{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T02:55:57Z","timestamp":1787021757640,"version":"build-2736575974"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1008757","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T00:00:00Z","timestamp":1615507200000}}],"reference-count":38,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T00:00:00Z","timestamp":1614643200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"publisher","award":["1019985"],"award-info":[{"award-number":["1019985"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"crossref","award":["1024983"],"award-info":[{"award-number":["1024983"]}],"id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>\n                    Microbes can metabolize more chemical compounds than any other group of organisms. As a result, their metabolism is of interest to investigators across biology. Despite the interest, information on metabolism of specific microbes is hard to access. Information is buried in text of books and journals, and investigators have no easy way to extract it out. Here we investigate if neural networks can extract out this information and predict metabolic traits. For proof of concept, we predicted two traits: whether microbes carry one type of metabolism (fermentation) or produce one metabolite (acetate). We collected written descriptions of 7,021 species of bacteria and archaea from\n                    <jats:italic>Bergey\u2019s Manual<\/jats:italic>\n                    . We read the descriptions and manually identified (labeled) which species were fermentative or produced acetate. We then trained neural networks to predict these labels. In total, we identified 2,364 species as fermentative, and 1,009 species as also producing acetate. Neural networks could predict which species were fermentative with 97.3% accuracy. Accuracy was even higher (98.6%) when predicting species also producing acetate. Phylogenetic trees of species and their traits confirmed that predictions were accurate. Our approach with neural networks can extract information efficiently and accurately. It paves the way for putting more metabolic traits into databases, providing easy access of information to investigators.\n                  <\/jats:p>","DOI":"10.1371\/journal.pcbi.1008757","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T13:50:10Z","timestamp":1614693010000},"page":"e1008757","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["Using neural networks to mine text and predict metabolic traits for thousands of microbes"],"prefix":"10.1371","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6455-1862","authenticated-orcid":true,"given":"Timothy J.","family":"Hackmann","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8984-9294","authenticated-orcid":true,"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,3,2]]},"reference":[{"issue":"5879","key":"pcbi.1008757.ref001","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1126\/science.1153213","article-title":"The microbial engines that drive Earth\u2019s biogeochemical cycles","volume":"320","author":"PG Falkowski","year":"2008","journal-title":"Science"},{"issue":"5","key":"pcbi.1008757.ref002","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1038\/nrmicro.2018.9","article-title":"The microbial nitrogen-cycling network","volume":"16","author":"MMM Kuypers","year":"2018","journal-title":"Nat Rev Microbiol"},{"key":"pcbi.1008757.ref003","volume-title":"Bacterial biogeochemistry: the ecophysiology of mineral cycling","author":"T Fenchel","year":"2012","edition":"3"},{"key":"pcbi.1008757.ref004","volume-title":"Microbial symbioses:","author":"S Duperron","year":"2016"},{"key":"pcbi.1008757.ref005","volume-title":"Microbial ecology: fundamentals and applications","author":"RM Atlas","year":"1998","edition":"4"},{"issue":"6","key":"pcbi.1008757.ref006","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1038\/nchembio.975","article-title":"Natural strategies for the spatial optimization of metabolism in synthetic biology","volume":"8","author":"CM Agapakis","year":"2012","journal-title":"Nat Chem Biol"},{"issue":"2","key":"pcbi.1008757.ref007","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.tibtech.2018.11.002","article-title":"Synthetic biology tools to engineer microbial communities for biotechnology","volume":"37","author":"NS McCarty","year":"2019","journal-title":"Trends Biotechnol"},{"key":"pcbi.1008757.ref008","volume-title":"Bergey\u2019s manual of systematics of archaea and bacteria:","author":"WB Whitman","year":"2020"},{"issue":"D1","key":"pcbi.1008757.ref009","doi-asserted-by":"crossref","first-page":"D631","DOI":"10.1093\/nar\/gky879","article-title":"BacDive in 2019: bacterial phenotypic data for high-throughput biodiversity analysis","volume":"47","author":"LC Reimer","year":"2019","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"pcbi.1008757.ref010","doi-asserted-by":"crossref","first-page":"e00237","DOI":"10.1128\/mSphere.00237-17","article-title":"Hiding in plain sight: mining bacterial species records for phenotypic trait information.","volume":"2","author":"A Barberan","year":"2017","journal-title":"mSphere"},{"issue":"6305","key":"pcbi.1008757.ref011","doi-asserted-by":"crossref","first-page":"1272","DOI":"10.1126\/science.aaf4507","article-title":"Decoupling function and taxonomy in the global ocean microbiome","volume":"353","author":"S Louca","year":"2016","journal-title":"Science"},{"issue":"1","key":"pcbi.1008757.ref012","doi-asserted-by":"crossref","first-page":"528","DOI":"10.1186\/s12859-016-1396-8","article-title":"Microbial phenomics information extractor (MicroPIE): a natural language processing tool for the automated acquisition of prokaryotic phenotypic characters from text sources.","volume":"17","author":"J Mao","year":"2016","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"pcbi.1008757.ref013","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1186\/s13643-019-1074-9","article-title":"Toward systematic review automation: a practical guide to using machine learning tools in research synthesis.","volume":"8","author":"IJ Marshall","year":"2019","journal-title":"Syst Rev."},{"key":"pcbi.1008757.ref014","first-page":"1903","article-title":"SciBERT: A pretrained language model for scientific text.","author":"I Beltagy","year":"2019","journal-title":"arXiv"},{"issue":"4","key":"pcbi.1008757.ref015","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"J Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"pcbi.1008757.ref016","unstructured":"Schmitt C, Walker V, Williams A, Varghese A, Ahmad Y, Rooney A, et al. Overview of the TAC 2018 Systematic Review Information Extraction Track. Proceedings of the Eleventh Text Analysis Conference2018."},{"key":"pcbi.1008757.ref017","first-page":"2004","article-title":"Specter: Document-level representation learning using citation-informed transformers.","author":"A Cohan","year":"2020","journal-title":"arXiv"},{"key":"pcbi.1008757.ref018","first-page":"1603","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems.","author":"M Abadi","year":"2016","journal-title":"arXiv"},{"key":"pcbi.1008757.ref019","article-title":"List of Prokaryotic names with Standing in Nomenclature (LPSN) moves to the DSMZ.","author":"AC Parte","year":"2020","journal-title":"Int J Syst Evol Microbiol"},{"key":"pcbi.1008757.ref020","doi-asserted-by":"crossref","first-page":"D613","DOI":"10.1093\/nar\/gkt1111","article-title":"LPSN\u2014list of prokaryotic names with standing in nomenclature","volume":"42","author":"AC Parte","year":"2014","journal-title":"Nucleic Acids Res"},{"issue":"18","key":"pcbi.1008757.ref021","doi-asserted-by":"crossref","first-page":"2578","DOI":"10.1021\/acs.biochem.5b01286","article-title":"Transport of a fluorescent analogue of glucose (2-NBDG) versus radiolabeled sugars by rumen bacteria and Escherichia coli.","volume":"55","author":"JY Tao","year":"2016","journal-title":"Biochemistry"},{"issue":"7","key":"pcbi.1008757.ref022","article-title":"Use of a fluorescent analog of glucose (2-NBDG) to identify uncultured rumen bacteria that take up glucose.","volume":"85","author":"J Tao","year":"2019","journal-title":"Appl Environ Microbiol"},{"key":"pcbi.1008757.ref023","article-title":"A new pathway for forming acetate and synthesizing ATP during fermentation in bacteria.","author":"B Zhang","year":"2020","journal-title":"bioRxiv."},{"issue":"4","key":"pcbi.1008757.ref024","article-title":"Lipopolysaccharide stimulates the growth of bacteria that contribute to ruminal acidosis","volume":"86","author":"X Dai","year":"2020","journal-title":"Appl Environ Microbiol"},{"issue":"D1","key":"pcbi.1008757.ref025","doi-asserted-by":"crossref","first-page":"D666","DOI":"10.1093\/nar\/gky901","article-title":"IMG\/M v.5.0: an integrated data management and comparative analysis system for microbial genomes and microbiomes","volume":"47","author":"IA Chen","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1008757.ref026","first-page":"baz049","article-title":"The MACADAM database: a MetAboliC pAthways DAtabase for Microbial taxonomic groups for mining potential metabolic capacities of archaeal and bacterial taxonomic groups.","author":"M Le Boulch","year":"2019","journal-title":"Database"},{"issue":"11","key":"pcbi.1008757.ref027","doi-asserted-by":"crossref","first-page":"4670","DOI":"10.1111\/1462-2920.13929","article-title":"Genomes of rumen bacteria encode atypical pathways for fermenting hexoses to short-chain fatty acids","volume":"19","author":"TJ Hackmann","year":"2017","journal-title":"Environ Microbiol"},{"issue":"6","key":"pcbi.1008757.ref028","doi-asserted-by":"crossref","first-page":"1181","DOI":"10.1016\/j.cell.2018.02.016","article-title":"Major new microbial groups expand diversity and alter our understanding of the tree of life","volume":"172","author":"CJ Castelle","year":"2018","journal-title":"Cell"},{"key":"pcbi.1008757.ref029","doi-asserted-by":"crossref","first-page":"16048","DOI":"10.1038\/nmicrobiol.2016.48","article-title":"A new view of the tree of life.","volume":"1","author":"LA Hug","year":"2016","journal-title":"Nat Microbiol."},{"issue":"D1","key":"pcbi.1008757.ref030","doi-asserted-by":"crossref","first-page":"D649","DOI":"10.1093\/nar\/gky977","article-title":"Genomes OnLine database (GOLD) v.7: updates and new features.","volume":"47","author":"S Mukherjee","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1008757.ref031","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1038\/msb.2011.75","article-title":"Fast, scalable generation of high-quality protein multiple sequence alignments using Clustal Omega","volume":"7","author":"F Sievers","year":"2011","journal-title":"Mol Syst Biol"},{"issue":"24","key":"pcbi.1008757.ref032","doi-asserted-by":"crossref","first-page":"3997","DOI":"10.1093\/bioinformatics\/btv494","article-title":"msa: an R package for multiple sequence alignment","volume":"31","author":"U Bodenhofer","year":"2015","journal-title":"Bioinformatics"},{"issue":"3","key":"pcbi.1008757.ref033","doi-asserted-by":"crossref","first-page":"728","DOI":"10.1093\/bioinformatics\/btz668","article-title":"Accurate estimation of microbial sequence diversity with Distanced","volume":"36","author":"TJ Hackmann","year":"2020","journal-title":"Bioinformatics"},{"issue":"9","key":"pcbi.1008757.ref034","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1093\/bioinformatics\/btu033","article-title":"RAxML version 8: a tool for phylogenetic analysis and post-analysis of large phylogenies","volume":"30","author":"A Stamatakis","year":"2014","journal-title":"Bioinformatics"},{"key":"pcbi.1008757.ref035","article-title":"Creating the CIPRES Science Gateway for inference of large phylogenetic trees.","author":"Ieee","year":"2010","journal-title":"2010 gateway computing environments workshop (GCE)"},{"issue":"2","key":"pcbi.1008757.ref036","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1111\/j.2041-210X.2011.00169.x","article-title":"phytools: an R package for phylogenetic comparative biology (and other things).","volume":"3","author":"L Revell","year":"2012","journal-title":"Methods Ecol Evol."},{"issue":"1","key":"pcbi.1008757.ref037","first-page":"28","volume":"8","author":"G Yu","year":"2017","journal-title":"Evolution. ggtree: an R package for visualization and annotation of phylogenetic trees with their covariates and other associated data"},{"issue":"4","key":"pcbi.1008757.ref038","doi-asserted-by":"crossref","first-page":"e61217","DOI":"10.1371\/journal.pone.0061217","article-title":"phyloseq: an R package for reproducible interactive analysis and graphics of microbiome census data","volume":"8","author":"PJ McMurdie","year":"2013","journal-title":"PLoS One"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1008757","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T00:00:00Z","timestamp":1615507200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T04:48:09Z","timestamp":1697950089000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1008757"}},"subtitle":[],"editor":[{"given":"Morgan","family":"Langille","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,3,2]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3,2]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1008757","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.09.29.319335","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,2]]}}}