{"id":"https://openalex.org/W4404103762","doi":"https://doi.org/10.1186/s13321-024-00920-2","title":"Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning","display_name":"Protein-small molecule binding site prediction based on a pre-trained protein language model with contrastive learning","publication_year":2024,"publication_date":"2024-11-06","ids":{"openalex":"https://openalex.org/W4404103762","doi":"https://doi.org/10.1186/s13321-024-00920-2","pmid":"https://pubmed.ncbi.nlm.nih.gov/39506806"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00920-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00920-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00920-2","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/s13321-024-00920-2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080813795","display_name":"Jue Wang","orcid":"https://orcid.org/0000-0002-3004-0877"},"institutions":[{"id":"https://openalex.org/I4391767655","display_name":"State Key Laboratory of Molecular Oncology","ror":"https://ror.org/014gmtw23","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210141458","https://openalex.org/I4391767655"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jue Wang","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4391767655"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868152","display_name":"Yufan Liu","orcid":"https://orcid.org/0009-0007-8781-0282"},"institutions":[{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Yufan Liu","raw_affiliation_strings":["Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Kingdom of Saudi Arabia"],"affiliations":[{"raw_affiliation_string":"Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering Division, King Abdullah University of Science and Technology (KAUST), Thuwal, 23955-6900, Kingdom of Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037870231","display_name":"Boxue Tian","orcid":"https://orcid.org/0000-0002-5830-0669"},"institutions":[{"id":"https://openalex.org/I4391767655","display_name":"State Key Laboratory of Molecular Oncology","ror":"https://ror.org/014gmtw23","country_code":null,"type":"facility","lineage":["https://openalex.org/I4210141458","https://openalex.org/I4391767655"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boxue Tian","raw_affiliation_strings":["MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China. boxuetian@mail.tsinghua.edu.cn","MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China. boxuetian@mail.tsinghua.edu.cn","institution_ids":[]},{"raw_affiliation_string":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I4391767655"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080813795"],"corresponding_institution_ids":["https://openalex.org/I4391767655","https://openalex.org/I99065089"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":6.1823,"has_fulltext":true,"cited_by_count":27,"citation_normalized_percentile":{"value":0.97383233,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"16","issue":"1","first_page":"125","last_page":"125"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9991999864578247,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9991999864578247,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9991000294685364,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.6119801998138428},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40269923210144043},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3339088559150696}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6119801998138428},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40269923210144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3339088559150696}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00920-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00920-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00920-2","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:39506806","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39506806","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:11542454","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11542454","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11542454/pdf/13321_2024_Article_920.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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:98b23c3c0e3447d5bc0face4e24b0920","is_oa":true,"landing_page_url":"https://doaj.org/article/98b23c3c0e3447d5bc0face4e24b0920","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 16, Iss 1, Pp 1-21 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00920-2","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00920-2","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00920-2","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G7179776169","display_name":null,"funder_award_id":"20231080030","funder_id":"https://openalex.org/F4320322392","funder_display_name":"Tsinghua University"}],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"},{"id":"https://openalex.org/F4320324787","display_name":"Peking University","ror":"https://ror.org/02v51f717"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404103762.pdf"},"referenced_works_count":71,"referenced_works":["https://openalex.org/W1508885706","https://openalex.org/W1603274157","https://openalex.org/W1881469793","https://openalex.org/W1980969309","https://openalex.org/W1982583124","https://openalex.org/W2012003686","https://openalex.org/W2016170088","https://openalex.org/W2016500278","https://openalex.org/W2030598505","https://openalex.org/W2038252445","https://openalex.org/W2041411283","https://openalex.org/W2046221309","https://openalex.org/W2056957086","https://openalex.org/W2060277733","https://openalex.org/W2073490027","https://openalex.org/W2076048958","https://openalex.org/W2077804275","https://openalex.org/W2078176948","https://openalex.org/W2080481362","https://openalex.org/W2081142506","https://openalex.org/W2082717449","https://openalex.org/W2086221159","https://openalex.org/W2097105872","https://openalex.org/W2098223336","https://openalex.org/W2118608964","https://openalex.org/W2124351063","https://openalex.org/W2140538197","https://openalex.org/W2141925453","https://openalex.org/W2156125289","https://openalex.org/W2160378127","https://openalex.org/W2281423246","https://openalex.org/W2397429809","https://openalex.org/W2409039558","https://openalex.org/W2464666781","https://openalex.org/W2469738507","https://openalex.org/W2560647685","https://openalex.org/W2580781053","https://openalex.org/W2617750324","https://openalex.org/W2620760558","https://openalex.org/W2716141585","https://openalex.org/W2743800043","https://openalex.org/W2743877237","https://openalex.org/W2791976745","https://openalex.org/W2884561390","https://openalex.org/W2887981960","https://openalex.org/W2903634707","https://openalex.org/W2907083886","https://openalex.org/W2949867299","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963744743","https://openalex.org/W2980948514","https://openalex.org/W2997833216","https://openalex.org/W2999309192","https://openalex.org/W3037888463","https://openalex.org/W3045004532","https://openalex.org/W3049692992","https://openalex.org/W3112376646","https://openalex.org/W3126232929","https://openalex.org/W3126876258","https://openalex.org/W3177500196","https://openalex.org/W4220991280","https://openalex.org/W4229031603","https://openalex.org/W4295165394","https://openalex.org/W4321485439","https://openalex.org/W4327550249","https://openalex.org/W4385814218","https://openalex.org/W4389076414","https://openalex.org/W4390563867","https://openalex.org/W4393342758","https://openalex.org/W4400231442"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Predicting":[0],"protein-small":[1,173,206],"molecule":[2,42,174,207],"binding":[3,43,139,175],"sites,":[4,176],"the":[5,60,81,104,135],"initial":[6],"step":[7],"in":[8,145],"structure-guided":[9],"drug":[10,146,202],"design,":[11],"remains":[12],"challenging":[13],"for":[14,178,200],"proteins":[15,48,89,179],"lacking":[16],"experimentally":[17],"derived":[18],"ligand-bound":[19],"structures.":[20],"Here,":[21],"we":[22],"propose":[23],"CLAPE-SMB,":[24],"which":[25,84],"integrates":[26],"a":[27,50,63,162,197],"pre-trained":[28,163],"protein":[29,119,164],"language":[30,165],"model":[31,166,191],"with":[32,167],"contrastive":[33,168],"learning":[34,169],"to":[35,143,170],"provide":[36],"high":[37],"accuracy":[38],"predictions":[39],"of":[40,76,101,113,129,137],"small":[41],"sites":[44,86],"that":[45,122],"can":[46],"accommodate":[47],"without":[49,180],"published":[51],"crystal":[52],"structure.":[53],"We":[54,78],"trained":[55],"and":[56,70,72,97,132,150,204],"tested":[57],"CLAPE-SMB":[58,109,160],"on":[59,67,91,103,115],"SJC":[61],"dataset,":[62,83],"non-redundant":[64,125],"dataset":[65,121],"based":[66,90],"sc-PDB,":[68],"JOINED,":[69],"COACH420,":[71],"achieved":[73,98,110],"an":[74,99,111],"MCC":[75,100,112],"0.529.":[77],"also":[79],"compiled":[80],"UniProtSMB":[82],"merges":[85],"from":[87,94],"similar":[88],"raw":[92],"data":[93],"UniProtKB":[95],"database,":[96],"0.699":[102],"test":[105],"set.":[106],"In":[107],"addition,":[108],"0.815":[114],"our":[116],"intrinsically":[117],"disordered":[118],"(IDP)":[120],"contains":[123],"336":[124],"sequences.":[126],"Case":[127],"studies":[128],"DAPK1,":[130],"RebH,":[131],"Nep1":[133],"support":[134],"potential":[136],"this":[138,190],"site":[140],"prediction":[141],"tool":[142,199],"aid":[144],"design.":[147],"The":[148],"code":[149],"datasets":[151],"are":[152],"freely":[153],"available":[154],"at":[155],"https://github.com/JueWangTHU/CLAPE-SMB":[156],".":[157],"SCIENTIFIC":[158],"CONTRIBUTION:":[159],"combines":[161],"accurately":[171],"predict":[172],"especially":[177],"experimental":[181],"structures,":[182],"such":[183],"as":[184],"IDPs.":[185],"Trained":[186],"across":[187],"various":[188],"datasets,":[189],"shows":[192],"strong":[193],"adaptability,":[194],"making":[195],"it":[196],"valuable":[198],"advancing":[201],"design":[203],"understanding":[205],"interactions.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":21}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}