{"id":"https://openalex.org/W4392452724","doi":"https://doi.org/10.1021/acs.jcim.3c01938","title":"Large-Scale Pretraining Improves Sample Efficiency of Active Learning-Based Virtual Screening","display_name":"Large-Scale Pretraining Improves Sample Efficiency of Active Learning-Based Virtual Screening","publication_year":2024,"publication_date":"2024-03-05","ids":{"openalex":"https://openalex.org/W4392452724","doi":"https://doi.org/10.1021/acs.jcim.3c01938","pmid":"https://pubmed.ncbi.nlm.nih.gov/38442000"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.3c01938","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01938","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043876952","display_name":"Zhonglin Cao","orcid":"https://orcid.org/0000-0003-2096-1178"},"institutions":[{"id":"https://openalex.org/I1297540436","display_name":"Biogen (United States)","ror":"https://ror.org/02jqkb192","country_code":"US","type":"company","lineage":["https://openalex.org/I1297540436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhonglin Cao","raw_affiliation_strings":["Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States"],"raw_orcid":"https://orcid.org/0000-0003-2096-1178","affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1297540436"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036518257","display_name":"Simone Sciabola","orcid":"https://orcid.org/0000-0003-1448-3608"},"institutions":[{"id":"https://openalex.org/I1297540436","display_name":"Biogen (United States)","ror":"https://ror.org/02jqkb192","country_code":"US","type":"company","lineage":["https://openalex.org/I1297540436"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Simone Sciabola","raw_affiliation_strings":["Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States"],"raw_orcid":"https://orcid.org/0000-0003-1448-3608","affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1297540436"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102922843","display_name":"Ye Wang","orcid":"https://orcid.org/0000-0001-5274-2928"},"institutions":[{"id":"https://openalex.org/I1297540436","display_name":"Biogen (United States)","ror":"https://ror.org/02jqkb192","country_code":"US","type":"company","lineage":["https://openalex.org/I1297540436"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ye Wang","raw_affiliation_strings":["Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States"],"raw_orcid":"https://orcid.org/0000-0001-5274-2928","affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Biogen, Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1297540436"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102922843"],"corresponding_institution_ids":["https://openalex.org/I1297540436"],"apc_list":null,"apc_paid":null,"fwci":5.8769,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.9662265,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"64","issue":"6","first_page":"1882","last_page":"1891"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.998199999332428,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.973800003528595,"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/virtual-screening","display_name":"Virtual screening","score":0.8294370770454407},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7267739772796631},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6633131504058838},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6613938212394714},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.6183157563209534},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5015881061553955},{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.4931902289390564},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4751191735267639},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.46691444516181946},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4623258411884308},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4301251471042633},{"id":"https://openalex.org/keywords/bayesian-network","display_name":"Bayesian network","score":0.42147019505500793},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.42122769355773926},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4193054139614105},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.0988459587097168},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.08731240034103394}],"concepts":[{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.8294370770454407},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7267739772796631},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6633131504058838},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6613938212394714},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.6183157563209534},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5015881061553955},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.4931902289390564},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4751191735267639},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.46691444516181946},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4623258411884308},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4301251471042633},{"id":"https://openalex.org/C33724603","wikidata":"https://www.wikidata.org/wiki/Q812540","display_name":"Bayesian network","level":2,"score":0.42147019505500793},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.42122769355773926},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4193054139614105},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.0988459587097168},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.08731240034103394},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001499","descriptor_name":"Bayes Theorem","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D054852","descriptor_name":"Small Molecule Libraries","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.3c01938","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.3c01938","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:38442000","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38442000","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W1560021816","https://openalex.org/W1592950931","https://openalex.org/W1757990252","https://openalex.org/W1985588649","https://openalex.org/W2021748110","https://openalex.org/W2024579386","https://openalex.org/W2049617698","https://openalex.org/W2060531713","https://openalex.org/W2078374001","https://openalex.org/W2085451507","https://openalex.org/W2098530568","https://openalex.org/W2107063279","https://openalex.org/W2114411231","https://openalex.org/W2116341502","https://openalex.org/W2133620840","https://openalex.org/W2134967712","https://openalex.org/W2153165208","https://openalex.org/W2155384593","https://openalex.org/W2171242938","https://openalex.org/W2176516200","https://openalex.org/W2192203593","https://openalex.org/W2274656763","https://openalex.org/W2899070097","https://openalex.org/W2901292178","https://openalex.org/W2911964244","https://openalex.org/W2912171584","https://openalex.org/W2921473648","https://openalex.org/W2947423323","https://openalex.org/W2966357564","https://openalex.org/W2983225234","https://openalex.org/W3010016408","https://openalex.org/W3027975282","https://openalex.org/W3044724994","https://openalex.org/W3094640617","https://openalex.org/W3103092523","https://openalex.org/W3112474878","https://openalex.org/W3114632476","https://openalex.org/W3120407713","https://openalex.org/W3135642867","https://openalex.org/W3156693194","https://openalex.org/W3159598019","https://openalex.org/W3188648403","https://openalex.org/W4200233821","https://openalex.org/W4206525059","https://openalex.org/W4210617107","https://openalex.org/W4214868967","https://openalex.org/W4220909721","https://openalex.org/W4221151574","https://openalex.org/W4290075791","https://openalex.org/W4291023040","https://openalex.org/W4293802560","https://openalex.org/W4313485929","https://openalex.org/W4318262876"],"related_works":["https://openalex.org/W2902857455","https://openalex.org/W2161782568","https://openalex.org/W3185720802","https://openalex.org/W4232045916","https://openalex.org/W2072444571","https://openalex.org/W2009937564","https://openalex.org/W4318472429","https://openalex.org/W1973079533","https://openalex.org/W4388943133","https://openalex.org/W4388499548"],"abstract_inverted_index":{"Virtual":[0],"screening":[1,129],"of":[2,13,23,33,47,56,70,87,101,124,132,156,180],"large":[3],"compound":[4,26],"libraries":[5],"to":[6,30,174],"identify":[7],"potential":[8],"hit":[9],"candidates":[10],"is":[11,59],"one":[12],"the":[14,21,31,50,67,88,99,125,143,153,175],"earliest":[15],"steps":[16],"in":[17,111,160],"drug":[18,165],"discovery.":[19,166],"As":[20],"size":[22],"commercially":[24],"available":[25],"collections":[27],"grows":[28],"exponentially":[29],"scale":[32],"billions,":[34],"active":[35,115,181],"learning":[36,63,116],"and":[37,107,163,177],"Bayesian":[38,113],"optimization":[39,114],"have":[40],"recently":[41],"been":[42],"proven":[43],"as":[44,171],"effective":[45],"methods":[46,58],"narrowing":[48],"down":[49],"search":[51],"space.":[52],"An":[53,72],"essential":[54],"component":[55],"those":[57],"a":[60,85,102,112,172],"surrogate":[61],"machine":[62],"model":[64,74,106,121],"that":[65,152],"predicts":[66],"desired":[68],"properties":[69],"compounds.":[71],"accurate":[73],"can":[75,169],"achieve":[76],"high":[77],"sample":[78,178],"efficiency":[79,179],"by":[80],"finding":[81],"hits":[82],"with":[83],"only":[84,130],"fraction":[86],"entire":[89],"library":[90,135],"being":[91],"virtually":[92],"screened.":[93],"In":[94],"this":[95],"study,":[96],"we":[97,150],"examined":[98],"performance":[100,155],"pretrained":[103,120,157],"transformer-based":[104],"language":[105],"graph":[108],"neural":[109],"network":[110],"framework.":[117],"The":[118],"best":[119],"identifies":[122],"58.97%":[123],"top-50,000":[126],"compounds":[127],"after":[128],"0.6%":[131],"an":[133],"ultralarge":[134],"containing":[136],"99.5":[137],"million":[138],"compounds,":[139],"improving":[140],"8%":[141],"over":[142],"previous":[144],"state-of-the-art":[145],"baseline.":[146],"Through":[147],"extensive":[148],"benchmarks,":[149],"show":[151],"superior":[154],"models":[158,168],"persists":[159],"both":[161],"structure-based":[162],"ligand-based":[164],"Pretrained":[167],"serve":[170],"boost":[173],"accuracy":[176],"learning-based":[182],"virtual":[183],"screening.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}