{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:54:36Z","timestamp":1790794476146,"version":"4.1.0"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1014034","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000}}],"reference-count":43,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100006751","name":"U.S. Army","doi-asserted-by":"publisher","award":["W911NF2210185"],"award-info":[{"award-number":["W911NF2210185"]}],"id":[{"id":"10.13039\/100006751","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Karol Family Professorship","award":["n\/a"],"award-info":[{"award-number":["n\/a"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>The Enzyme Commission (EC) numbering scheme provides a hierarchical way to classify enzymes according to their catalytic functions. While recent protein language model (PLM) based approaches like CLEAN and ProteInter have improved sequence-based EC number prediction, they struggle with fine-grained classification at the deepest hierarchical level. Structure-based approaches for grouping similar proteins using alignment tools excel at finding proteins that share overall global structure, but suffer from high false positive rates when classifying proteins that are globally structurally similar but functional differentiation depends on a localized region. This problem is particularly relevant to EC number prediction, as enzymatic function depends on its catalytic domain, which is a relatively small, specific region of the protein. We introduce Deep Enzyme Function Transfer (DEFT) that harmonizes sequence- and structure-based approaches through the key insight that PLM based annotations of the first two EC number hierarchy levels vastly reduce false positives that are likely to show in purely structure-based EC number prediction. Given an enzyme of interest, DEFT first uses a PLM based method to assign the first two levels of the enzyme\u2019s EC number, and then uses a structure-based method to predict the remaining two levels of the EC number. Using benchmarking datasets, we demonstrate that DEFT achieves superior accuracy compared with current state-of-the-art tools for EC number prediction. Furthermore we show that DEFT\u2019s computational efficiency enables high-throughput, genome-wide annotations of total enzyme repertoires in organisms. We illustrate this capability by experimentally validating DEFT predicted glycoside hydrolase (GH) profiles of intestinal mucus associated bacteria.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1014034","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T17:55:11Z","timestamp":1790358911000},"page":"e1014034","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fast structural search for classification of gut bacterial mucin O-glycan degrading enzymes"],"prefix":"10.1371","volume":"22","author":[{"given":"Mert","family":"Erden","sequence":"first","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3338-4219","authenticated-orcid":true,"given":"Tyler","family":"Schult","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Chemical and Biological Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karin","family":"Yanagi","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Chemical and Biological Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jugal Kishore","family":"Sahoo","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Biomedical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David L.","family":"Kaplan","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Biomedical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-6413","authenticated-orcid":true,"given":"Lenore J.","family":"Cowen","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0699-8057","authenticated-orcid":true,"given":"Kyongbum","family":"Lee","sequence":"additional","affiliation":[{"name":"Tufts University","place":["Medford, Massachusetts, United States of America"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"pcbi.1014034.ref001","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1016\/j.pisc.2014.02.006","article-title":"Current IUBMB recommendations on enzyme nomenclature and kinetics","volume":"1","author":"A Cornish-Bowden","year":"2014","journal-title":"Perspect Sci"},{"issue":"2","key":"pcbi.1014034.ref002","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0147952","article-title":"Characterising Complex Enzyme Reaction Data","volume":"11","author":"HM D\u00f6nerta\u015f","year":"2016","journal-title":"PLoS One"},{"issue":"10","key":"pcbi.1014034.ref003","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btad620","article-title":"Predicting enzymatic function of protein sequences with attention","volume":"39","author":"N Buton","year":"2023","journal-title":"Bioinformatics"},{"key":"pcbi.1014034.ref004","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.80942","article-title":"ProteInfer, deep neural networks for protein functional inference","volume":"12","author":"T Sanderson","year":"2023","journal-title":"Elife"},{"issue":"12","key":"pcbi.1014034.ref005","doi-asserted-by":"crossref","first-page":"1987","DOI":"10.1002\/int.22280","article-title":"DeepEC: An error correction framework for dose prediction and organ segmentation using deep neural networks","volume":"35","author":"H Wang","year":"2020","journal-title":"Int J Intell Syst"},{"issue":"6639","key":"pcbi.1014034.ref006","doi-asserted-by":"crossref","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"T Yu","year":"2023","journal-title":"Science"},{"issue":"1","key":"pcbi.1014034.ref007","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1186\/s12859-018-2368-y","article-title":"ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature","volume":"19","author":"A Dalkiran","year":"2018","journal-title":"BMC Bioinform"},{"issue":"5","key":"pcbi.1014034.ref008","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1016\/j.jmb.2010.12.005","article-title":"Structural signatures of enzyme binding pockets from order-independent surface alignment: a study of metalloendopeptidase and NAD binding proteins","volume":"406","author":"J Dundas","year":"2011","journal-title":"J Mol Biol"},{"issue":"7873","key":"pcbi.1014034.ref009","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"J Jumper","year":"2021","journal-title":"Nature"},{"key":"pcbi.1014034.ref010","unstructured":"Abramson J, Adler J, Dunger J, Evans R, Green T, Pritzel A, et al. Accurate structure prediction of biomolecular interactions with AlphaFold 3. Nature. 2024;1\u20133."},{"issue":"6637","key":"pcbi.1014034.ref011","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Z Lin","year":"2023","journal-title":"Science"},{"key":"pcbi.1014034.ref012","unstructured":"Wu R, Ding F, Wang R, Shen R, Zhang X, Luo S, et al. High-resolution de novo structure prediction from primary sequence. bioRxiv. 2022. Available from: https:\/\/www.biorxiv.org\/content\/early\/2022\/07\/22\/2022.07.21.500999"},{"issue":"7","key":"pcbi.1014034.ref013","doi-asserted-by":"crossref","first-page":"2302","DOI":"10.1093\/nar\/gki524","article-title":"TM-align: a protein structure alignment algorithm based on the TM-score","volume":"33","author":"Y Zhang","year":"2005","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1014034.ref014","doi-asserted-by":"crossref","unstructured":"Su J, Han C, Zhou Y, Shan J, Zhou X, Yuan F. SaProt: protein language modeling with structure-aware vocabulary. bioRxiv. 2023;2023-10.","DOI":"10.1101\/2023.10.01.560349"},{"issue":"2","key":"pcbi.1014034.ref015","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1038\/s41587-023-01773-0","article-title":"Fast and accurate protein structure search with Foldseek","volume":"42","author":"M van Kempen","year":"2024","journal-title":"Nat Biotechnol"},{"issue":"3","key":"pcbi.1014034.ref016","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1007\/s10719-018-9824-9","article-title":"Cloning, purification and biochemical characterisation of a GH35 beta-1,3\/beta-1,6-galactosidase from the mucin-degrading gut bacterium Akkermansia muciniphila","volume":"35","author":"B-S Guo","year":"2018","journal-title":"Glycoconj J"},{"key":"pcbi.1014034.ref017","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.carres.2015.08.001","article-title":"Biochemical characterisation of the neuraminidase pool of the human gut symbiont Akkermansia muciniphila","volume":"415","author":"K Huang","year":"2015","journal-title":"Carbohydr Res"},{"issue":"1","key":"pcbi.1014034.ref018","doi-asserted-by":"crossref","first-page":"3485","DOI":"10.1038\/s41467-025-58660-2","article-title":"A Bacteroides thetaiotaomicron genetic locus encodes activities consistent with mucin O-glycoprotein processing and N-acetylgalactosamine metabolism","volume":"16","author":"DA Ndeh","year":"2025","journal-title":"Nat Commun"},{"key":"pcbi.1014034.ref019","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1042\/bj2800309","article-title":"A classification of glycosyl hydrolases based on amino acid sequence similarities","volume":"280","author":"B Henrissat","year":"1991","journal-title":"Biochem J"},{"issue":"9","key":"pcbi.1014034.ref020","doi-asserted-by":"crossref","first-page":"853","DOI":"10.1016\/S0969-2126(01)00220-9","article-title":"Structures and mechanisms of glycosyl hydrolases","volume":"3","author":"G Davies","year":"1995","journal-title":"Structure"},{"key":"pcbi.1014034.ref021","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, et al. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:210609685. 2021."},{"issue":"3","key":"pcbi.1014034.ref022","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/0888-7543(91)90071-L","article-title":"Searching protein sequence libraries: comparison of the sensitivity and selectivity of the Smith-Waterman and FASTA algorithms","volume":"11","author":"WR Pearson","year":"1991","journal-title":"Genomics"},{"issue":"5","key":"pcbi.1014034.ref023","doi-asserted-by":"crossref","first-page":"723","DOI":"10.3390\/microorganisms8050723","article-title":"Revisiting the Metabolic Capabilities of Bifidobacterium longum susbp. longum and Bifidobacterium longum subsp. infantis from a Glycoside Hydrolase Perspective","volume":"8","author":"G Blanco","year":"2020","journal-title":"Microorganisms"},{"issue":"45","key":"pcbi.1014034.ref024","doi-asserted-by":"crossref","first-page":"37415","DOI":"10.1074\/jbc.M506874200","article-title":"Identification and molecular cloning of a novel glycoside hydrolase family of core 1 type O-glycan-specific endo-alpha-N-acetylgalactosaminidase from Bifidobacterium longum","volume":"280","author":"K Fujita","year":"2005","journal-title":"J Biol Chem"},{"issue":"20","key":"pcbi.1014034.ref025","doi-asserted-by":"crossref","first-page":"6444","DOI":"10.1128\/AEM.01425-07","article-title":"Identification of N-acetylhexosamine 1-kinase in the complete lacto-N-biose I\/galacto-N-biose metabolic pathway in Bifidobacterium longum","volume":"73","author":"M Nishimoto","year":"2007","journal-title":"Appl Environ Microbiol"},{"issue":"13","key":"pcbi.1014034.ref026","doi-asserted-by":"crossref","first-page":"3996","DOI":"10.1128\/AEM.00149-08","article-title":"Bifidobacterium bifidum lacto-N-biosidase, a critical enzyme for the degradation of human milk oligosaccharides with a type 1 structure","volume":"74","author":"J Wada","year":"2008","journal-title":"Appl Environ Microbiol"},{"issue":"50","key":"pcbi.1014034.ref027","doi-asserted-by":"crossref","first-page":"34661","DOI":"10.1021\/jacs.4c12945","article-title":"Selective Biofilm Inhibition through Mucin-Inspired Engineering of Silk Glycopolymers","volume":"146","author":"CA Werlang","year":"2024","journal-title":"J Am Chem Soc"},{"issue":"1","key":"pcbi.1014034.ref028","doi-asserted-by":"crossref","first-page":"7370","DOI":"10.1038\/s41467-023-43216-z","article-title":"Functional annotation of enzyme-encoding genes using deep learning with transformer layers","volume":"14","author":"GB Kim","year":"2023","journal-title":"Nat Commun"},{"key":"pcbi.1014034.ref029","doi-asserted-by":"crossref","unstructured":"Su J, Han C, Zhou Y, Shan J, Zhou X, Yuan F. Saprot: Protein language modeling with structure-aware vocabulary. In: 2024. 6987\u20137009.","DOI":"10.1101\/2023.10.01.560349"},{"issue":"1","key":"pcbi.1014034.ref030","doi-asserted-by":"crossref","first-page":"8180","DOI":"10.1038\/s41467-024-52533-w","article-title":"Accurately predicting enzyme functions through geometric graph learning on ESMFold-predicted structures","volume":"15","author":"Y Song","year":"2024","journal-title":"Nat Commun"},{"issue":"2","key":"pcbi.1014034.ref031","doi-asserted-by":"crossref","first-page":"131","DOI":"10.1016\/j.anaerobe.2009.07.006","article-title":"Safety evaluation of probiotic bifidobacteria by analysis of mucin degradation activity and translocation ability","volume":"16","author":"F Abe","year":"2010","journal-title":"Anaerobe"},{"issue":"6","key":"pcbi.1014034.ref032","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1128\/AEM.02509-07","article-title":"Mucin degradation by Bifidobacterium strains isolated from the human intestinal microbiota","volume":"74","author":"P Ruas-Madiedo","year":"2008","journal-title":"Appl Environ Microbiol"},{"key":"pcbi.1014034.ref033","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkt376","article-title":"Analysis Tool Web Services from the EMBL-EBI","volume":"41","author":"H McWilliam","year":"2013","journal-title":"Nucleic Acids Res"},{"issue":"8","key":"pcbi.1014034.ref034","doi-asserted-by":"crossref","first-page":"1128","DOI":"10.1093\/glycob\/cws083","article-title":"Detailed O-glycomics of the Muc2 mucin from colon of wild-type, core 1- and core 3-transferase-deficient mice highlights differences compared with human MUC2","volume":"22","author":"KA Thomsson","year":"2012","journal-title":"Glycobiology"},{"issue":"1","key":"pcbi.1014034.ref035","doi-asserted-by":"crossref","first-page":"1833","DOI":"10.1038\/s41467-023-37533-6","article-title":"Sialidases and fucosidases of Akkermansia muciniphila are crucial for growth on mucin and nutrient sharing with mucus-associated gut bacteria","volume":"14","author":"B Shuoker","year":"2023","journal-title":"Nat Commun"},{"issue":"8","key":"pcbi.1014034.ref036","doi-asserted-by":"crossref","DOI":"10.1128\/mbio.00039-24","article-title":"Ruminococcus torques is a keystone degrader of intestinal mucin glycoprotein, releasing oligosaccharides used by Bacteroides thetaiotaomicron","volume":"15","author":"SR Schaus","year":"2024","journal-title":"mBio"},{"issue":"1","key":"pcbi.1014034.ref037","doi-asserted-by":"crossref","first-page":"8456","DOI":"10.1038\/s41598-022-11819-z","article-title":"Characterizing the mucin-degrading capacity of the human gut microbiota","volume":"12","author":"JS Glover","year":"2022","journal-title":"Sci Rep"},{"issue":"8","key":"pcbi.1014034.ref038","article-title":"Distinct in vitro utilization and degradation of porcine gastric mucin glycans by human intestinal bacteria","volume":"101","author":"C de Ram","year":"2025","journal-title":"FEMS Microbiol Ecol"},{"key":"pcbi.1014034.ref039","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkaf1113","article-title":"BRENDA in 2026: a Global Core Biodata Resource for functional enzyme and metabolic data within the DSMZ Digital Diversity","volume":"54","author":"J Hauenstein","year":"2026","journal-title":"Nucleic Acids Res"},{"key":"pcbi.1014034.ref040","unstructured":"BRENDA-Enzymes. Database entry for EC 3.2.1.52. Accessed: 2025-05-10. https:\/\/www.brenda-enzymes.org\/enzyme.php?ecno=3.2.1.52"},{"key":"pcbi.1014034.ref041","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/0076-6879(82)83058-9","article-title":"Endo-beta-N-acetylglucosaminidase L from Streptomyces plicatus","volume":"83","author":"RB Trimble","year":"1982","journal-title":"Methods Enzymol"},{"issue":"6","key":"pcbi.1014034.ref042","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1038\/s41589-023-01272-y","article-title":"A bacterial sulfoglycosidase highlights mucin O-glycan breakdown in the gut ecosystem","volume":"19","author":"T Katoh","year":"2023","journal-title":"Nat Chem Biol"},{"issue":"1","key":"pcbi.1014034.ref043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/03602530701836662","article-title":"Cytochromes P450: a structure-based summary of biotransformations using representative substrates","volume":"40","author":"CM Brown","year":"2008","journal-title":"Drug Metab Rev"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1014034","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014034","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:56:24Z","timestamp":1790790984000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1014034"}},"subtitle":[],"editor":[{"given":"Boyang","family":"Ji","sequence":"first","affiliation":[{"name":"BioInnovation Institute","place":["DENMARK"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":43,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1014034","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]}}}