{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T18:55:51Z","timestamp":1792176951594,"version":"4.4.0"},"reference-count":93,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Comput Chem"],"published-print":{"date-parts":[[2026,3,15]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Laccases are multi\u2010copper oxidase enzymes that oxidize a wide range of aromatic and non\u2010aromatic compounds using molecular oxygen, producing water as the sole byproduct and making them attractive biocatalysts for green chemistry. However, the ability of laccases to oxidize specific substrates depends on a complex interplay of molecular structure, enzyme properties, redox potential, and environmental context, making laccase\u2013substrate compatibility hard to predict. We apply machine learning models to pre\u2010screen laccase\u2013substrate combinations, streamlining experimental workflows. We evaluate four classical classifiers and a transformer\u2010based model (ChemBERTa) on three in\u2010house curated datasets of aromatic substrates with oxidation profiles for distinct laccases. Overall, the tested models achieve comparable performance, with random forest (RFC) demonstrating more stability across different data splits and laccases. This assessment is complemented by RFC feature\u2010importance and ChemBERTa attention analyses, which highlight molecular features associated with oxidation outcomes. We also introduce a lightweight tool to visualize ChemBERTa predictions by mapping SMILES attributions onto molecular graphs. These findings provide a robust, interpretable framework for accelerating laccase\u2013substrate discovery.<\/jats:p>","DOI":"10.1002\/jcc.70344","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T10:51:06Z","timestamp":1772967066000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning Prediction of Laccase\u2010Catalyzed Oxidation of Aromatic Compounds Using Curated Enzyme\u2010Specific Datasets"],"prefix":"10.1002","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9066-7129","authenticated-orcid":false,"given":"Yulia","family":"Kulagina","sequence":"first","affiliation":[{"name":"WoodTec Swiss Federal Laboratories for Materials Science and Technology (Empa)  D\u00fcbendorf Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Goldhahn","sequence":"additional","affiliation":[{"name":"Wood Materials Science ETH Z\u00fcrich  Z\u00fcrich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramon","family":"Weishaupt","sequence":"additional","affiliation":[{"name":"Medical Department A. Vogel AG  Roggwil Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Schubert","sequence":"additional","affiliation":[{"name":"WoodTec Swiss Federal Laboratories for Materials Science and Technology (Empa)  D\u00fcbendorf Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"e_1_2_16_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1521-401X(199805)26:3<180::AID-AHEH180>3.0.CO;2-9"},{"key":"e_1_2_16_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep10465"},{"key":"e_1_2_16_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/07388551.2017.1354353"},{"key":"e_1_2_16_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40643-021-00484-1"},{"key":"e_1_2_16_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s43393-023-00163-6"},{"key":"e_1_2_16_7_1","doi-asserted-by":"publisher","DOI":"10.1039\/C2CY20350B"},{"key":"e_1_2_16_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-014-1823-9"},{"key":"e_1_2_16_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00253-002-1047-z"},{"key":"e_1_2_16_10_1","doi-asserted-by":"publisher","DOI":"10.1128\/AEM.71.4.1775-1784.2005"},{"key":"e_1_2_16_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0924-2244(02)00155-3"},{"key":"e_1_2_16_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.orgel.2016.10.037"},{"key":"e_1_2_16_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0926-3373(00)00168-5"},{"key":"e_1_2_16_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12934-019-1248-0"},{"key":"e_1_2_16_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/10643380902945706"},{"key":"e_1_2_16_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10311-020-01081-y"},{"key":"e_1_2_16_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.enzmictec.2007.12.003"},{"key":"e_1_2_16_18_1","doi-asserted-by":"publisher","DOI":"10.1128\/AEM.01856-12"},{"key":"e_1_2_16_19_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0089924"},{"key":"e_1_2_16_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/cbic.201800064"},{"key":"e_1_2_16_21_1","doi-asserted-by":"publisher","DOI":"10.1557\/s43580-022-00304-4"},{"key":"e_1_2_16_22_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0065633"},{"key":"e_1_2_16_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-014-1826-6"},{"key":"e_1_2_16_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.micron.2003.10.029"},{"key":"e_1_2_16_25_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci049714"},{"key":"e_1_2_16_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkj067"},{"key":"e_1_2_16_27_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr777"},{"key":"e_1_2_16_28_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv951"},{"key":"e_1_2_16_29_1","doi-asserted-by":"publisher","DOI":"10.1517\/17425250902753261"},{"key":"e_1_2_16_30_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.8b00507"},{"key":"e_1_2_16_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addr.2015.03.014"},{"key":"e_1_2_16_32_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpca.3c04779"},{"key":"e_1_2_16_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ddtec.2020.11.009"},{"key":"e_1_2_16_34_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.accounts.0c00699"},{"key":"e_1_2_16_35_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.3c01250"},{"key":"e_1_2_16_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-53751-y"},{"key":"e_1_2_16_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0079-6107(98)00026-1"},{"key":"e_1_2_16_38_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat2663"},{"key":"e_1_2_16_39_1","doi-asserted-by":"publisher","DOI":"10.1039\/C9ME00039A"},{"key":"e_1_2_16_40_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00839"},{"key":"e_1_2_16_41_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01496"},{"key":"e_1_2_16_42_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.2c01191"},{"key":"e_1_2_16_43_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.chemrev.1c00033"},{"key":"e_1_2_16_44_1","unstructured":"B.Rankovi\u0107andP.Schwaller \u201cBochemian: Large Language Model Embeddings for Bayesian Optimization of Chemical Reactions \u201d inNeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World(2023)."},{"key":"e_1_2_16_45_1","unstructured":"D.Zhang W.Liu Q.Tan et\u00a0al. \u201cChemllm: A Chemical Large Language Model \u201d arXiv Preprint arXiv:2402.06852(2024)."},{"key":"e_1_2_16_46_1","doi-asserted-by":"publisher","DOI":"10.1039\/D4SC03921A"},{"key":"e_1_2_16_47_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28536-w"},{"key":"e_1_2_16_48_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41929-022-00909-w"},{"key":"e_1_2_16_49_1","doi-asserted-by":"publisher","DOI":"10.1021\/jacsau.3c00188"},{"key":"e_1_2_16_50_1","doi-asserted-by":"publisher","DOI":"10.1093\/protein\/gzac009"},{"key":"e_1_2_16_51_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci100050t"},{"key":"e_1_2_16_52_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-015-0069-3"},{"key":"e_1_2_16_53_1","doi-asserted-by":"crossref","unstructured":"L.McInnes J.Healy andJ.Melville \u201cUmap: Uniform Manifold Approximation and Projection for Dimension Reduction \u201d arXiv Preprint arXiv:1802.03426(2018).","DOI":"10.21105\/joss.00861"},{"key":"e_1_2_16_54_1","doi-asserted-by":"publisher","DOI":"10.1021\/jm9602928"},{"key":"e_1_2_16_55_1","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1603"},{"key":"e_1_2_16_56_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00237"},{"key":"e_1_2_16_57_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-41948-6"},{"key":"e_1_2_16_58_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci00007a012"},{"key":"e_1_2_16_59_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-00460-5"},{"key":"e_1_2_16_60_1","unstructured":"S.Liu H.Wang W.Liu J.Lasenby H.Guo andJ.Tang \u201cPre\u2010Training Molecular Graph Representation With 3d Geometry \u201d arXiv Preprint arXiv:2110.07728(2021)."},{"key":"e_1_2_16_61_1","doi-asserted-by":"crossref","unstructured":"J.Zhu Y.Xia L.Wu et\u00a0al. \u201cUnified 2d and 3d Pre\u2010Training of Molecular Representations \u201d inProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining Association for Computing Machinery (ACM)(2022) 2626\u20132636.","DOI":"10.1145\/3534678.3539368"},{"key":"e_1_2_16_62_1","doi-asserted-by":"publisher","DOI":"10.1021\/ci00057a005"},{"key":"e_1_2_16_63_1","unstructured":"Daylight Chemical Information Systems I \u201cSmarts\u2010a Language for Describing Molecular Patterns \u201d(2019)."},{"key":"e_1_2_16_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100588"},{"issue":"2","key":"e_1_2_16_65_1","first-page":"237","article-title":"Dragon Software: An Easy Approach to Molecular Descriptor Calculations","volume":"56","author":"Mauri A.","year":"2006","journal-title":"Match"},{"key":"e_1_2_16_66_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_2_16_67_1","unstructured":"S.Chithrananda G.Grand andB.Ramsundar \u201cChemberta: Large\u2010Scale Self\u2010Supervised Pretraining for Molecular Property Prediction \u201d arXiv Preprint arXiv:2010.09885(2020)."},{"key":"e_1_2_16_68_1","unstructured":"W.Ahmad E.Simon S.Chithrananda G.Grand andB.Ramsundar \u201cChemberta\u20102: Towards Chemical Foundation Models \u201darXiv Preprint arXiv:2209.01712 (2022)."},{"key":"e_1_2_16_69_1","unstructured":"Y.Liu M.Ott N.Goyal et\u00a0al. \u201cRoberta: A Robustly Optimized Bert Pretraining Approach \u201darXiv Preprint arXiv:1907.11692 (2019)."},{"key":"e_1_2_16_70_1","unstructured":"PyTorch Contributors \u201ctorch.nn.BCELoss \u2014 PyTorch Documentation \u201d(2024) https:\/\/pytorch.org\/docs\/stable\/generated\/torch.nn.BCELoss.html."},{"key":"e_1_2_16_71_1","first-page":"2825","article-title":"Scikit\u2010Learn: Machine Learning in Python","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_16_72_1","doi-asserted-by":"crossref","unstructured":"T.Wolf L.Debut V.Sanh et\u00a0al. \u201cTransformers: State\u2010of\u2010the\u2010Art Natural Language Processing \u201d inProceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations Association for Computational Linguistics (ACL)(2020) 38\u201345.","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_2_16_73_1","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke A.","year":"2019"},{"key":"e_1_2_16_74_1","doi-asserted-by":"crossref","unstructured":"T.Akiba S.Sano T.Yanase T.Ohta andM.Koyama \u201cOptuna: A Next\u2010Generation Hyperparameter Optimization Framework \u201d inProceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining Association for Computing Machinery (ACM)(2019) 2623\u20132631.","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_16_75_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_2_16_76_1","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"issue":"17","key":"e_1_2_16_77_1","first-page":"1","article-title":"Imbalanced\u2010Learn: A Python Toolbox to Tackle the Curse of Imbalanced Datasets in Machine Learning","volume":"18","author":"Lema\u00c3\u017dtre G.","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_16_78_1","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203451"},{"key":"e_1_2_16_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/2347736.2347755"},{"key":"e_1_2_16_80_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"e_1_2_16_81_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3229161"},{"issue":"1","key":"e_1_2_16_82_1","first-page":"1929","article-title":"Dropout: A Simple Way to Prevent Neural Networks From Overfitting","volume":"15","author":"Srivastava N.","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_16_83_1","doi-asserted-by":"publisher","DOI":"10.1021\/bi0201318"},{"key":"e_1_2_16_84_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00018-014-1824-8"},{"issue":"265","key":"e_1_2_16_85_1","first-page":"1","article-title":"Pgmpy: A Python Toolkit for Bayesian Networks","volume":"25","author":"Ankan A.","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_16_86_1","unstructured":"U. M.FayyadandK. B.Irani \u201cMulti\u2010Interval Discretization of Continuous\u2010Valued Attributes for Classification Learning \u201d inIjcai vol.93(Morgan Kaufmann 1993) 1022\u20131029."},{"key":"e_1_2_16_87_1","unstructured":"J.Vig \u201cBertviz: A Tool for Visualizing Multihead Self\u2010Attention in the Bert Model \u201d inICLR Workshop: Debugging Machine Learning Models vol.3(2019)."},{"key":"e_1_2_16_88_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5b00570"},{"key":"e_1_2_16_89_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_2_16_90_1","unstructured":"L.Xu M.Skoularidou A.Cuesta\u2010Infante andK.Veeramachaneni \u201cModeling Tabular Data Using Conditional GAN \u201dAdvances in Neural Information Processing Systems32(2019)."},{"key":"e_1_2_16_91_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00492-0"},{"key":"e_1_2_16_92_1","doi-asserted-by":"publisher","DOI":"10.3390\/math12121898"},{"key":"e_1_2_16_93_1","unstructured":"Z.Wang P.Wang K.Liu et\u00a0al. \u201cA Comprehensive Survey on Data Augmentation \u201darXiv Preprint arXiv:2405.09591 (2024)."},{"key":"e_1_2_16_94_1","volume-title":"Learning With Kernels: Support Vector Machines, Regularization, Optimization, and Beyond","author":"Sch\u00f6lkopf B.","year":"2002"}],"container-title":["Journal of Computational Chemistry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcc.70344","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/jcc.70344","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/jcc.70344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T18:42:24Z","timestamp":1792176144000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/jcc.70344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":93,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,3,15]]}},"alternative-id":["10.1002\/jcc.70344"],"URL":"https:\/\/doi.org\/10.1002\/jcc.70344","archive":["Portico"],"relation":{},"ISSN":["0192-8651","1096-987X"],"issn-type":[{"value":"0192-8651","type":"print"},{"value":"1096-987X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"2025-07-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70344"}}