@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{Goff2022b,

title = {Ecophysiological and genomic analyses of a representative isolate of highly abundant \textit{Bacillus cereus} strains in contaminated subsurface sediments},

author = {Jennifer L. Goff and Elizabeth G. Szink and Michael P. Thorgersen and Andrew D. Putt and Yupeng Fan and Lauren M. Lui and Torben N. Nielsen and Kristopher A. Hunt and Jonathan P. Michael and Yajiao Wang and Daliang Ning and Ying Fu and Joy D. Van Nostrand and Farris L. Poole and John‐Marc Chandonia and Terry C. Hazen and David A. Stahl and Jizhong Zhou and Adam P. Arkin and Michael W. W. Adams},

doi = {10.1111/1462-2920.16173},

issn = {1462-2920},

year  = {2022},

date = {2022-11-00},

journal = {Environmental Microbiology},

volume = {24},

number = {11},

pages = {5546--5560},

publisher = {Wiley},

abstract = {AbstractBacillus cereus strain CPT56D‐587‐MTF (CPTF) was isolated from the highly contaminated Oak Ridge Reservation (ORR) subsurface. This site is contaminated with high levels of nitric acid and multiple heavy metals. Amplicon sequencing of the 16S rRNA genes (V4 region) in sediment from this area revealed an amplicon sequence variant (ASV) with 100% identity to the CPTF 16S rRNA sequence. Notably, this CPTF‐matching ASV had the highest relative abundance in this community survey, with a median relative abundance of 3.77% and comprised 20%–40% of reads in some samples. Pangenomic analysis revealed that strain CPTF has expanded genomic content compared to other B. cereus species—largely due to plasmid acquisition and expansion of transposable elements. This suggests that these features are important for rapid adaptation to native environmental stressors. We connected genotype to phenotype in the context of the unique geochemistry of the site. These analyses revealed that certain genes (e.g. nitrate reductase, heavy metal efflux pumps) that allow this strain to successfully occupy the geochemically heterogenous microniches of its native site are characteristic of the B. cereus species while others such as acid tolerance are mobile genetic element associated and are generally unique to strain CPTF.},

keywords = {Behavior and Systematics, Ecology, Evolution, Microbiology},

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{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{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{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}

}