{"id":"https://openalex.org/W7222013322","doi":"https://doi.org/10.1093/nar/gkag1003","title":"CLEAN Database: providing enzyme function coverage for over 55 million sequences","display_name":"CLEAN Database: providing enzyme function coverage for over 55 million sequences","publication_year":2026,"publication_date":"2026-10-06","ids":{"openalex":"https://openalex.org/W7222013322","doi":"https://doi.org/10.1093/nar/gkag1003","pmid":"https://pubmed.ncbi.nlm.nih.gov/42876371"},"language":"en","primary_location":{"id":"doi:10.1093/nar/gkag1003","doi":"https://doi.org/10.1093/nar/gkag1003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkag1003","pdf_url":"https://academic.oup.com/nar/advance-article-pdf/doi/10.1093/nar/gkag1003/71957356/gkag1003.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/nar/advance-article-pdf/doi/10.1093/nar/gkag1003/71957356/gkag1003.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040288402","display_name":"Le Yuan","orcid":"https://orcid.org/0000-0003-3317-9011","observed_orcids":["https://orcid.org/0000-0003-3317-9011"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4405271866","display_name":"Carl R. Woese Institute for Genomic Biology","ror":"https://ror.org/036j6yj81","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405271866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Yuan","raw_affiliation_strings":["Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":"https://orcid.org/0000-0003-3317-9011","affiliations":[{"raw_affiliation_string":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4405271866"]},{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061059626","display_name":"Jianan Canal Li","orcid":"https://orcid.org/0009-0001-7772-5742","observed_orcids":["https://orcid.org/0009-0001-7772-5742"]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianan Canal Li","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California , Berkeley, CA 94720 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California , Berkeley, CA 94720 ,","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158842273","display_name":"Miaoyuan Wen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoyuan Wen","raw_affiliation_strings":["School of Information Sciences, University of Illinois Urbana-Champaign , Champaign, IL 61820 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Sciences, University of Illinois Urbana-Champaign , Champaign, IL 61820 ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059127602","display_name":"David M. Bianchi","orcid":"https://orcid.org/0000-0003-4674-194X","observed_orcids":["https://orcid.org/0000-0003-4674-194X"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David M Bianchi","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":"https://orcid.org/0000-0003-4674-194X","affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5118454839","display_name":"Katherine Arneson","orcid":"https://orcid.org/0009-0009-6114-241X","observed_orcids":["https://orcid.org/0009-0009-6114-241X"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Katherine Arneson","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":"https://orcid.org/0009-0009-6114-241X","affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158803703","display_name":"Bingji Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bingji Guo","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144197996","display_name":"Sara Lambert","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sara Lambert","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126048389","display_name":"Chris Stephens","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chris Stephens","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044232156","display_name":"Tianhao Yu","orcid":"https://orcid.org/0000-0001-5172-8139","observed_orcids":["https://orcid.org/0000-0001-5172-8139"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4405271866","display_name":"Carl R. Woese Institute for Genomic Biology","ror":"https://ror.org/036j6yj81","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405271866"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianhao Yu","raw_affiliation_strings":["Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4405271866"]},{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110962658","display_name":"Lijiang Fu","orcid":"https://orcid.org/0009-0003-6659-3101","observed_orcids":["https://orcid.org/0009-0003-6659-3101"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lijiang Fu","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152020122","display_name":"Christopher Pond","orcid":"https://orcid.org/0000-0002-6372-9128","observed_orcids":["https://orcid.org/0000-0002-6372-9128"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Pond","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064247100","display_name":"Matthew J. Berry","orcid":"https://orcid.org/0000-0002-8197-9577","observed_orcids":["https://orcid.org/0000-0002-8197-9577"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210135837","display_name":"National Center for Supercomputing Applications","ror":"https://ror.org/03r10zj06","country_code":"US","type":"facility","lineage":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew J Berry","raw_affiliation_strings":["NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"National Center for Supercomputing Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4210135837"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014465828","display_name":"Huimin Zhao","orcid":"https://orcid.org/0000-0002-9069-6739","observed_orcids":["https://orcid.org/0000-0002-9069-6739"]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4405271866","display_name":"Carl R. Woese Institute for Genomic Biology","ror":"https://ror.org/036j6yj81","country_code":"US","type":"facility","lineage":["https://openalex.org/I4405271866"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huimin Zhao","raw_affiliation_strings":["Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF Global Center for Biofoundry Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,"],"raw_orcid":"https://orcid.org/0000-0002-9069-6739","affiliations":[{"raw_affiliation_string":"Carl R. Woese Institute for Genomic Biology, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4405271866"]},{"raw_affiliation_string":"Department of Chemical and Biomolecular Engineering, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF Global Center for Biofoundry Applications, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF Molecule Maker Lab Institute, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"NSF iBioFoundry, University of Illinois Urbana-Champaign , Urbana, IL 61801 ,","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5014465828"],"corresponding_institution_ids":["https://openalex.org/I157725225","https://openalex.org/I4405271866"],"apc_list":{"value":3992,"currency":"USD","value_usd":3992},"apc_paid":{"value":3992,"currency":"USD","value_usd":3992},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.66042213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6435999870300293,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.6435999870300293,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10404","display_name":"Enzyme Catalysis and Immobilization","score":0.1565999984741211,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.07129999995231628,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.6710000038146973},{"id":"https://openalex.org/keywords/mutation-effect-prediction","display_name":"mutation effect prediction","score":0.7409999966621399},{"id":"https://openalex.org/keywords/enzyme-function-prediction","display_name":"enzyme function prediction","score":0.44999998807907104},{"id":"https://openalex.org/keywords/protein-sequence-space","display_name":"protein sequence space","score":0.45500001311302185},{"id":"https://openalex.org/keywords/enzyme-discovery","display_name":"enzyme discovery","score":0.6439999938011169},{"id":"https://openalex.org/keywords/enzyme-engineering","display_name":"enzyme engineering","score":0.6010000109672546},{"id":"https://openalex.org/keywords/metabolic-engineering","display_name":"metabolic engineering","score":0.7110000252723694},{"id":"https://openalex.org/keywords/synthetic-biology","display_name":"synthetic biology","score":0.593999981880188}],"concepts":[{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.7487999796867371},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6292999982833862},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.6244000196456909},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5062999725341797},{"id":"https://openalex.org/C181199279","wikidata":"https://www.wikidata.org/wiki/Q8047","display_name":"Enzyme","level":2,"score":0.49950000643730164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4359999895095825},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.41190001368522644},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.39010000228881836},{"id":"https://openalex.org/C2983909278","wikidata":"https://www.wikidata.org/wiki/Q6368","display_name":"Web browser","level":3,"score":0.37779998779296875},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3488999903202057},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.336899995803833},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C147816474","wikidata":"https://www.wikidata.org/wiki/Q169525","display_name":"Protein engineering","level":3,"score":0.3116999864578247},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C30711495","wikidata":"https://www.wikidata.org/wiki/Q289411","display_name":"Sequence space","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.2782999873161316},{"id":"https://openalex.org/C191908910","wikidata":"https://www.wikidata.org/wiki/Q862838","display_name":"Synthetic biology","level":2,"score":0.27549999952316284},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.25949999690055847},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/nar/gkag1003","doi":"https://doi.org/10.1093/nar/gkag1003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkag1003","pdf_url":"https://academic.oup.com/nar/advance-article-pdf/doi/10.1093/nar/gkag1003/71957356/gkag1003.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},{"id":"pmid:42876371","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42876371","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic acids research","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1093/nar/gkag1003","doi":"https://doi.org/10.1093/nar/gkag1003","is_oa":true,"landing_page_url":"https://doi.org/10.1093/nar/gkag1003","pdf_url":"https://academic.oup.com/nar/advance-article-pdf/doi/10.1093/nar/gkag1003/71957356/gkag1003.pdf","source":{"id":"https://openalex.org/S134668137","display_name":"Nucleic Acids Research","issn_l":"0305-1048","issn":["0305-1048","1362-4954","1362-4962"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-scientific","cwts-core","doaj","dongbi-a","doyens","jufo-3","ki-jl-3","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Nucleic Acids Research","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1912064254","display_name":"Track 4:  Advanced CI Coordination Ecosystem: Monitoring and Measurement Services","funder_award_id":"2137603","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2699098518","display_name":"BioFoundry: NSF iBioFoundry for Basic and Applied Biology","funder_award_id":"2400058","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2955713158","display_name":"Global Centers: Reliable and Scalable Biofoundries for Biomanufacturing and Global Bioeconomy","funder_award_id":"2435374","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4006316252","display_name":"Track 1: ACCESS Resource Allocations Marketplace and Platform Services (RAMPS)","funder_award_id":"2138259","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4676224565","display_name":"ACO: An Open CI Ecosystem to Advance Scientific Discovery (OpenCI)","funder_award_id":"2138296","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G509285653","display_name":"Track 3: COre National Ecosystem for CyberinfrasTructure (CONECT)","funder_award_id":"2138307","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8300691027","display_name":"Track 2: Customized Multi-tier Assistance, Training, and Computational Help (MATCH) for End User ACCESS to CI","funder_award_id":"2138286","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G942151759","display_name":"AI Institute for Molecular Discovery, Synthetic Strategy, and Manufacturing: Molecule Maker Lab Institute (MMLI)","funder_award_id":"2505932","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320312143","display_name":"National Centre for Supercomputing Applications","ror":"https://ror.org/03r10zj06"},{"id":"https://openalex.org/F4320337370","display_name":"Office of International Science and Engineering","ror":"https://ror.org/01k638r21"},{"id":"https://openalex.org/F4320337377","display_name":"Office of Advanced Cyberinfrastructure","ror":"https://ror.org/04nh1dc89"},{"id":"https://openalex.org/F4320337393","display_name":"Division of Chemistry","ror":"https://ror.org/01ar8dr59"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7222013322.pdf","grobid_xml":"https://content.openalex.org/works/W7222013322.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W2140047797","https://openalex.org/W2154139219","https://openalex.org/W2793690814","https://openalex.org/W2997692303","https://openalex.org/W3105895642","https://openalex.org/W3177828909","https://openalex.org/W3185760697","https://openalex.org/W3186179742","https://openalex.org/W3206238391","https://openalex.org/W3211718555","https://openalex.org/W3212063608","https://openalex.org/W4281774287","https://openalex.org/W4283032119","https://openalex.org/W4310957810","https://openalex.org/W4321099926","https://openalex.org/W4327550249","https://openalex.org/W4362471278","https://openalex.org/W4388336654","https://openalex.org/W4388464011","https://openalex.org/W4388665407","https://openalex.org/W4389546039","https://openalex.org/W4390579570","https://openalex.org/W4390971823","https://openalex.org/W4391544240","https://openalex.org/W4401869998","https://openalex.org/W4405636820","https://openalex.org/W4406317514","https://openalex.org/W4407356649","https://openalex.org/W4407887175","https://openalex.org/W4411887054","https://openalex.org/W4414938342","https://openalex.org/W4415330757","https://openalex.org/W4415799131","https://openalex.org/W4415928499","https://openalex.org/W4417502201","https://openalex.org/W7116675129","https://openalex.org/W7118636139","https://openalex.org/W7133185245","https://openalex.org/W7138432100"],"related_works":["https://openalex.org/W4417153351","https://openalex.org/W4397289756","https://openalex.org/W4405702281","https://openalex.org/W4415928499","https://openalex.org/W4362471278","https://openalex.org/W3089837105","https://openalex.org/W2766352633","https://openalex.org/W4401669909","https://openalex.org/W4297461078","https://openalex.org/W2131366108"],"abstract_inverted_index":{"Enzyme":[0],"function":[1,53,78,108],"annotation":[2,54],"is":[3,166],"critical":[4],"for":[5,21,147],"decoding":[6],"biological":[7],"systems":[8],"and":[9,40,58,105,132,151,161],"enabling":[10],"rational":[11],"enzyme":[12,17,52,77,107,149,158],"design.":[13],"However,":[14],"experimentally":[15],"characterized":[16],"functions":[18],"remain":[19],"available":[20,168],"only":[22],"a":[23,32,71,117,144],"small":[24],"fraction":[25],"of":[26],"known":[27],"protein":[28,62,118],"sequences,":[29],"resulting":[30],"in":[31,46,153],"widening":[33],"gap":[34],"between":[35],"rapidly":[36],"expanding":[37],"sequence":[38],"space":[39],"reliable":[41],"functional":[42],"assignments.":[43],"Recent":[44],"advances":[45],"artificial":[47],"intelligence":[48],"(AI)":[49],"have":[50],"accelerated":[51],"by":[55,86,116],"facilitating":[56],"accurate":[57],"high-throughput":[59],"prediction":[60,126],"from":[61],"sequences.":[63],"Here,":[64],"we":[65],"present":[66],"CLEAN":[67,88,121,139],"Database":[68],"(CLEAN":[69],"DB),":[70],"comprehensive":[72],"resource":[73],"encompassing":[74],">55":[75],"million":[76],"annotations":[79],"across":[80],"1":[81],"098":[82],"305":[83],"strains,":[84],"predicted":[85],"the":[87],"AI":[89],"model.":[90],"The":[91,164],"database":[92,165],"features":[93],"an":[94],"intuitive":[95],"web":[96],"interface":[97],"that":[98,138],"enables":[99],"users":[100],"to":[101],"efficiently":[102],"search,":[103],"explore,":[104],"download":[106],"data":[109,134],"through":[110,127],"flexible":[111],"query":[112],"options.":[113],"Additionally,":[114],"powered":[115],"language":[119],"model,":[120],"DB":[122,140],"supports":[123],"mutation":[124],"effect":[125],"interactive":[128],"heatmaps,":[129],"structural":[130],"overlays,":[131],"tabular":[133],"visualizations.":[135],"We":[136],"anticipate":[137],"will":[141],"serve":[142],"as":[143],"valuable":[145],"platform":[146],"advancing":[148],"discovery":[150],"applications":[152],"synthetic":[154],"biology,":[155],"metabolic":[156],"engineering,":[157,159],"retrosynthesis,":[160],"drug":[162],"discovery.":[163],"freely":[167],"at":[169],"https://cleandb.platform.moleculemaker.org/.":[170]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-16T00:00:00"}
