charged molecules and proton balancing on reactions; (ii) being extensible by the user community, with all data stored in GitHub; and (iii) design as a biochemical ‘Rosetta Stone’ to facilitate comparison and integration of annotations from many different tools and databases. The database was constructed by combining chemical data from many resources, applying standard transformations, identifying redundancies and computing thermodynamic properties. The ModelSEED biochemistry is continually tested using flux balance analysis to ensure the biochemical network is modeling-ready and capable of simulating diverse phenotypes. Ontologies can be designed to aid in comparing and reconciling metabolic reconstructions that differ in how they represent various metabolic pathways. ModelSEED now includes 33,978 compounds and 36,645 reactions, available as a set of extensible files on GitHub, and available to search at https://modelseed.org/biochem and KBase.},

keywords = {Genetics},

pubstate = {published},

tppubtype = {article}

}