{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:19:15Z","timestamp":1789395555413,"version":"build-2803163510"},"reference-count":45,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province","doi-asserted-by":"publisher","award":["BK20250960"],"award-info":[{"award-number":["BK20250960"]}],"id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506176"],"award-info":[{"award-number":["62506176"]}],"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":["62576178"],"award-info":[{"award-number":["62576178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of the Jiangsu Higher Education Institutions of China","award":["25KJB520041"],"award-info":[{"award-number":["25KJB520041"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The enzyme kinetic parameters, including the turnover number, Michaelis constant, and inhibition constant, are key metrics for assessing catalytic performance. Although deep learning models have recently incorporated multimodal information from enzymes and substrates to predict these parameters, several obstacles still persist. First, current data sets suffer from limited size, inconsistency, and a lack of unified standards. Second, most existing approaches prioritize cross-modal consistency but fail to sufficiently exploit the unique information residing in each individual modality. Meanwhile, although a limited number of studies have recognized that collaborative exploration of shared and specific information can enhance model performance, these methods remain difficult to directly apply to enzyme\u2013substrate pairs, as enzyme\u2013substrate relationships are inherently interactive rather than semantically equivalent counterparts. Third, the measured kinetic parameters are often unevenly distributed, which severely undermines the predictive accuracy of existing models when dealing with extreme value ranges. To resolve the above challenges, we first compile Kinetic-DB, a large-scale and consistently formatted data set from public resources. Building upon this data set, we develop GAPEK, a new framework for estimating enzyme kinetic parameters. In particular, an adaptive data augmentation module is devised to enrich the diversity of both enzyme and substrate sequences, thereby alleviating the adverse effects of data imbalance. Subsequently, we perform feature extraction using two pretrained models, ESM-2 for enzymes and Mole-BERT for substrates, to obtain multimodal embeddings. To decouple these complex interacting features, we introduce a tailored dual information exploration module to capture both modality-specific and cross-modal information, further refined by domain classification and distribution alignment loss functions. To explicitly handle the imbalanced data distribution, our base model, GAPEK, incorporates an adaptive density-weighted loss function. Building on this, we propose GAPEK+, which integrates the Squared Error Relevance Area (SERA) function to reconfigure the learning objective. By prioritizing high-relevance regions, GAPEK+ effectively calibrates the model\u2019s sensitivity to rare but critical extreme values, substantially mitigating the prediction bias inherent in heavy-tailed regression tasks. Experimental results demonstrate that both GAPEK and GAPEK+ achieve superior performance over existing state-of-the-art approaches, particularly across extreme parameter ranges, highlighting their potential as valuable tools applicable to enzyme engineering, synthetic biology, and drug discovery.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c02546","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T03:27:32Z","timestamp":1788406052000},"page":"11527-11541","source":"Crossref","is-referenced-by-count":0,"title":["GAPEK: A General\nFramework for Multiparameter Enzyme\nKinetic Prediction with Adaptive Learning"],"prefix":"10.1021","volume":"66","author":[{"given":"Chenghao","family":"Zhu","sequence":"first","affiliation":[{"name":"Nantong University , , , ,","place":["Nantong, Jiangsu, China, 226019"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiping","family":"Ding","sequence":"additional","affiliation":[{"name":"Nantong University , , , ,","place":["Nantong, Jiangsu, China, 226019"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5785-7363","authenticated-orcid":true,"given":"Wei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nantong University , , , ,","place":["Nantong, Jiangsu, China, 226019"]},{"name":"Jiangnan University , , , ,","place":["Wuxi, Jiangsu, China, 214122"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5921-8512","authenticated-orcid":true,"given":"Shu","family":"Jiang","sequence":"additional","affiliation":[{"name":"Nantong University , , , ,","place":["Nantong, Jiangsu, China, 226019"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Zhou","sequence":"additional","affiliation":[{"name":"Jiangnan University , , , ,","place":["Wuxi, Jiangsu, China, 214122"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohong","family":"Deng","sequence":"additional","affiliation":[{"name":"Jiangnan University , , , ,","place":["Wuxi, Jiangsu, China, 214122"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6786-8053","authenticated-orcid":true,"given":"Dong-Jun","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University of Science and Technology , , ,","place":["Nanjing, China, 210014"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Liu","sequence":"additional","affiliation":[{"name":"Nantong University , , , ,","place":["Nantong, Jiangsu, China, 226019"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,31]]},"reference":[{"issue":"1","key":"2026091409083401700_cit1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.17113\/ftb.56.01.18.5491","article-title":"Applications of microbial\nenzymes in food industry","volume":"56","author":"Raveendran","year":"2018","journal-title":"Food Technol. Biotechnol."},{"key":"2026091409083401700_cit2","doi-asserted-by":"publisher","first-page":"1447","DOI":"10.1016\/j.rser.2014.09.035","article-title":"Advances in\nsynthesis of biodiesel via enzyme catalysis: Novel and sustainable\napproaches","volume":"41","author":"Guldhe","year":"2015","journal-title":"Renewable Sustainable Energy Rev."},{"issue":"4","key":"2026091409083401700_cit3","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1002\/bab.1919","article-title":"Enzymes for pharmaceutical\nand therapeutic applications","volume":"67","author":"Meghwanshi","year":"2020","journal-title":"Biotechnol. Appl.\nBiochem."},{"issue":"3","key":"2026091409083401700_cit4","doi-asserted-by":"publisher","first-page":"231","DOI":"10.2174\/138920006776359329","article-title":"A literature\nreview of enzyme kinetic parameters for CYP3A4-mediated metabolic\nreactions of 113 drugs in human liver microsomes: structure-kinetics\nrelationship assessment","volume":"7","author":"Bu","year":"2006","journal-title":"Curr. Drug Metab."},{"issue":"5","key":"2026091409083401700_cit5","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1039\/C4CS00351A","article-title":"Synthetic biology\nfor the directed evolution of protein biocatalysts: navigating sequence\nspace intelligently","volume":"44","author":"Currin","year":"2015","journal-title":"Chem. Soc. Rev."},{"issue":"12","key":"2026091409083401700_cit6","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/S0167-7799(97)01138-4","article-title":"Directed evolution\nof enzyme catalysts","volume":"15","author":"Kuchner","year":"1997","journal-title":"Trends Biotechnol."},{"issue":"5989","key":"2026091409083401700_cit7","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1126\/science.1190239","article-title":"Computational design of an enzyme\ncatalyst for a stereoselective bimolecular Diels-Alder reaction","volume":"329","author":"Siegel","year":"2010","journal-title":"Science"},{"issue":"7983","key":"2026091409083401700_cit8","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1038\/s41586-023-06510-w","article-title":"Clustering predicted structures at the scale of the\nknown protein universe","volume":"622","author":"Barrio-Hernandez","year":"2023","journal-title":"Nature"},{"issue":"7873","key":"2026091409083401700_cit9","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction\nwith AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026091409083401700_cit10","doi-asserted-by":"publisher","first-page":"5411","DOI":"10.1021\/acs.jcim.5c00526","article-title":"Advancing Enzyme Optimal pH Prediction via Retrieved\nEmbedding Data Augmentation","volume":"65","author":"Zhang","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"1","key":"2026091409083401700_cit11","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1109\/TCBB.2023.3337158","article-title":"MVDINET: A Novel Multi-Level Enzyme\nFunction Predictor With Multi-View Deep Interactive Learning","volume":"21","author":"Tang","year":"2024","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"2026091409083401700_cit12","first-page":"574","volume-title":"AMTL-RFC: A multi-task learning based method\nfor evaluating\nthe feasibility of enzymatic reactions","author":"Liu","year":"2023"},{"issue":"1","key":"2026091409083401700_cit13","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s12967-023-03876-3","article-title":"DeepMPF: deep\nlearning framework for predicting drug\u2013target interactions\nbased on multi-modal representation with meta-path semantic analysis","volume":"21","author":"Ren","year":"2023","journal-title":"J. Transl. Med."},{"issue":"8","key":"2026091409083401700_cit14","doi-asserted-by":"publisher","first-page":"662","DOI":"10.1038\/s41929-022-00798-z","article-title":"Deep learning-based\nk cat prediction enables improved enzyme-constrained model reconstruction","volume":"5","author":"Li","year":"2022","journal-title":"Nat. Catal."},{"issue":"1","key":"2026091409083401700_cit15","doi-asserted-by":"publisher","first-page":"8211","DOI":"10.1038\/s41467-023-44113-1","article-title":"UniKP: a unified\nframework for the prediction of enzyme kinetic parameters","volume":"14","author":"Yu","year":"2023","journal-title":"Nat. Commun."},{"issue":"5","key":"2026091409083401700_cit16","doi-asserted-by":"publisher","first-page":"bbae387","DOI":"10.1093\/bib\/bbae387","article-title":"MPEK: a multitask deep\nlearning framework based on pretrained language models for enzymatic\nreaction kinetic parameters prediction","volume":"25","author":"Wang","year":"2024","journal-title":"Briefings\nBioinf."},{"issue":"1","key":"2026091409083401700_cit17","doi-asserted-by":"publisher","first-page":"2072","DOI":"10.1038\/s41467-025-57215-9","article-title":"CatPred: a comprehensive\nframework for deep learning\nin vitro enzyme kinetic parameters","volume":"16","author":"Boorla","year":"2025","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091409083401700_cit18","doi-asserted-by":"publisher","first-page":"2736","DOI":"10.1038\/s41467-025-58038-4","article-title":"Robust enzyme discovery\nand engineering with deep learning using CataPro","volume":"16","author":"Wang","year":"2025","journal-title":"Nat. Commun."},{"key":"2026091409083401700_cit19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1042\/bse0590001","article-title":"Enzymes:\nprinciples and biotechnological applications","volume":"59","author":"Robinson","year":"2015","journal-title":"Essays Biochem."},{"key":"2026091409083401700_cit20","doi-asserted-by":"publisher","first-page":"14031","DOI":"10.1109\/TNNLS.2023.3274289","article-title":"One-step multiview\nfuzzy clustering with collaborative learning between common and specific\nhidden space information","volume":"35","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural\nNetworks Leran. Syst."},{"key":"2026091409083401700_cit21","doi-asserted-by":"publisher","first-page":"15878","DOI":"10.1109\/CVPR52729.2023.01524","volume-title":"Multi-modal learning with missing modality via shared-specific\nfeature modelling","author":"Wang","year":"2023"},{"issue":"7","key":"2026091409083401700_cit22","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s10462-025-11183-0","article-title":"Dual representation\nlearning for one-step clustering of multi-view data","volume":"58","author":"Zhang","year":"2025","journal-title":"Artif. Intell. Rev."},{"issue":"1","key":"2026091409083401700_cit23","doi-asserted-by":"publisher","first-page":"bbad506","DOI":"10.1093\/bib\/bbad506","article-title":"DLTKcat: deep\nlearning-based prediction\nof temperature-dependent enzyme turnover rates","volume":"25","author":"Qiu","year":"2024","journal-title":"Briefings Bioinf."},{"issue":"D1","key":"2026091409083401700_cit24","doi-asserted-by":"publisher","first-page":"D790","DOI":"10.1093\/nar\/gkr1046","article-title":"SABIO-RK--database for\nbiochemical reaction kinetics","volume":"40","author":"Wittig","year":"2012","journal-title":"Nucleic Acids\nRes."},{"issue":"D1","key":"2026091409083401700_cit25","doi-asserted-by":"publisher","first-page":"D498","DOI":"10.1093\/nar\/gkaa1025","article-title":"the ELIXIR\ncore data resource in 2021: new developments and updates","volume":"49","author":"Chang","year":"2021","journal-title":"Nucleic Acids Res."},{"key":"2026091409083401700_cit26","doi-asserted-by":"crossref","first-page":"1542","DOI":"10.1109\/BIBM66473.2025.11356302","article-title":"ADKcat: Enhanced Enzyme Turnover Number\nPrediction\nwith Adaptive Data Augmentation and Dual Information Exploration","volume-title":"2025 IEEE International Conference on Bioinformatics\nand Biomedicine (BIBM)","author":"Zhu","year":"2025"},{"issue":"D1","key":"2026091409083401700_cit27","doi-asserted-by":"publisher","first-page":"D204","DOI":"10.1093\/nar\/gku989","article-title":"UniProt: a\nhub for protein information","volume":"43","author":"Consortium","year":"2015","journal-title":"Nucleic Acids Res."},{"issue":"D1","key":"2026091409083401700_cit28","doi-asserted-by":"publisher","first-page":"D1388","DOI":"10.1093\/nar\/gkaa971","article-title":"PubChem\nin 2021: new\ndata content and improved web interfaces","volume":"49","author":"Kim","year":"2021","journal-title":"Nucleic\nAcids Res."},{"issue":"31.10","key":"2026091409083401700_cit29","first-page":"5281","article-title":"RDKit: A software\nsuite for cheminformatics, computational chemistry, and predictive\nmodeling","volume":"8","author":"Landrum","year":"2013","journal-title":"Greg Landrum"},{"issue":"1","key":"2026091409083401700_cit30","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/1758-2946-4-22","article-title":"Towards\na Universal SMILES representation-A standard method to generate canonical\nSMILES based on the InChI","volume":"4","author":"O\u2019Boyle","year":"2012","journal-title":"J. Cheminform."},{"issue":"19","key":"2026091409083401700_cit31","doi-asserted-by":"publisher","first-page":"7246","DOI":"10.1073\/pnas.0600605103","article-title":"Despite slow catalysis\nand confused\nsubstrate specificity, all ribulose bisphosphate carboxylases may\nbe nearly perfectly optimized","volume":"103","author":"Tcherkez","year":"2006","journal-title":"Proc. Natl. Acad.\nSci. U. S. A."},{"key":"2026091409083401700_cit32","doi-asserted-by":"publisher","first-page":"2187","DOI":"10.1007\/s10994-021-06023-5","article-title":"Density-based\nweighting for imbalanced regression","volume":"110","author":"Steininger","year":"2021","journal-title":"Mach. Learn."},{"key":"2026091409083401700_cit33","doi-asserted-by":"publisher","DOI":"10.1101\/2021.02.18.431877","article-title":"Improving generalizability\nof protein sequence models with data augmentations","author":"Shen","year":"2021","journal-title":"bioRxiv"},{"key":"2026091409083401700_cit34","volume-title":"Multi-Modal Contrastive Learning for Proteins\nby Combining Domain-Informed Views","author":"Xu","year":"2024"},{"issue":"1","key":"2026091409083401700_cit35","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1038\/s43588-023-00576-2","article-title":"Unbiased organism-agnostic\nand highly sensitive signal peptide predictor with deep protein language\nmodel","volume":"4","author":"Shen","year":"2024","journal-title":"Nat. Comput. Sci."},{"issue":"6637","key":"2026091409083401700_cit36","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction\nof atomic-level protein structure with\na language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026091409083401700_cit37","volume-title":"Mole-bert: Rethinking\npre-training graph neural networks for molecules","author":"Xia","year":"2023"},{"issue":"9","key":"2026091409083401700_cit38","doi-asserted-by":"publisher","first-page":"1939","DOI":"10.3390\/app9091939","article-title":"Two-level attentions\nand grouping attention convolutional network for fine-grained image\nclassification","volume":"9","author":"Yang","year":"2019","journal-title":"Appl. Sci."},{"key":"2026091409083401700_cit39","first-page":"30","article-title":"Attention\nis all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"6","key":"2026091409083401700_cit40","doi-asserted-by":"publisher","first-page":"bbac446","DOI":"10.1093\/bib\/bbac446","article-title":"CoaDTI: multi-modal co-attention based framework for\ndrug\u2013target interaction annotation","volume":"23","author":"Huang","year":"2022","journal-title":"Briefings\nBioinf."},{"issue":"9","key":"2026091409083401700_cit41","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s10994-020-05900-9","article-title":"Imbalanced regression\nand extreme value prediction","volume":"109","author":"Ribeiro","year":"2020","journal-title":"Mach. Learn."},{"key":"2026091409083401700_cit42","first-page":"3","volume-title":"Model optimization in\nimbalanced regression","author":"Silva","year":"2022"},{"issue":"1","key":"2026091409083401700_cit43","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1038\/s42003-023-05523-5","article-title":"Computational design\nof highly efficient thermostable\nMHET hydrolases and dual enzyme system for PET recycling","volume":"6","author":"Zhang","year":"2023","journal-title":"Commun. Biol."},{"issue":"1","key":"2026091409083401700_cit44","doi-asserted-by":"publisher","first-page":"6211","DOI":"10.1038\/s41467-025-61599-z","article-title":"Harnessing protein language model\nfor structure-based discovery of highly efficient and robust PET hydrolases","volume":"16","author":"Wu","year":"2025","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091409083401700_cit45","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1021\/acssynbio.5c00745","article-title":"Computational\nRedesign of Thermo-Resistant MHETase\nfor Complete Polyethylene Terephthalate Degradation by Dual-Enzyme\nSystem","volume":"15","author":"Zheng","year":"2026","journal-title":"ACS Synth. Biol."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c02546","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11527\/68001248\/acs.jcim.6c02546.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/11527\/68001248\/acs.jcim.6c02546.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:29:45Z","timestamp":1789392585000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/11527\/5385492\/GAPEK-A-General-Framework-for-Multiparameter"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,31]]},"references-count":45,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,31]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c02546","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,31]]}}}