{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T07:49:06Z","timestamp":1791964146460,"version":"4.3.4"},"reference-count":127,"publisher":"Wiley","issue":"19","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["https:\/\/doi.org\/10.61686\/ZXZCQ29832"],"award-info":[{"award-number":["https:\/\/doi.org\/10.61686\/ZXZCQ29832"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["chemistry-europe.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["ChemBioChem"],"published-print":{"date-parts":[[2026,10,14]]},"abstract":"<jats:p>Machine learning has become an increasingly powerful tool in enzyme discovery, enabling the prediction of enzyme activity, substrate scope, and functional specificity across diverse protein families. However, many reported models rely on narrowly sampled datasets and task\u2010specific benchmarks, limiting their robustness and generalizability to distantly related enzymes or novel chemical substrates. In this concept article, we provide a practical, best\u2010practice\u2013oriented perspective on developing enzyme family\u2010 or class\u2010specific machine learning (ML) predictors with an emphasis on data quality, representation, and model interpretability. We first discuss strategies for assembling biochemical datasets from literature, highlighting common sources of bias, redundancy, and uncertainty impacting downstream model performance. We then outline key considerations for generating new experimental data that are better suited for ML applications, including dataset design and coverage of enzyme and chemical space. Next, we summarize core computational steps involved in constructing enzyme and substrate representations, training and testing predictive models, and analyzing learned embedding spaces. Finally, we discuss outstanding technical challenges, such as mitigating taxonomic sampling bias, computing representations of enzymes with cofactors and post\u2010translational modifications, and integrating predictions into design\u2013build\u2013test\u2013learn cycles for real\u2010world applications.<\/jats:p>","DOI":"10.1002\/cbic.70568","type":"journal-article","created":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T06:33:30Z","timestamp":1791614010000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting Functional Diversity Within Enzyme Families: A Practical Perspective"],"prefix":"10.1002","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4129-2890","authenticated-orcid":false,"given":"Nika","family":"Sokolova","sequence":"first","affiliation":[{"name":"Department of Health Sciences and Technology ETH Z\u00fcrich  Z\u00fcrich Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1361-1508","authenticated-orcid":false,"given":"Kristina","family":"Haslinger","sequence":"additional","affiliation":[{"name":"Department of Chemical and Pharmaceutical Biology University of Groningen  Groningen The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbae289"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2025.03.003"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf635"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tem.2024.02.018"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbad439"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010021\u201023303\u20109"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010023\u201006622\u20103"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.5c04814"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.5c00949"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1012100"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.checat.2024.101094"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41929\u2010022\u201000798\u2010z"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201039840\u20104"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201044113\u20101"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201047613\u2010w"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201051511\u20106"},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201038347\u20102"},{"key":"e_1_2_10_19_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c02357"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010025\u201009697\u20102"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaf343"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx400"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr323"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/bs.mie.2025.11.001"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae033"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1093\/synbio\/ysaa004"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010022\u201028536\u2010w"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.synbio.2024.02.006"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sbi.2025.103070"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009853"},{"key":"e_1_2_10_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.coche.2025.101208"},{"key":"e_1_2_10_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1025"},{"key":"e_1_2_10_33_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku989"},{"key":"e_1_2_10_34_1","doi-asserted-by":"crossref","first-page":"baaa065","DOI":"10.1093\/database\/baaa065","article-title":"EnzyMine: A Comprehensive Database for Enzyme Function Annotation With Enzymatic Reaction Chemical Feature","volume":"2023","author":"Sun D.","year":"2020","journal-title":"Database: The Journal of Biological Databases and Curation"},{"key":"e_1_2_10_35_1","doi-asserted-by":"publisher","DOI":"10.3390\/ijms242316918"},{"key":"e_1_2_10_36_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.adf2465"},{"key":"e_1_2_10_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.crbiot.2021.12.002"},{"key":"e_1_2_10_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201049587\u20101"},{"key":"e_1_2_10_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010022\u201035237\u2010x"},{"key":"e_1_2_10_40_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.4c01583"},{"key":"e_1_2_10_41_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkag656"},{"key":"e_1_2_10_42_1","doi-asserted-by":"publisher","DOI":"10.1021\/jacsau.5c01636"},{"key":"e_1_2_10_43_1","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.5c08076"},{"key":"e_1_2_10_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010025\u201058521\u2010y"},{"key":"e_1_2_10_45_1","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.54532"},{"key":"e_1_2_10_46_1","doi-asserted-by":"publisher","DOI":"10.1039\/D4DD00338A"},{"key":"e_1_2_10_47_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa275"},{"key":"e_1_2_10_48_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btab551"},{"key":"e_1_2_10_49_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad046"},{"key":"e_1_2_10_50_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty1051"},{"key":"e_1_2_10_51_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac083"},{"key":"e_1_2_10_52_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btad235"},{"key":"e_1_2_10_53_1","doi-asserted-by":"publisher","DOI":"10.1039\/D3SC02752J"},{"key":"e_1_2_10_54_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41589\u2010018\u20100154\u20109"},{"key":"e_1_2_10_55_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010025\u201009519\u20105"},{"key":"e_1_2_10_56_1","doi-asserted-by":"publisher","DOI":"10.1002\/anie.v64.44"},{"key":"e_1_2_10_57_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.v89.3"},{"key":"e_1_2_10_58_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm772"},{"key":"e_1_2_10_59_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku1267"},{"key":"e_1_2_10_60_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btt627"},{"key":"e_1_2_10_61_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010022\u201005575\u20103"},{"key":"e_1_2_10_62_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkn663"},{"key":"e_1_2_10_63_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1423570112"},{"key":"e_1_2_10_64_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00835"},{"key":"e_1_2_10_65_1","doi-asserted-by":"publisher","DOI":"10.1002\/cbic.202100510"},{"key":"e_1_2_10_66_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.checat.2022.09.011"},{"key":"e_1_2_10_67_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmb.2014.04.013"},{"key":"e_1_2_10_68_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.1001843"},{"key":"e_1_2_10_69_1","doi-asserted-by":"publisher","DOI":"10.1111\/mbt.2010.3.issue\u20101"},{"key":"e_1_2_10_70_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1815791116"},{"key":"e_1_2_10_71_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009446"},{"key":"e_1_2_10_72_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.7b03523"},{"key":"e_1_2_10_73_1","doi-asserted-by":"publisher","DOI":"10.1002\/cbic.v16.12"},{"key":"e_1_2_10_74_1","doi-asserted-by":"publisher","DOI":"10.1038\/nchembio.1387"},{"key":"e_1_2_10_75_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.3c02498"},{"key":"e_1_2_10_76_1","doi-asserted-by":"publisher","DOI":"10.1002\/pro.v34.9"},{"key":"e_1_2_10_77_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.03.03.641178"},{"key":"e_1_2_10_78_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae756"},{"key":"e_1_2_10_79_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa372"},{"key":"e_1_2_10_80_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6c00090"},{"key":"e_1_2_10_81_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.4c02322"},{"key":"e_1_2_10_82_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1000605"},{"key":"e_1_2_10_83_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.joc.3c00844"},{"key":"e_1_2_10_84_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac993"},{"key":"e_1_2_10_85_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkt1183"},{"key":"e_1_2_10_86_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkr944"},{"key":"e_1_2_10_87_1","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad992"},{"key":"e_1_2_10_88_1","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/147671"},{"key":"e_1_2_10_89_1","doi-asserted-by":"publisher","DOI":"10.1039\/D3GC02384B"},{"key":"e_1_2_10_90_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010025\u201002836\u20100"},{"key":"e_1_2_10_91_1","first-page":"315","volume-title":"Methods Enzymol","author":"Copp J. N.","year":"2019"},{"key":"e_1_2_10_92_1","doi-asserted-by":"publisher","DOI":"10.1038\/nprot.2012.004"},{"key":"e_1_2_10_93_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btag043"},{"key":"e_1_2_10_94_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586\u2010021\u201003819\u20102"},{"key":"e_1_2_10_95_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2025.09.039"},{"key":"e_1_2_10_96_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biotechadv.2024.108459"},{"key":"e_1_2_10_97_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201055462\u2010w"},{"key":"e_1_2_10_98_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321\u2010025\u201001099\u2010w"},{"key":"e_1_2_10_99_1","doi-asserted-by":"publisher","DOI":"10.1021\/acschembio.7b00996"},{"key":"e_1_2_10_100_1","doi-asserted-by":"publisher","DOI":"10.1093\/synbio\/ysy012"},{"key":"e_1_2_10_101_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.9b00021"},{"key":"e_1_2_10_102_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chembiol.2021.04.010"},{"key":"e_1_2_10_103_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201055399\u20100"},{"key":"e_1_2_10_104_1","doi-asserted-by":"publisher","DOI":"10.1093\/synbio\/ysab017"},{"key":"e_1_2_10_105_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.chembiol.2019.10.008"},{"key":"e_1_2_10_106_1","doi-asserted-by":"publisher","DOI":"10.1002\/bit.v120.10"},{"key":"e_1_2_10_107_1","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.00536"},{"key":"e_1_2_10_108_1","doi-asserted-by":"publisher","DOI":"10.1039\/D4NP00053F"},{"key":"e_1_2_10_109_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biotechadv.2023.108171"},{"key":"e_1_2_10_110_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010024\u201051844\u20102"},{"key":"e_1_2_10_111_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587\u2010025\u201002859\u20107"},{"key":"e_1_2_10_112_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321\u2010020\u201000460\u20105"},{"key":"e_1_2_10_113_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321\u2010024\u201000916\u2010y"},{"key":"e_1_2_10_114_1","doi-asserted-by":"publisher","DOI":"10.3390\/metabo14030154"},{"key":"e_1_2_10_115_1","doi-asserted-by":"publisher","DOI":"10.1039\/D4CS00196F"},{"key":"e_1_2_10_116_1","doi-asserted-by":"publisher","DOI":"10.1021\/jacsau.4c01101"},{"key":"e_1_2_10_117_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010019\u201013633\u20100"},{"key":"e_1_2_10_118_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467\u2010023\u201037958\u2010z"},{"key":"e_1_2_10_119_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42004\u2010023\u201001054\u20106"},{"key":"e_1_2_10_120_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13321\u2010024\u201000817\u20100"},{"key":"e_1_2_10_121_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.5c02428"},{"key":"e_1_2_10_122_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biotechadv.2025.108698"},{"key":"e_1_2_10_123_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac496"},{"key":"e_1_2_10_124_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pisc.2014.02.012"},{"key":"e_1_2_10_125_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41929\u2010024\u201001261\u2010x"},{"key":"e_1_2_10_126_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010022\u201001763\u20101"},{"key":"e_1_2_10_127_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11831\u2010025\u201010444\u2010z"},{"key":"e_1_2_10_128_1","doi-asserted-by":"publisher","DOI":"10.1101\/2025.03.30.645636"}],"container-title":["ChemBioChem"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/chemistry-europe.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cbic.70568","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/chemistry-europe.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cbic.70568","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/chemistry-europe.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cbic.70568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T07:34:08Z","timestamp":1791963248000},"score":1,"resource":{"primary":{"URL":"https:\/\/chemistry-europe.onlinelibrary.wiley.com\/doi\/10.1002\/cbic.70568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":127,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2026,10,14]]}},"alternative-id":["10.1002\/cbic.70568"],"URL":"https:\/\/doi.org\/10.1002\/cbic.70568","archive":["Portico"],"relation":{},"ISSN":["1439-4227","1439-7633"],"issn-type":[{"value":"1439-4227","type":"print"},{"value":"1439-7633","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]},"assertion":[{"value":"2026-01-31","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70568"}}