{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T15:18:40Z","timestamp":1778339920345,"version":"3.51.4"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T00:00:00Z","timestamp":1740614400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["DFA\/BD\/08789\/2021"],"award-info":[{"award-number":["DFA\/BD\/08789\/2021"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"],"award-info":[{"award-number":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"],"award-info":[{"award-number":["10.54499\/CEECIND\/03425\/2018\/CP1581\/CT0020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"European Molecular Biology Laboratory (EMBL) Corporate Partnership Programme"},{"DOI":"10.13039\/100013060","name":"European Molecular Biology Laboratory","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100013060","id-type":"DOI","asserted-by":"crossref"}]},{"name":"LABBELS","award":["LA\/P\/0029\/2020"],"award-info":[{"award-number":["LA\/P\/0029\/2020"]}]},{"name":"LABBELS","award":["LA\/P\/0029\/2020"],"award-info":[{"award-number":["LA\/P\/0029\/2020"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"DOI":"10.1186\/s12859-025-06081-9","type":"journal-article","created":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T12:38:47Z","timestamp":1740746327000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Comparative Assessment of Protein Large Language Models for Enzyme Commission Number Prediction"],"prefix":"10.1186","volume":"26","author":[{"given":"Jo\u00e3o","family":"Capela","sequence":"first","affiliation":[]},{"given":"Maria","family":"Zimmermann-Kogadeeva","sequence":"additional","affiliation":[]},{"given":"Aalt D. J. van","family":"Dijk","sequence":"additional","affiliation":[]},{"given":"Dick","family":"de Ridder","sequence":"additional","affiliation":[]},{"given":"Oscar","family":"Dias","sequence":"additional","affiliation":[]},{"given":"Miguel","family":"Rocha","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,27]]},"reference":[{"issue":"34","key":"6081_CR1","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.copbio.2014.12.020","volume":"8","author":"MA Keller","year":"2015","unstructured":"Keller MA, Piedrafita G, Ralser M. The widespread role of non-enzymatic reactions in cellular metabolism. Curr Opin Biotechnol. 2015;8(34):153\u201361.","journal-title":"Curr Opin Biotechnol."},{"issue":"12","key":"6081_CR2","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1038\/s41570-019-0143-x","volume":"3","author":"RB Leveson-Gower","year":"2019","unstructured":"Leveson-Gower RB, Mayer C, Roelfes G. The importance of catalytic promiscuity for enzyme design and evolution. Nat Rev Chem. 2019;3(12):687\u2013705.","journal-title":"Nat Rev Chem."},{"issue":"28","key":"6081_CR3","doi-asserted-by":"publisher","first-page":"13996","DOI":"10.1073\/pnas.1821905116","volume":"116","author":"JY Ryu","year":"2019","unstructured":"Ryu JY, Kim HU, Lee SY. Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers. PNAS. 2019;116(28):13996\u20134001.","journal-title":"PNAS."},{"issue":"50","key":"6081_CR4","doi-asserted-by":"publisher","first-page":"16487","DOI":"10.1021\/ja0466457","volume":"126","author":"M Kotera","year":"2004","unstructured":"Kotera M, Okuno Y, Hattori M, et al. Computational assignment of the EC numbers for genomic-scale analysis of enzymatic reactions. JACS. 2004;126(50):16487\u201398.","journal-title":"JACS."},{"issue":"W1","key":"6081_CR5","doi-asserted-by":"publisher","first-page":"W60","DOI":"10.1093\/nar\/gkab328","volume":"49","author":"D Baldazzi","year":"2021","unstructured":"Baldazzi D, Savojardo C, Martelli PL, et al. BENZ WS: the bologna ENZyme web server for four-level EC number annotation. Nucleic Acids Res. 2021;49(W1):W60\u20136.","journal-title":"Nucleic Acids Res."},{"issue":"11","key":"6081_CR6","doi-asserted-by":"publisher","first-page":"6052","DOI":"10.1093\/nar\/gkac459","volume":"50","author":"J Capela","year":"2022","unstructured":"Capela J, Lagoa D, Rodrigues R, et al. An improved framework for the reconstruction of high-quality genome-scale metabolic models. Nucleic Acids Res. 2022;50(11):6052\u201366.","journal-title":"Nucleic Acids Res."},{"issue":"1","key":"6081_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-12-376","volume":"12","author":"S Quester","year":"2011","unstructured":"Quester S, Schomburg D. EnzymeDetector: an integrated enzyme function prediction tool and database. BMC Bioinf. 2011;12(1):1\u201313.","journal-title":"BMC Bioinf."},{"issue":"5","key":"6081_CR8","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1093\/bioinformatics\/btx680","volume":"34","author":"Y Li","year":"2018","unstructured":"Li Y, Wang S, Umarov R, Xie B, et al. DEEPre: sequence-based enzyme EC number prediction by deep learning. Bioinformatics. 2018;34(5):760\u20139.","journal-title":"Bioinformatics."},{"issue":"3","key":"6081_CR9","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, et al. Basic local alignment search tool. J Mol Biol. 1990;215(3):403\u201310.","journal-title":"J Mol Biol."},{"issue":"13","key":"6081_CR10","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1186\/1471-2105-13-61","volume":"12","author":"LD Ferrari","year":"2012","unstructured":"Ferrari LD, Aitken S, van Hemert J, Goryanin I. EnzML: multi-label prediction of enzyme classes using InterPro signatures. BMC Bioinf. 2012;12(13):61.","journal-title":"BMC Bioinf."},{"key":"6081_CR11","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1093\/bioinformatics\/bts510","volume":"28","author":"N Kumar","year":"2012","unstructured":"Kumar N, Skolnick J. EFICAz2.5: application of a high-precision enzyme function predictor to 396 proteomes. Bioinformatics. 2012;28:2687\u20138.","journal-title":"Bioinformatics."},{"issue":"1","key":"6081_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0084623","volume":"9","author":"C Nagao","year":"2014","unstructured":"Nagao C, Nagano N, Mizuguchi K. Prediction of detailed enzyme functions and identification of specificity determining residues by random forests. PLoS One. 2014;9(1): e84623.","journal-title":"PLoS One."},{"key":"6081_CR13","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.80942","volume":"12","author":"T Sanderson","year":"2023","unstructured":"Sanderson T, Bileschi ML, Belanger D, et al. ProteInfer deep neural networks for protein functional inference. eLife. 2023;12: e80942.","journal-title":"eLife."},{"key":"6081_CR14","first-page":"6","volume":"1","author":"Z Shi","year":"2023","unstructured":"Shi Z, Deng R, Yuan Q, et al. Enzyme commission number prediction and benchmarking with hierarchical dual-core multitask learning framework. Research. 2023;1:6.","journal-title":"Research."},{"key":"6081_CR15","first-page":"39","volume":"10","author":"N Buton","year":"2023","unstructured":"Buton N, Coste F, Cunff YL. Predicting enzymatic function of protein sequences with attention. Bioinformatics. 2023;10:39.","journal-title":"Bioinformatics."},{"key":"6081_CR16","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1126\/science.adf2465","volume":"379","author":"T Yu","year":"2023","unstructured":"Yu T, Cui H, Li JC, et al. Enzyme function prediction using contrastive learning. Science. 2023;379:1358\u201363.","journal-title":"Science."},{"issue":"14","key":"6081_CR17","doi-asserted-by":"publisher","first-page":"7370","DOI":"10.1038\/s41467-023-43216-z","volume":"11","author":"GB Kim","year":"2023","unstructured":"Kim GB, Kim JY, Lee JA, et al. Functional annotation of enzyme-encoding genes using deep learning with transformer layers. Nat Commun. 2023;11(14):7370.","journal-title":"Nat Commun."},{"key":"6081_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-018-2368-y","volume":"19","author":"A Dalkiran","year":"2018","unstructured":"Dalkiran A, Rifaioglu A, Martin MJ, et al. ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature. BMC Bioinf. 2018;19:1\u201313.","journal-title":"BMC Bioinf."},{"issue":"51","key":"6081_CR19","first-page":"D523","volume":"1","author":"A Bateman","year":"2023","unstructured":"Bateman A, Martin MJ, Orchard S, et al. UniProt: the universal protein knowledgebase in 2023. Nucleic Acids Res. 2023;1(51):D523\u201331.","journal-title":"Nucleic Acids Res."},{"issue":"D1","key":"6081_CR20","doi-asserted-by":"publisher","first-page":"D412","DOI":"10.1093\/nar\/gkaa913","volume":"49","author":"J Mistry","year":"2021","unstructured":"Mistry J, Chuguransky S, Williams L, et al. Pfam: the protein families database in 2021. Nucleic Acids Res. 2021;49(D1):D412\u20139.","journal-title":"Nucleic Acids Res."},{"key":"6081_CR21","doi-asserted-by":"crossref","unstructured":"Schwartz AS, Hannum GJ, Dwiel ZR, et\u00a0al. Deep semantic protein representation for annotation, discovery, and engineering. bioRxiv. 2018;.","DOI":"10.1101\/365965"},{"issue":"1","key":"6081_CR22","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/nmeth.3176","volume":"12","author":"B Buchfink","year":"2015","unstructured":"Buchfink B, Xie C, Huson DH. Fast and sensitive protein alignment using DIAMOND. Nat Methods. 2015;12(1):59\u201360.","journal-title":"Nat Methods."},{"key":"6081_CR23","first-page":"118","volume":"4","author":"A Rives","year":"2021","unstructured":"Rives A, Meier J, Sercu T, et al. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci. 2021;4:118.","journal-title":"Proc Natl Acad Sci."},{"issue":"6637","key":"6081_CR24","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","volume":"379","author":"Z Lin","year":"2023","unstructured":"Lin Z, Akin H, Rao R, et al. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science. 2023;379(6637):1123\u201330.","journal-title":"Science."},{"issue":"10","key":"6081_CR25","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","volume":"44","author":"A Elnaggar","year":"2022","unstructured":"Elnaggar A, Heinzinger M, Dallago C, et al. ProtTrans: toward understanding the language of life through self-supervised learning. IEEE Trans Pattern Anal Mach Intell. 2022;44(10):7112\u201327.","journal-title":"IEEE Trans Pattern Anal Mach Intell."},{"issue":"4","key":"6081_CR26","doi-asserted-by":"publisher","first-page":"bbac232","DOI":"10.1093\/bib\/bbac232","volume":"23","author":"E Fenoy","year":"2022","unstructured":"Fenoy E, Edera AA, Stegmayer G. Transfer learning in proteins: evaluating novel protein learned representations for bioinformatics tasks. Brief Bioinf. 2022;23(4):bbac232.","journal-title":"Brief Bioinf."},{"issue":"7","key":"6081_CR27","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1038\/s41592-019-0437-4","volume":"16","author":"M Steinegger","year":"2019","unstructured":"Steinegger M, Mirdita M, S\u00f6ding J. Protein-level assembly increases protein sequence recovery from metagenomic samples many fold. Nature methods. 2019;16(7):603\u20136.","journal-title":"Nature methods."},{"key":"6081_CR28","unstructured":"Wehrmann J, Cerri R, Barros R. Hierarchical multi-label classification networks. In: Dy J, Krause A, editors. Proc. 35th ICML. vol.\u00a080 of Proc. Mach. Learn. Res.; 2018. p. 5075\u20135084."},{"key":"6081_CR29","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/978-3-642-23808-6_10","volume-title":"Machine learning and knowledge discovery in databases","author":"K Sechidis","year":"2011","unstructured":"Sechidis K, Tsoumakas G, Vlahavas I. On the stratification of multi-label data. In: Gunopulos D, Hofmann T, Malerba D, Vazirgiannis M, editors. Machine learning and knowledge discovery in databases. Berlin Heidelberg: Springer; 2011. p. 145\u201358."},{"issue":"23","key":"6081_CR30","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1093\/bioinformatics\/bts565","volume":"28","author":"L Fu","year":"2012","unstructured":"Fu L, Niu B, Zhu Z, Wu S, Li W. CD-HIT: accelerated for clustering the next-generation sequencing data. Bioinformatics. 2012;28(23):3150\u20132.","journal-title":"Bioinformatics."},{"issue":"7706","key":"6081_CR31","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1038\/s41586-018-0124-0","volume":"557","author":"MN Price","year":"2018","unstructured":"Price MN, Wetmore KM, Waters RJ, et al. Mutant phenotypes for thousands of bacterial genes of unknown function. Nature. 2018;557(7706):503\u20139.","journal-title":"Nature."},{"key":"6081_CR32","doi-asserted-by":"crossref","unstructured":"Choudhuri S. In: sequence alignment and similarity searching in genomic databases. Elsevier; 2014. p. 133\u2013155.","DOI":"10.1016\/B978-0-12-410471-6.00006-2"},{"issue":"13","key":"6081_CR33","doi-asserted-by":"publisher","first-page":"i53","DOI":"10.1093\/bioinformatics\/btt228","volume":"29","author":"WT Clark","year":"2013","unstructured":"Clark WT, Radivojac P. Information-theoretic evaluation of predicted ontological annotations. Bioinformatics. 2013;29(13):i53\u201361.","journal-title":"Bioinformatics."},{"issue":"1","key":"6081_CR34","first-page":"vbae043","volume":"4","author":"D Piovesan","year":"2024","unstructured":"Piovesan D, Zago D, Joshi P, De Paolis Kaluza MC, Mehdiabadi M, Ramola R, et al. CAFA-evaluator: a python tool for benchmarking ontological classification methods. Bioinf Adv. 2024;4(1):vbae043.","journal-title":"Bioinf Adv."},{"issue":"6","key":"6081_CR35","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1038\/s41587-021-01179-w","volume":"40","author":"M Bileschi","year":"2022","unstructured":"Bileschi M, Belanger D, Bryant D, et al. Using deep learning to annotate the protein universe. Nat Biotech. 2022;40(6):932\u20137.","journal-title":"Nat Biotech."},{"issue":"17","key":"6081_CR36","doi-asserted-by":"publisher","first-page":"9443","DOI":"10.1039\/D0CS01551B","volume":"50","author":"C Crowe","year":"2021","unstructured":"Crowe C, Molyneux S, Sharma SV, Zhang Y, Gkotsi DS, Connaris H, et al. Halogenases: a palette of emerging opportunities for synthetic biology-synthetic chemistry and C-H functionalisation. Chem Soc Rev. 2021;50(17):9443\u201381.","journal-title":"Chem Soc Rev."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06081-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-025-06081-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-025-06081-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,28]],"date-time":"2025-02-28T12:38:57Z","timestamp":1740746337000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-025-06081-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,2,27]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6081"],"URL":"https:\/\/doi.org\/10.1186\/s12859-025-06081-9","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,2,27]]},"assertion":[{"value":"2 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 February 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no Conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"68"}}