{"id":"https://openalex.org/W3126502429","doi":"https://doi.org/10.1021/acs.jcim.1c00096","title":"Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses","display_name":"Learning from Docked Ligands: Ligand-Based Features Rescue Structure-Based Scoring Functions When Trained on Docked Poses","publication_year":2021,"publication_date":"2021-09-01","ids":{"openalex":"https://openalex.org/W3126502429","doi":"https://doi.org/10.1021/acs.jcim.1c00096","mag":"3126502429","pmid":"https://pubmed.ncbi.nlm.nih.gov/34469150"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00096","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00096","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":"review","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/A5016484730","display_name":"Fergus Boyles","orcid":"https://orcid.org/0000-0002-4185-1229"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Fergus Boyles","raw_affiliation_strings":["Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-4185-1229","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015572211","display_name":"Charlotte M. Deane","orcid":"https://orcid.org/0000-0003-1388-2252"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Charlotte M. Deane","raw_affiliation_strings":["Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1388-2252","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011245839","display_name":"Garrett M. Morris","orcid":"https://orcid.org/0000-0003-1731-8405"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Garrett M. Morris","raw_affiliation_strings":["Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1731-8405","affiliations":[{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles\u2019, Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Department of Statistics, University of Oxford, 24-29 St Giles', Oxford, OX1 3LB, United Kingdom","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011245839"],"corresponding_institution_ids":["https://openalex.org/I40120149"],"apc_list":null,"apc_paid":null,"fwci":2.574,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90614774,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"62","issue":"22","first_page":"5329","last_page":"5341"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9958999752998352,"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/T10252","display_name":"Microbial Natural Products and Biosynthesis","score":0.9847999811172485,"subfield":{"id":"https://openalex.org/subfields/2736","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.8473843336105347},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6142462491989136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6038533449172974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5597746968269348},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47607582807540894},{"id":"https://openalex.org/keywords/protein-ligand","display_name":"Protein ligand","score":0.47074657678604126},{"id":"https://openalex.org/keywords/docking","display_name":"Docking (animal)","score":0.4544726312160492},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4492267668247223},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.421235591173172},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.20997673273086548},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.1992799937725067},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.1652199923992157},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.16382300853729248},{"id":"https://openalex.org/keywords/biochemistry","display_name":"Biochemistry","score":0.07240226864814758}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.8473843336105347},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6142462491989136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6038533449172974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5597746968269348},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47607582807540894},{"id":"https://openalex.org/C109095088","wikidata":"https://www.wikidata.org/wiki/Q899107","display_name":"Protein ligand","level":2,"score":0.47074657678604126},{"id":"https://openalex.org/C41685203","wikidata":"https://www.wikidata.org/wiki/Q1974042","display_name":"Docking (animal)","level":2,"score":0.4544726312160492},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4492267668247223},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.421235591173172},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.20997673273086548},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.1992799937725067},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1652199923992157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.16382300853729248},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.07240226864814758},{"id":"https://openalex.org/C159110408","wikidata":"https://www.wikidata.org/wiki/Q121176","display_name":"Nursing","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008024","descriptor_name":"Ligands","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011485","descriptor_name":"Protein Binding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062105","descriptor_name":"Molecular Docking Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.1c00096","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00096","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:34469150","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34469150","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:ora.ox.ac.uk:uuid:bd4636ee-c153-4780-9d90-a9b22f59f4c4","is_oa":false,"landing_page_url":"https://ora.ox.ac.uk/objects/uuid:bd4636ee-c153-4780-9d90-a9b22f59f4c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306402636","display_name":"Oxford University Research Archive (ORA) (University of Oxford)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I40120149","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/I40120149"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symplectic Elements","raw_type":"Journal article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1571791257","display_name":"EPSRC and MRC Centre for Doctoral Training in Systems Approaches to Biomedical Science","funder_award_id":"EP/L016044/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5464881661","display_name":"Systems Biology Doctoral Training Centre","funder_award_id":"EP/G03706X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6908532722","display_name":"EPSRC CDT in Sustainable Approaches to Biomedical Science: Responsible and Reproducible Research - SABS:R^3","funder_award_id":"EP/S024093/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1527782499","https://openalex.org/W1968319881","https://openalex.org/W1974324284","https://openalex.org/W1988037271","https://openalex.org/W1992441011","https://openalex.org/W1993285168","https://openalex.org/W1993403967","https://openalex.org/W2013085020","https://openalex.org/W2022998385","https://openalex.org/W2028609644","https://openalex.org/W2028629022","https://openalex.org/W2030286884","https://openalex.org/W2065854198","https://openalex.org/W2075020622","https://openalex.org/W2076779488","https://openalex.org/W2092285329","https://openalex.org/W2096740407","https://openalex.org/W2101234009","https://openalex.org/W2128983966","https://openalex.org/W2130479394","https://openalex.org/W2134967712","https://openalex.org/W2148512505","https://openalex.org/W2169678694","https://openalex.org/W2244785476","https://openalex.org/W2521525223","https://openalex.org/W2550887636","https://openalex.org/W2558999090","https://openalex.org/W2587598315","https://openalex.org/W2784213390","https://openalex.org/W2792951589","https://openalex.org/W2800892557","https://openalex.org/W2889677957","https://openalex.org/W2902812092","https://openalex.org/W2911964244","https://openalex.org/W2918239264","https://openalex.org/W2922063386","https://openalex.org/W2963883198","https://openalex.org/W2978132989","https://openalex.org/W2980234582","https://openalex.org/W2980863799","https://openalex.org/W3005009369","https://openalex.org/W3005417975","https://openalex.org/W3008726875","https://openalex.org/W3010016408","https://openalex.org/W3106162654","https://openalex.org/W3109549311","https://openalex.org/W3129321183","https://openalex.org/W3168430821"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W4286629047","https://openalex.org/W2917182849","https://openalex.org/W3201070945","https://openalex.org/W2792951589","https://openalex.org/W1185153672","https://openalex.org/W1999725648","https://openalex.org/W2510617091"],"abstract_inverted_index":{"Machine":[0],"learning":[1,65,84],"scoring":[2,15,66,85,100,112,140,186,206],"functions":[3,16,141,207],"for":[4,55,204],"protein-ligand":[5,26],"binding":[6,128,161],"affinity":[7,129,162],"have":[8],"been":[9],"found":[10],"to":[11,39,126,135,191],"consistently":[12],"outperform":[13],"classical":[14],"when":[17,37],"trained":[18,87,102,142],"and":[19,58,88,103,118,121,143,168,208],"tested":[20,89,104,144],"on":[21,90,105,145,173],"crystal":[22,146],"structures":[23],"of":[24,42,49,63,80,97,137,176],"bound":[25],"complexes.":[27,43],"However,":[28],"it":[29],"is":[30,93,133],"less":[31],"clear":[32],"how":[33,46],"these":[34],"methods":[35],"perform":[36],"applied":[38],"docked":[40,50,91,131,174],"poses":[41,54,92,132,175],"We":[44,108,148],"explore":[45],"the":[47,61,69,78,98,177,198,202],"use":[48],"rather":[51],"than":[52,95],"crystallographic":[53,106],"both":[56,116],"training":[57,199],"testing":[59],"affects":[60],"performance":[62,79,172],"machine":[64,83],"functions.":[67],"Using":[68],"PDBbind":[70,178],"Core":[71,179],"Sets":[72],"as":[73],"benchmarks,":[74],"we":[75,181],"show":[76,122],"that":[77,96,123,136,183],"a":[81,110,151,192],"structure-based":[82,117,139],"function":[86,101,113,187],"lower":[94],"same":[99],"poses.":[107,147],"construct":[109],"hybrid":[111,185],"by":[114],"combining":[115],"ligand-based":[119],"features,":[120],"its":[124],"ability":[125],"predict":[127],"using":[130,164],"comparable":[134],"purely":[138],"also":[149],"present":[150],"new,":[152],"freely":[153],"available":[154],"validation":[155,210],"set\u2500the":[156],"Updated":[157],"DUD-E":[158,167],"Diverse":[159],"Subset\u2500for":[160],"prediction":[163],"data":[165],"from":[166],"ChEMBL.":[169],"Despite":[170],"strong":[171],"Sets,":[180],"find":[182],"our":[184],"sometimes":[188],"generalizes":[189],"poorly":[190],"protein":[193],"target":[194],"not":[195],"represented":[196],"in":[197],"set,":[200],"demonstrating":[201],"need":[203],"improved":[205],"additional":[209],"benchmarks.":[211]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}