{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:45:53Z","timestamp":1792053953117,"version":"4.4.0"},"reference-count":39,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["CHE-2505932"],"award-info":[{"award-number":["CHE-2505932"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["DBI-2400058"],"award-info":[{"award-number":["DBI-2400058"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"U.S. National Science Foundation","doi-asserted-by":"publisher","award":["OISE-2435374"],"award-info":[{"award-number":["OISE-2435374"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010548","name":"National Center for Supercomputing Applications","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010548","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Advanced Cyberinfrastructure Coordination Ecosystem: Services"},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2138259"],"award-info":[{"award-number":["2138259"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2138286"],"award-info":[{"award-number":["2138286"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2138307"],"award-info":[{"award-number":["2138307"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2137603"],"award-info":[{"award-number":["2137603"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["2138296"],"award-info":[{"award-number":["2138296"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Enzyme function annotation is critical for decoding biological systems and enabling rational enzyme design. However, experimentally characterized enzyme functions remain available for only a small fraction of known protein sequences, resulting in a widening gap between rapidly expanding sequence space and reliable functional assignments. Recent advances in artificial intelligence (AI) have accelerated enzyme function annotation by facilitating accurate and high-throughput prediction from protein sequences. Here, we present CLEAN Database (CLEAN DB), a comprehensive resource encompassing &amp;gt;55 million enzyme function annotations across 1\u2009098\u2009305 strains, predicted by the CLEAN AI model. The database features an intuitive web interface that enables users to efficiently search, explore, and download enzyme function data through flexible query options. Additionally, powered by a protein language model, CLEAN DB supports mutation effect prediction through interactive heatmaps, structural overlays, and tabular data visualizations. We anticipate that CLEAN DB will serve as a valuable platform for advancing enzyme discovery and applications in synthetic biology, metabolic engineering, enzyme engineering, retrosynthesis, and drug discovery. The database is freely available at https:\/\/cleandb.platform.moleculemaker.org\/.<\/jats:p>","DOI":"10.1093\/nar\/gkag1003","type":"journal-article","created":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T11:40:30Z","timestamp":1791286830000},"source":"Crossref","is-referenced-by-count":0,"title":["CLEAN Database: providing enzyme function coverage for over 55 million sequences"],"prefix":"10.1093","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3317-9011","authenticated-orcid":false,"given":"Le","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianan Canal","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering and Computer Sciences, University of California , Berkeley, CA 94720 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miaoyuan","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Information Sciences, University of Illinois Urbana-Champaign , Champaign, IL 61820 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4674-194X","authenticated-orcid":false,"given":"David M","family":"Bianchi","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6114-241X","authenticated-orcid":false,"given":"Katherine","family":"Arneson","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingji","family":"Guo","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Lambert","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Stephens","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijiang","family":"Fu","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Pond","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew J","family":"Berry","sequence":"additional","affiliation":[{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9069-6739","authenticated-orcid":false,"given":"Huimin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]},{"name":"NSF Global Center for Biofoundry Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"key":"2026101504081350100_B1","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1021\/acscentsci.3c01275","article-title":"Opportunities and challenges for machine learning-assisted enzyme engineering","volume":"10","author":"Yang","year":"2024","journal-title":"ACS Cent Sci"},{"key":"2026101504081350100_B2","doi-asserted-by":"publisher","first-page":"12384","DOI":"10.1021\/acs.chemrev.1c00260","article-title":"Directed evolution: methodologies and applications","volume":"121","author":"Wang","year":"2021","journal-title":"Chem Rev"},{"key":"2026101504081350100_B3","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/s44160-023-00417-0","article-title":"Engineered enzymes for the synthesis of pharmaceuticals and other high-value products","volume":"3","author":"Reetz","year":"2024","journal-title":"Nat Synth"},{"key":"2026101504081350100_B4","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1038\/s41596-023-00931-7","article-title":"Reconstruction, simulation and analysis of enzyme-constrained metabolic models using GECKO Toolbox 3.0","volume":"19","author":"Chen","year":"2024","journal-title":"Nat Protoc"},{"key":"2026101504081350100_B5","doi-asserted-by":"publisher","first-page":"MSB202110427","DOI":"10.15252\/msb.202110427","article-title":"Yeast metabolic innovations emerged via expanded metabolic network and gene positive selection","volume":"17","author":"Lu","year":"2021","journal-title":"Mol Syst Biol"},{"key":"2026101504081350100_B6","doi-asserted-by":"publisher","first-page":"2969","DOI":"10.1038\/s41467-022-30689-7","article-title":"Improving recombinant protein production by yeast through genome-scale modeling using proteome constraints","volume":"13","author":"Li","year":"2022","journal-title":"Nat Commun"},{"key":"2026101504081350100_B7","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41564-025-02214-1","article-title":"Approaches for accelerating microbial gene function discovery using artificial intelligence","volume":"11","author":"Palsson","year":"2026","journal-title":"Nat Microbiol"},{"key":"2026101504081350100_B8","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1093\/bib\/bbz065","article-title":"Data-driven rational biosynthesis design: from molecules to cell factories","volume":"21","author":"Chen","year":"2020","journal-title":"Brief Bioinform"},{"key":"2026101504081350100_B9","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1038\/s41929-022-00909-w","article-title":"Machine learning-enabled retrobiosynthesis of molecules","volume":"6","author":"Yu","year":"2023","journal-title":"Nat Catal"},{"key":"2026101504081350100_B10","doi-asserted-by":"publisher","first-page":"D115","DOI":"10.1093\/nar\/gkh131","article-title":"UniProt: the universal protein knowledgebase","volume":"32","author":"Apweiler","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2026101504081350100_B11","doi-asserted-by":"publisher","first-page":"2214","DOI":"10.1111\/febs.16274","article-title":"Enzyme nomenclature and classification: the state of the art","volume":"290","author":"McDonald","year":"2023","journal-title":"FEBS J"},{"key":"2026101504081350100_B12","doi-asserted-by":"publisher","first-page":"101208","DOI":"10.1016\/j.coche.2025.101208","article-title":"Enzyme property prediction using artificial intelligence","volume":"51","author":"Yuan","year":"2026","journal-title":"Curr Opin Chem Eng"},{"key":"2026101504081350100_B13","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1021\/acscatal.5c04814","article-title":"Machine learning-driven enzyme mining: opportunities, challenges, and future perspectives","volume":"16","author":"Moorhoff","year":"2025","journal-title":"ACS Catal"},{"key":"2026101504081350100_B14","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with AlphaFold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2026101504081350100_B15","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1126\/science.abj8754","article-title":"Accurate prediction of protein structures and interactions using a three-track neural network","volume":"373","author":"Baek","year":"2021","journal-title":"Science"},{"key":"2026101504081350100_B16","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":"2026101504081350100_B17","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":"2026101504081350100_B18","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1038\/s41586-025-09697-2","article-title":"Enzyme specificity prediction using cross-attention graph neural networks","volume":"647","author":"Cui","year":"2025","journal-title":"Nature"},{"key":"2026101504081350100_B19","doi-asserted-by":"publisher","first-page":"5544","DOI":"10.1016\/j.csbj.2023.11.006","article-title":"DeepTM: a deep learning algorithm for prediction of melting temperature of thermophilic proteins directly from sequences","volume":"21","author":"Li","year":"2023","journal-title":"Comput Struct Biotechnol J"},{"key":"2026101504081350100_B20","doi-asserted-by":"publisher","first-page":"2304","DOI":"10.1021\/acs.jcim.4c01752","article-title":"ProCeSa: contrast-enhanced structure-aware network for thermostability prediction with protein language models","volume":"65","author":"Zhou","year":"2025","journal-title":"J Chem Inf Model"},{"key":"2026101504081350100_B21","doi-asserted-by":"publisher","first-page":"bbae404","DOI":"10.1093\/bib\/bbae404","article-title":"PLM_Sol: predicting protein solubility by benchmarking multiple protein language models with the updated Escherichia coli protein solubility dataset","volume":"25","author":"Zhang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026101504081350100_B22","doi-asserted-by":"publisher","first-page":"3737","DOI":"10.1021\/acs.jcim.6c00124","article-title":"SurfSol: a multimodal surface-based deep learning framework for protein solubility prediction","volume":"66","author":"Fang","year":"2026","journal-title":"J Chem Inf Model"},{"key":"2026101504081350100_B23","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1126\/science.adf2465","article-title":"Enzyme function prediction using contrastive learning","volume":"379","author":"Yu","year":"2023","journal-title":"Science"},{"key":"2026101504081350100_B24","doi-asserted-by":"publisher","first-page":"D693","DOI":"10.1093\/nar\/gkab1016","article-title":"Rhea, the reaction knowledgebase in 2022","volume":"50","author":"Bansal","year":"2022","journal-title":"Nucleic Acids Res"},{"key":"2026101504081350100_B25","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":"2026101504081350100_B26","doi-asserted-by":"publisher","first-page":"32027","DOI":"10.48550\/arXiv.2509.18480","article-title":"Simplefold: folding proteins is simpler than you think","volume":"2026","author":"Wang","year":"2026","journal-title":"International Conference on Learning Representations"},{"key":"2026101504081350100_B27","doi-asserted-by":"publisher","first-page":"1322","DOI":"10.1093\/bioinformatics\/btu829","article-title":"3Dmol. js: molecular visualization with WebGL","volume":"31","author":"Rego","year":"2015","journal-title":"Bioinformatics"},{"key":"2026101504081350100_B28","doi-asserted-by":"publisher","first-page":"D498","DOI":"10.1093\/nar\/gkaa1025","article-title":"BRENDA, the ELIXIR core data resource in 2021: new developments and updates","volume":"49","author":"Chang","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2026101504081350100_B29","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1038\/s41467-025-56751-8","article-title":"Integrating protein language models and automatic biofoundry for enhanced protein evolution","volume":"16","author":"Zhang","year":"2025","journal-title":"Nat Commun"},{"key":"2026101504081350100_B30","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1038\/s41467-025-61209-y","article-title":"A generalized platform for artificial intelligence-powered autonomous enzyme engineering","volume":"16","author":"Singh","year":"2025","journal-title":"Nat Commun"},{"key":"2026101504081350100_B31","doi-asserted-by":"publisher","first-page":"3094","DOI":"10.52202\/079017-0101","article-title":"Care: a benchmark suite for the classification and retrieval of enzymes","volume":"37","author":"Yang","year":"2024","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026101504081350100_B32","doi-asserted-by":"publisher","article-title":"Interpretable enzyme function prediction via residue-level detection","author":"Yang","DOI":"10.48550\/arXiv.2501.05644"},{"key":"2026101504081350100_B33","doi-asserted-by":"publisher","first-page":"7370","DOI":"10.1038\/s41467-023-43216-z","article-title":"Functional annotation of enzyme-encoding genes using deep learning with transformer layers","volume":"14","author":"Kim","year":"2023","journal-title":"Nat Commun"},{"key":"2026101504081350100_B34","doi-asserted-by":"publisher","first-page":"D368","DOI":"10.1093\/nar\/gkad1011","article-title":"AlphaFold Protein Structure Database in 2024: providing structure coverage for over 214 million protein sequences","volume":"52","author":"Varadi","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026101504081350100_B35","doi-asserted-by":"publisher","first-page":"D643","DOI":"10.1093\/nar\/gkaf1082","article-title":"Open Enzyme Database: a community-wide repository for sharing enzyme data","volume":"54","author":"Yuan","year":"2026","journal-title":"Nucleic Acids Res"},{"key":"2026101504081350100_B36","doi-asserted-by":"publisher","first-page":"2193","DOI":"10.1111\/febs.14427","article-title":"STRENDA DB: enabling the validation and sharing of enzyme kinetics data","volume":"285","author":"Swainston","year":"2018","journal-title":"FEBS J"},{"key":"2026101504081350100_B37","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1038\/s41929-024-01261-x","article-title":"The STRENDA biocatalysis guidelines for cataloguing metadata","volume":"7","author":"Malzacher","year":"2024","journal-title":"Nat Catal"},{"key":"2026101504081350100_B38","doi-asserted-by":"publisher","first-page":"64331","DOI":"10.52202\/075280-2810","article-title":"Proteingym: large-scale benchmarks for protein fitness prediction and design","volume":"36","author":"Notin","year":"2023","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026101504081350100_B39","doi-asserted-by":"publisher","first-page":"D753","DOI":"10.1093\/nar\/gkac1080","article-title":"MGnify: the microbiome sequence data analysis resource in 2023","volume":"51","author":"Richardson","year":"2023","journal-title":"Nucleic Acids Res"}],"container-title":["Nucleic Acids Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/nar\/advance-article-pdf\/doi\/10.1093\/nar\/gkag1003\/71957356\/gkag1003.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/nar\/advance-article-pdf\/doi\/10.1093\/nar\/gkag1003\/71957356\/gkag1003.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T08:08:21Z","timestamp":1792051701000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/nar\/advance-article\/doi\/10.1093\/nar\/gkag1003\/8916836"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1093\/nar\/gkag1003","relation":{},"ISSN":["0305-1048","1362-4962"],"issn-type":[{"value":"0305-1048","type":"print"},{"value":"1362-4962","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]},"article-number":"gkag1003"}}