{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T21:49:12Z","timestamp":1791496152609,"version":"4.3.4"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":4,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2025YFC3409900"],"award-info":[{"award-number":["2025YFC3409900"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502050"],"award-info":[{"award-number":["62502050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322215"],"award-info":[{"award-number":["62322215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62532017"],"award-info":[{"award-number":["62532017"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62672520"],"award-info":[{"award-number":["62672520"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20257"],"award-info":[{"award-number":["U24A20257"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing University of Chinese Medicine Teaching Reform Project","award":["JX-JBGS-2601020"],"award-info":[{"award-number":["JX-JBGS-2601020"]}],"id":[{"id":"https:\/\/ror.org\/05damtm70","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Shenzhen Science and Technology","award":["JCYJ20241202130212016"],"award-info":[{"award-number":["JCYJ20241202130212016"]}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2026JJ30018"],"award-info":[{"award-number":["2026JJ30018"]}],"id":[{"id":"10.13039\/501100004735","id-type":"DOI","asserted-by":"publisher"}]},{"name":"High-Performance Computing Center of Central South University","id":[{"id":"https:\/\/ror.org\/00f1zfq44","id-type":"ROR","asserted-by":"crossref"}]},{"name":"High-Performance Computing Clusters","award":["PL-17161"],"award-info":[{"award-number":["PL-17161"]}]},{"name":"Shenzhen Institutes of Advanced Technology","id":[{"id":"https:\/\/ror.org\/04gh4er46","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>The turnover number (kcat) is crucial for understanding enzyme kinetics, yet its experimental determination remains costly and low-throughput. Existing deep learning approaches often rely on single-substrate assumptions and overlook full reaction contexts or language-informed semantic representations, limiting their accuracy and generalization across diverse reactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>To address these challenges, we propose Katalyst, a knowledge-guided semantic alignment framework for kcat\u00a0prediction based on contrastive learning. Katalyst integrates enzyme sequences, protein textual descriptions, substrates and products into a shared latent space using multi-channel encoders and contrastive alignment. An interaction-aware fusion module is designed to capture complementary cross-modal information. Experimental results demonstrate that Katalyst achieved the best overall performance, with the RMSE of 0.9880, R2 of 0.5829, and SRCC of 0.7603. Compared with the State-Of-The-Art (SOTA) baselines, Katalyst reduced RMSE by 3.01% and improved R2 and SRCC by 4.72% and 2.31%, respectively. Moreover, ablation studies and evaluations across sequence scales further confirmed the effectiveness of semantic alignment and multimodal feature fusion. Overall, Katalyst provides a robust and accurate framework for kcat\u00a0prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The code and data are available at https:\/\/github.com\/liruilin-SUAT\/Katalyst.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag709","type":"journal-article","created":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T11:37:31Z","timestamp":1791027451000},"source":"Crossref","is-referenced-by-count":0,"title":["Katalyst: knowledge-guided semantic alignment via contrastive learning for enzyme turnover prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Ruilin","family":"Li","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen, 518060,","place":["China"]},{"name":"School of Computer Science and Control Engineering, Shenzhen University of Advanced Technology , Shenzhen, 518107,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senyu","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Software Engineering, Shenzhen University , Shenzhen, 518060,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaqi","family":"Deng","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Software Engineering, Southern University of Science and Technology , Shenzhen, 518055,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taixing","family":"Qiu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nanjing University , Nanjing, 210023,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8346-0798","authenticated-orcid":false,"given":"Fei","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University , Changsha, 410083,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijun","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Control Engineering, Shenzhen University of Advanced Technology , Shenzhen, 518107,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Chinese Materia Medica, Beijing University of Chinese Medicine , Beijing, 102488,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,3]]},"reference":[{"key":"2026100816511661900_btag709-B1","doi-asserted-by":"publisher","first-page":"e1012229","DOI":"10.1371\/journal.pcbi.1012229","article-title":"MTMol-GPT: de novo multi-target molecular generation with transformer-based generative adversarial imitation learning","volume":"20","author":"Ai","year":"2024","journal-title":"PLoS Comput Biol"},{"key":"2026100816511661900_btag709-B2","first-page":"19580","author":"Ai"},{"key":"2026100816511661900_btag709-B3","doi-asserted-by":"publisher","first-page":"4402","DOI":"10.1021\/bi2002289","article-title":"The moderately efficient enzyme: evolutionary and physicochemical trends shaping enzyme parameters","volume":"50","author":"Bar-Even","year":"2011","journal-title":"Biochemistry"},{"key":"2026100816511661900_btag709-B4","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1042\/bj0190338","article-title":"A note on the kinetics of enzyme action","volume":"19","author":"Briggs","year":"1925","journal-title":"Biochem J"},{"key":"2026100816511661900_btag709-B5","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1080\/09296171003643098","article-title":"Cutting the Gordian knot: the moving-average type\u2013token ratio (MATTR)","volume":"17","author":"Covington","year":"2010","journal-title":"J Quant Linguist"},{"key":"2026100816511661900_btag709-B6","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1039\/c4cs00351a","article-title":"Synthetic biology for the directed evolution of protein biocatalysts: navigating sequence space intelligently","volume":"44","author":"Currin","year":"2015","journal-title":"Chem Soc Rev"},{"key":"2026100816511661900_btag709-B7","doi-asserted-by":"publisher","first-page":"3401","DOI":"10.1073\/pnas.1514240113","article-title":"Global characterization of in vivo enzyme catalytic rates and their correspondence to in vitro k cat measurements","volume":"113","author":"Davidi","year":"2016","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026100816511661900_btag709-B8","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026100816511661900_btag709-B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2022","journal-title":"ACM Trans Comput Healthcare"},{"key":"2026100816511661900_btag709-B10","author":"Honda","year":"2019"},{"key":"2026100816511661900_btag709-B11","author":"Hu","year":"2025"},{"key":"2026100816511661900_btag709-B12","author":"Kang","year":"2025"},{"key":"2026100816511661900_btag709-B13","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026100816511661900_btag709-B14","doi-asserted-by":"publisher","first-page":"4139","DOI":"10.1038\/s41467-023-39840-4","article-title":"Turnover number predictions for kinetically uncharacterized enzymes using machine and deep learning","volume":"14","author":"Kroll","year":"2023","journal-title":"Nat Commun"},{"key":"2026100816511661900_btag709-B15","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/S0167-7799(97)01138-4","article-title":"Directed evolution of enzyme catalysts","volume":"15","author":"Kuchner","year":"1997","journal-title":"Trends Biotechnol"},{"key":"2026100816511661900_btag709-B16","doi-asserted-by":"publisher","first-page":"bbaa199","DOI":"10.1093\/bib\/bbaa199","article-title":"Semantic similarity and machine learning with ontologies","volume":"22","author":"Kulmanov","year":"2021","journal-title":"Brief Bioinform"},{"key":"2026100816511661900_btag709-B17","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41929-022-00798-z","article-title":"Deep learning-based kcat prediction enables improved enzyme-constrained model reconstruction","volume":"5","author":"Li","year":"2022","journal-title":"Nat Catal"},{"key":"2026100816511661900_btag709-B18","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.1093\/bioinformatics\/btac035","article-title":"BACPI: a bi-directional attention neural network for compound\u2013protein interaction and binding affinity prediction","volume":"38","author":"Li","year":"2022","journal-title":"Bioinformatics"},{"key":"2026100816511661900_btag709-B19","doi-asserted-by":"publisher","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":"Lin","year":"2023","journal-title":"Science"},{"key":"2026100816511661900_btag709-B20","doi-asserted-by":"publisher","first-page":"bbad393","DOI":"10.1093\/bib\/bbad393","article-title":"MVML-MPI: multi-view multi-label learning for metabolic pathway inference","volume":"24","author":"Liu","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026100816511661900_btag709-B21","doi-asserted-by":"publisher","first-page":"131230","DOI":"10.1016\/j.eswa.2026.131230","article-title":"Refprogen: a reference-guided molecular generation model with protein-ligand joint representation for property-aware drug design","volume":"309","author":"Liu","year":"2026","journal-title":"Expert Syst Appl"},{"key":"2026100816511661900_btag709-B22","doi-asserted-by":"publisher","first-page":"btaf524","DOI":"10.1093\/bioinformatics\/btaf524","article-title":"HyperPhS: a pharmacophore-guided multimodal representation framework for metabolic stability prediction through contrastive hypergraph learning","volume":"41","author":"Liu","year":"2025","journal-title":"Bioinformatics"},{"key":"2026100816511661900_btag709-B23","first-page":"18177","author":"Ma","year":"2022"},{"key":"2026100816511661900_btag709-B24","doi-asserted-by":"publisher","first-page":"bar009","DOI":"10.1093\/database\/bar009","article-title":"UniProt knowledgebase: a hub of integrated protein data","volume":"2011","author":"Magrane","year":"2011","journal-title":"Database (Oxford)"},{"key":"2026100816511661900_btag709-B25","author":"Oord","year":"2018"},{"key":"2026100816511661900_btag709-B26","doi-asserted-by":"publisher","first-page":"bbad506","DOI":"10.1093\/bib\/bbad506","article-title":"DLTKcat: deep learning-based prediction of temperature-dependent enzyme turnover rates","volume":"25","author":"Qiu","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026100816511661900_btag709-B27","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026100816511661900_btag709-B28","doi-asserted-by":"publisher","first-page":"935","DOI":"10.15252\/msb.20167411","article-title":"Improving the phenotype predictions of a yeast genome-scale metabolic model by incorporating enzymatic constraints","volume":"13","author":"S\u00e1nchez","year":"2017","journal-title":"Mol Syst Biol"},{"key":"2026100816511661900_btag709-B29","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans Neural Netw"},{"key":"2026100816511661900_btag709-B30","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.jbiotec.2017.04.020","article-title":"The BRENDA enzyme information system\u2014from a database to an expert system","volume":"261","author":"Schomburg","year":"2017","journal-title":"J Biotechnol"},{"key":"2026100816511661900_btag709-B31","doi-asserted-by":"publisher","first-page":"101094","DOI":"10.1016\/j.checat.2024.101094","article-title":"EITLEM-kinetics: a deep-learning framework for kinetic parameter prediction of mutant enzymes","volume":"4","author":"Shen","year":"2024","journal-title":"Chem Catal"},{"key":"2026100816511661900_btag709-B32","doi-asserted-by":"publisher","first-page":"2292","DOI":"10.1111\/febs.16404","article-title":"A guide to enzyme kinetics in early drug discovery","volume":"290","author":"Srinivasan","year":"2023","journal-title":"FEBS J"},{"key":"2026100816511661900_btag709-B33","doi-asserted-by":"publisher","first-page":"110348","DOI":"10.1016\/j.compbiomed.2025.110348","article-title":"A multimodal deep learning framework for enzyme turnover prediction with missing modality","volume":"193","author":"Sun","year":"2025","journal-title":"Comput Biol Med"},{"key":"2026100816511661900_btag709-B34","volume-title":"Certain Language Skills in Children; Their Development and Interrelationships","author":"Templin"},{"key":"2026100816511661900_btag709-B35","doi-asserted-by":"publisher","first-page":"bbad493","DOI":"10.1093\/bib\/bbad493","article-title":"Opportunities and challenges for ChatGpt and large language models in biomedicine and health","volume":"25","author":"Tian","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026100816511661900_btag709-B36","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026100816511661900_btag709-B37","author":"Veli\u010dkovi\u0107"},{"key":"2026100816511661900_btag709-B38","first-page":"1132","author":"Wang"},{"key":"2026100816511661900_btag709-B39","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"Smiles, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"key":"2026100816511661900_btag709-B40","doi-asserted-by":"publisher","first-page":"D656","DOI":"10.1093\/nar\/gkx1065","article-title":"SABIO-RK: an updated resource for manually curated biochemical reaction kinetics","volume":"46","author":"Wittig","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2026100816511661900_btag709-B41","doi-asserted-by":"publisher","first-page":"938","DOI":"10.1021\/ar000058i","article-title":"The depth of chemical time and the power of enzymes as catalysts","volume":"34","author":"Wolfenden","year":"2001","journal-title":"Acc Chem Res"},{"key":"2026100816511661900_btag709-B42","doi-asserted-by":"publisher","first-page":"e70547","DOI":"10.1002\/pro.70547","article-title":"Proteinmcp: an agentic AI framework for autonomous protein engineering","volume":"35","author":"Xu","year":"2026","journal-title":"Protein Sci"},{"key":"2026100816511661900_btag709-B43","author":"Yang","year":"2025"},{"key":"2026100816511661900_btag709-B44","doi-asserted-by":"publisher","first-page":"8211","DOI":"10.1038\/s41467-023-44113-1","article-title":"UniKP: a unified framework for the prediction of enzyme kinetic parameters","volume":"14","author":"Yu","year":"2023","journal-title":"Nat Commun"},{"key":"2026100816511661900_btag709-B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3777411","article-title":"Instruction tuning for large language models: a survey","volume":"58","author":"Zhang","year":"2026","journal-title":"ACM Comput Surv"},{"key":"2026100816511661900_btag709-B46","doi-asserted-by":"publisher","first-page":"101535","DOI":"10.1016\/j.cels.2026.101535","article-title":"Context-informed subgraph foundation models enable interpretable protein-function prediction","volume":"17","author":"Zhou","year":"2026","journal-title":"Cell Syst"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag709\/71581565\/btag709.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/10\/btag709\/71581565\/btag709.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/10\/btag709\/71581565\/btag709.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T20:51:26Z","timestamp":1791492686000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag709\/8860687"}},"subtitle":[],"editor":[{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":46,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag709","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,10]]},"article-number":"btag709"}}