{"id":"https://openalex.org/W4406120415","doi":"https://doi.org/10.1186/s13321-024-00944-8","title":"CLAIRE: a contrastive learning-based predictor for EC number of chemical reactions","display_name":"CLAIRE: a contrastive learning-based predictor for EC number of chemical reactions","publication_year":2025,"publication_date":"2025-01-07","ids":{"openalex":"https://openalex.org/W4406120415","doi":"https://doi.org/10.1186/s13321-024-00944-8","pmid":"https://pubmed.ncbi.nlm.nih.gov/39773344"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00944-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00944-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00944-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00944-8","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115791540","display_name":"Zishuo Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1283595831","display_name":"Synlab Czech (Czechia)","ror":"https://ror.org/01hqrb170","country_code":"CZ","type":"company","lineage":["https://openalex.org/I1283595831"]},{"id":"https://openalex.org/I4210089756","display_name":"Bioscience (China)","ror":"https://ror.org/0072d4h61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089756"]}],"countries":["CN","CZ"],"is_corresponding":true,"raw_author_name":"Zishuo Zeng","raw_affiliation_strings":["Synceres Biosciences Co. Ltd., Shenzhen, 518100, China. zengzishuo@synceres.com","Synceres Biosciences Co. Ltd., Shenzhen, 518100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Synceres Biosciences Co. Ltd., Shenzhen, 518100, China. zengzishuo@synceres.com","institution_ids":["https://openalex.org/I1283595831"]},{"raw_affiliation_string":"Synceres Biosciences Co. Ltd., Shenzhen, 518100, China","institution_ids":["https://openalex.org/I4210089756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102215166","display_name":"Jin Guo","orcid":"https://orcid.org/0000-0002-8016-3664"},"institutions":[{"id":"https://openalex.org/I4210089756","display_name":"Bioscience (China)","ror":"https://ror.org/0072d4h61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Guo","raw_affiliation_strings":["Synceres Biosciences Co. Ltd., Shenzhen, 518100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Synceres Biosciences Co. Ltd., Shenzhen, 518100, China","institution_ids":["https://openalex.org/I4210089756"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103619968","display_name":"Jiao Jin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210089756","display_name":"Bioscience (China)","ror":"https://ror.org/0072d4h61","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210089756"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiao Jin","raw_affiliation_strings":["Synceres Biosciences Co. Ltd., Shenzhen, 518100, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Synceres Biosciences Co. Ltd., Shenzhen, 518100, China","institution_ids":["https://openalex.org/I4210089756"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005377453","display_name":"Xiaozhou Luo","orcid":"https://orcid.org/0000-0001-9808-6890"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaozhou Luo","raw_affiliation_strings":["Shenzhen Key Laboratory for the Intelligent Microbial Manufacturing of Medicines, Key Laboratory of Quantitative Synthetic Biology, Center for Synthetic Biochemistry, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. xz.luo@siat.ac.cn","Shenzhen Key Laboratory for the Intelligent Microbial Manufacturing of Medicines, Key Laboratory of Quantitative Synthetic Biology, Center for Synthetic Biochemistry, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Key Laboratory for the Intelligent Microbial Manufacturing of Medicines, Key Laboratory of Quantitative Synthetic Biology, Center for Synthetic Biochemistry, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China. xz.luo@siat.ac.cn","institution_ids":["https://openalex.org/I4210145761"]},{"raw_affiliation_string":"Shenzhen Key Laboratory for the Intelligent Microbial Manufacturing of Medicines, Key Laboratory of Quantitative Synthetic Biology, Center for Synthetic Biochemistry, Shenzhen Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005377453","https://openalex.org/A5115791540"],"corresponding_institution_ids":["https://openalex.org/I1283595831","https://openalex.org/I4210089756","https://openalex.org/I4210145761"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":6.2956,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.96836706,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"1","first_page":"2","last_page":"2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9955000281333923,"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/T10932","display_name":"Microbial Metabolic Engineering and Bioproduction","score":0.9955000281333923,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9873999953269958,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7484250068664551},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6369665861129761},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6174707412719727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5681706070899963},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.5165397524833679},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.44672006368637085},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4181285798549652},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4151343107223511},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38846081495285034},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.129411518573761}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7484250068664551},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6369665861129761},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6174707412719727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5681706070899963},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.5165397524833679},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.44672006368637085},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4181285798549652},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4151343107223511},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38846081495285034},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.129411518573761},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00944-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00944-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00944-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:39773344","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39773344","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,"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":"Journal of cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11707929","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11707929","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11707929/pdf/13321_2024_Article_944.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:72acf5f8d83d49678b1e525df58b7a56","is_oa":true,"landing_page_url":"https://doaj.org/article/72acf5f8d83d49678b1e525df58b7a56","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-9 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00944-8","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00944-8","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00944-8","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.44999998807907104}],"awards":[{"id":"https://openalex.org/G4476598844","display_name":null,"funder_award_id":"2021B1515020049","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G6553455013","display_name":null,"funder_award_id":"32071421","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7430600730","display_name":null,"funder_award_id":"2019YFA0904100","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4406120415.pdf"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1996830618","https://openalex.org/W2033377040","https://openalex.org/W2047632644","https://openalex.org/W2055043387","https://openalex.org/W2062601468","https://openalex.org/W2070484508","https://openalex.org/W2078775934","https://openalex.org/W2090505208","https://openalex.org/W2095300485","https://openalex.org/W2096706242","https://openalex.org/W2096733369","https://openalex.org/W2159628188","https://openalex.org/W2163748594","https://openalex.org/W2165373392","https://openalex.org/W2171421143","https://openalex.org/W2551217916","https://openalex.org/W2766352633","https://openalex.org/W2892210937","https://openalex.org/W2907470641","https://openalex.org/W2910665987","https://openalex.org/W2913898479","https://openalex.org/W2924412896","https://openalex.org/W2952015518","https://openalex.org/W2953321375","https://openalex.org/W2979585142","https://openalex.org/W2980794254","https://openalex.org/W3118349318","https://openalex.org/W3123901912","https://openalex.org/W3136918052","https://openalex.org/W3202979417","https://openalex.org/W3211718555","https://openalex.org/W3212063608","https://openalex.org/W4213314063","https://openalex.org/W4220747243","https://openalex.org/W4226145240","https://openalex.org/W4281697264","https://openalex.org/W4285678567","https://openalex.org/W4290725232","https://openalex.org/W4318561874","https://openalex.org/W4318778685","https://openalex.org/W4322494707","https://openalex.org/W4362471278","https://openalex.org/W4384023735","https://openalex.org/W4387814399","https://openalex.org/W4401192719"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W1571141552","https://openalex.org/W2392921965","https://openalex.org/W4391636338","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W4405124681"],"abstract_inverted_index":{"Predicting":[0],"EC":[1,141],"numbers":[2],"for":[3,10,35,113,137],"chemical":[4],"reactions":[5],"enables":[6],"efficient":[7],"enzymatic":[8,139],"annotations":[9],"computer-aided":[11,162],"synthesis":[12,163],"planning.":[13,164],"However,":[14],"conventional":[15],"machine":[16],"learning":[17,136],"approaches":[18],"encounter":[19],"challenges":[20,145],"due":[21],"to":[22,52],"data":[23,50,147],"scarcity":[24,148],"and":[25,49,68,77,100,119,149,158],"class":[26],"imbalance.":[27,150],"Here,":[28],"we":[29],"introduce":[30],"CLAIRE":[31,56,91,108,123],"(Contrastive":[32],"Learning-based":[33],"AnnotatIon":[34],"Reaction's":[36],"EC),":[37],"a":[38,110],"novel":[39],"framework":[40],"leveraging":[41],"contrastive":[42,135],"learning,":[43],"pre-trained":[44],"language":[45],"model-based":[46],"reaction":[47],"embeddings,":[48],"augmentation":[51],"address":[53],"these":[54],"limitations.":[55],"achieved":[57],"notable":[58],"performance":[59,157],"improvements,":[60],"demonstrating":[61],"weighted":[62],"average":[63],"F1":[64],"scores":[65],"of":[66],"0.861":[67],"0.911":[69],"on":[70,127],"the":[71,94,144,155,161],"testing":[72],"set":[73],"(n":[74,81],"=":[75,82],"18,816)":[76],"an":[78],"independent":[79],"dataset":[80],"1040)":[83],"derived":[84],"from":[85],"yeast's":[86],"metabolic":[87],"model,":[88],"respectively.":[89,103],"Remarkably,":[90],"significantly":[92],"outperformed":[93],"state-of-the-art":[95,156],"model":[96,153],"by":[97],"3.65":[98],"folds":[99],"1.18":[101],"folds,":[102],"Its":[104],"high":[105],"accuracy":[106],"positions":[107],"as":[109],"promising":[111],"tool":[112],"retrosynthesis":[114],"planning,":[115],"drug":[116],"fate":[117],"prediction,":[118],"synthetic":[120],"biology":[121],"applications.":[122],"is":[124],"freely":[125],"available":[126],"GitHub":[128],"(":[129],"https://github.com/zishuozeng/CLAIRE":[130],").Scientific":[131],"contributionThis":[132],"work":[133],"employed":[134],"predicting":[138],"reaction's":[140],"numbers,":[142],"overcoming":[143],"in":[146],"The":[151],"new":[152],"achieves":[154],"may":[159],"facilitate":[160]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8}],"updated_date":"2026-07-14T08:27:34.040176","created_date":"2025-10-10T00:00:00"}