{"id":"https://openalex.org/W4365504163","doi":"https://doi.org/10.1021/acs.jcim.2c01569","title":"MF-PCBA: Multifidelity High-Throughput Screening Benchmarks for Drug Discovery and Machine Learning","display_name":"MF-PCBA: Multifidelity High-Throughput Screening Benchmarks for Drug Discovery and Machine Learning","publication_year":2023,"publication_date":"2023-04-14","ids":{"openalex":"https://openalex.org/W4365504163","doi":"https://doi.org/10.1021/acs.jcim.2c01569","pmid":"https://pubmed.ncbi.nlm.nih.gov/37058588"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c01569","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01569","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.2c01569","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081668013","display_name":"David Buterez","orcid":"https://orcid.org/0000-0001-6558-0833"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David Buterez","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, U.K","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030485362","display_name":"Jon Paul Janet","orcid":"https://orcid.org/0000-0001-7825-4797"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Jon Paul Janet","raw_affiliation_strings":["Molecular AI, Discovery Sciences, R&D, AstraZeneca, 431 50 Gothenburg, Sweden"],"affiliations":[{"raw_affiliation_string":"Molecular AI, Discovery Sciences, R&D, AstraZeneca, 431 50 Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107385959","display_name":"Steven J. Kiddle","orcid":"https://orcid.org/0000-0003-4350-7437"},"institutions":[{"id":"https://openalex.org/I4210109524","display_name":"AstraZeneca (Australia)","ror":"https://ror.org/018nw3344","country_code":"AU","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210109524"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Steven J. Kiddle","raw_affiliation_strings":["Data Science & Advanced Analytics, Data Science & Artificial Intelligence, R&D, AstraZeneca, Cambridge CB2 8PA, U.K"],"affiliations":[{"raw_affiliation_string":"Data Science & Advanced Analytics, Data Science & Artificial Intelligence, R&D, AstraZeneca, Cambridge CB2 8PA, U.K","institution_ids":["https://openalex.org/I4210109524"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056748708","display_name":"P\u00edetro Li\u00f3","orcid":"https://orcid.org/0000-0002-0540-5053"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pietro Li\u00f2","raw_affiliation_strings":["Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, U.K"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, University of Cambridge, Cambridge CB3 0FD, U.K","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5081668013"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":3.9087,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.94577194,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"63","issue":"9","first_page":"2667","last_page":"2678"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9361000061035156,"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/pubchem","display_name":"PubChem","score":0.9181530475616455},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7561439275741577},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.7276843190193176},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6284799575805664},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6081955432891846},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5257062315940857},{"id":"https://openalex.org/keywords/high-throughput-screening","display_name":"High-throughput screening","score":0.4831237494945526},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.4410301446914673},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4403519928455353},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.338606595993042},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.17095491290092468},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.14299964904785156},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09519487619400024}],"concepts":[{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.9181530475616455},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7561439275741577},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.7276843190193176},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6284799575805664},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6081955432891846},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5257062315940857},{"id":"https://openalex.org/C51323132","wikidata":"https://www.wikidata.org/wiki/Q626251","display_name":"High-throughput screening","level":2,"score":0.4831237494945526},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.4410301446914673},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4403519928455353},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.338606595993042},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.17095491290092468},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.14299964904785156},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09519487619400024},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001681","descriptor_name":"Biological Assay","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019985","descriptor_name":"Benchmarking","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jcim.2c01569","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01569","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:37058588","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37058588","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},{"id":"pmh:oai:iris.uniroma1.it:11573/1723982","is_oa":true,"landing_page_url":"https://hdl.handle.net/11573/1723982","pdf_url":"https://iris.uniroma1.it/bitstream/11573/1723982/2/Buterez_MF-PCBA_2023.pdf","source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10170507","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10170507","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10170507/pdf/ci2c01569.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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.2c01569","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01569","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1969073798","https://openalex.org/W2031441006","https://openalex.org/W2050081822","https://openalex.org/W2155478691","https://openalex.org/W2235675062","https://openalex.org/W2594183968","https://openalex.org/W2613900957","https://openalex.org/W2806547269","https://openalex.org/W2809247499","https://openalex.org/W2899587428","https://openalex.org/W2900090807","https://openalex.org/W2954088480","https://openalex.org/W2967052368","https://openalex.org/W3007309629","https://openalex.org/W3015572666","https://openalex.org/W3022256936","https://openalex.org/W3043238520","https://openalex.org/W3103736477","https://openalex.org/W3126232929","https://openalex.org/W3182706339","https://openalex.org/W4280619953","https://openalex.org/W4282053982","https://openalex.org/W4296035488","https://openalex.org/W4310895557"],"related_works":["https://openalex.org/W2460225311","https://openalex.org/W1964976889","https://openalex.org/W3012362343","https://openalex.org/W3018299999","https://openalex.org/W3009346573","https://openalex.org/W3018504856","https://openalex.org/W2079781933","https://openalex.org/W3011653581","https://openalex.org/W1862448690","https://openalex.org/W2811096937"],"abstract_inverted_index":{"High-throughput":[0],"screening":[1],"(HTS),":[2],"as":[3],"one":[4],"of":[5,28,45,47,54,95,115,121,123,136,140,156,197,231,251,266,276,279],"the":[6,29,102,112,134,195,209,215,223,237,243,260,264,277,280,302],"key":[7],"techniques":[8],"in":[9,20,69,107,133,212,229,274],"drug":[10,18,63,82],"discovery,":[11],"is":[12,36],"frequently":[13],"used":[14],"to":[15,80,119,168,226,241],"identify":[16],"promising":[17],"candidates":[19],"a":[21,37,153,188,252,272],"largely":[22],"automated":[23],"and":[24,39,61,76,85,87,170,186,199,217,236,271],"cost-effective":[25],"way.":[26],"One":[27],"necessary":[30],"conditions":[31],"for":[32,59,164,192,256],"successful":[33],"HTS":[34,109,141,184,269],"campaigns":[35],"large":[38],"diverse":[40],"compound":[41],"library,":[42],"enabling":[43],"hundreds":[44,120],"thousands":[46,122],"activity":[48,83,125,282],"measurements":[49,201],"per":[50],"project.":[51],"Such":[52],"collections":[53,94],"data":[55,104,162,180,232],"hold":[56],"great":[57],"promise":[58],"computational":[60],"experimental":[62,90,116],"discovery":[64],"efforts,":[65],"especially":[66],"when":[67],"leveraged":[68],"combination":[70],"with":[71],"modern":[72],"deep":[73],"learning":[74,138],"techniques,":[75],"can":[77,296],"potentially":[78],"lead":[79],"improved":[81],"predictions":[84],"cheaper":[86],"more":[88],"effective":[89],"design.":[91],"However,":[92],"existing":[93],"machine-learning-ready":[96],"public":[97],"datasets":[98,158,295],"do":[99],"not":[100],"exploit":[101],"multiple":[103],"modalities":[105,163],"present":[106,187],"real-world":[108,183],"projects.":[110],"Thus,":[111],"largest":[113],"fraction":[114],"measurements,":[117],"corresponding":[118,167],"\"noisy\"":[124],"values":[126],"from":[127,234],"primary":[128,169,216],"screening,":[129,172],"are":[130],"effectively":[131],"ignored":[132],"majority":[135],"machine":[137,193],"models":[139],"data.":[142,245],"To":[143],"address":[144],"these":[145],"limitations,":[146],"we":[147,176,221],"introduce":[148],"Multifidelity":[149,179],"PubChem":[150,235],"BioAssay":[151],"(MF-PCBA),":[152],"curated":[154],"collection":[155],"60":[157],"that":[159,175],"includes":[160],"two":[161],"each":[165],"dataset,":[166],"confirmatory":[171,218],"an":[173,249],"aspect":[174],"call":[177],"<i>multifidelity</i>.":[178],"accurately":[181],"reflect":[182],"conventions":[185],"new,":[189],"challenging":[190],"task":[191],"learning:":[194],"integration":[196,258],"low-":[198],"high-fidelity":[200],"through":[202],"molecular":[203,281],"representation":[204],"learning,":[205],"taking":[206],"into":[207],"account":[208],"orders-of-magnitude":[210],"difference":[211],"size":[213],"between":[214],"screens.":[219],"Here":[220],"detail":[222],"steps":[224,239],"taken":[225],"assemble":[227],"MF-PCBA":[228,286],"terms":[230,275],"acquisition":[233],"filtering":[238],"required":[240],"curate":[242],"raw":[244],"We":[246],"also":[247],"provide":[248],"evaluation":[250],"recent":[253],"deep-learning-based":[254],"method":[255],"multifidelity":[257],"across":[259],"introduced":[261],"datasets,":[262],"demonstrating":[263],"benefit":[265],"leveraging":[267],"all":[268],"modalities,":[270],"discussion":[273],"roughness":[278],"landscape.":[283],"In":[284],"total,":[285],"contains":[287],"over":[288],"16.6":[289],"million":[290],"unique":[291],"molecule-protein":[292],"interactions.":[293],"The":[294],"be":[297],"easily":[298],"assembled":[299],"by":[300],"using":[301],"source":[303],"code":[304],"available":[305],"at":[306],"https://github.com/davidbuterez/mf-pcba.":[307]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":5}],"updated_date":"2026-04-16T15:07:20.185449","created_date":"2025-10-10T00:00:00"}