{"id":"https://openalex.org/W4394767381","doi":"https://doi.org/10.1186/s13321-024-00832-1","title":"Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors","display_name":"Comprehensive machine learning boosts structure-based virtual screening for PARP1 inhibitors","publication_year":2024,"publication_date":"2024-04-06","ids":{"openalex":"https://openalex.org/W4394767381","doi":"https://doi.org/10.1186/s13321-024-00832-1"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00832-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00832-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00832-1","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00832-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094177895","display_name":"Klaudia Caba","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Klaudia Caba","raw_affiliation_strings":["Department of Bioengineering, Imperial College London, London, SW7 2AZ, UK","Department of Bioengineering [Imperial College London] (Imperial College London, South Kensington Campus, SW7 2AZ London, UK  - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Bioengineering [Imperial College London] (Imperial College London, South Kensington Campus, SW7 2AZ London, UK  - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014611705","display_name":"Viet\u2010Khoa Tran\u2010Nguyen","orcid":"https://orcid.org/0000-0001-7497-333X"},"institutions":[{"id":"https://openalex.org/I204730241","display_name":"Universit\u00e9 Paris Cit\u00e9","ror":"https://ror.org/05f82e368","country_code":"FR","type":"education","lineage":["https://openalex.org/I204730241"]},{"id":"https://openalex.org/I4210137329","display_name":"Unit of Functional and Adaptive Biology","ror":"https://ror.org/02z0jq636","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I4210096427","https://openalex.org/I4210137329"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Viet-Khoa Tran-Nguyen","raw_affiliation_strings":["Unit\u00e9 de Biologie Fonctionnelle et Adaptative (BFA), UFR Sciences du Vivant, Universit\u00e9 Paris Cit\u00e9, 75013, Paris, France","BFA (UMR_8251 / U1133) - Unit\u00e9 de Biologie Fonctionnelle et Adaptative (Universit\u00e9 Paris Diderot, B\u00e2t. Buffon, 4 rue Marie-Andr\u00e9e Lagroua Weill-Hall\u00e9, case postale 7081 , 75205 Paris cedex 13 - France)"],"affiliations":[{"raw_affiliation_string":"Unit\u00e9 de Biologie Fonctionnelle et Adaptative (BFA), UFR Sciences du Vivant, Universit\u00e9 Paris Cit\u00e9, 75013, Paris, France","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I4210137329"]},{"raw_affiliation_string":"BFA (UMR_8251 / U1133) - Unit\u00e9 de Biologie Fonctionnelle et Adaptative (Universit\u00e9 Paris Diderot, B\u00e2t. Buffon, 4 rue Marie-Andr\u00e9e Lagroua Weill-Hall\u00e9, case postale 7081 , 75205 Paris cedex 13 - France)","institution_ids":["https://openalex.org/I204730241","https://openalex.org/I4210137329"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056897202","display_name":"Taufiq Rahman","orcid":"https://orcid.org/0000-0003-3830-5160"},"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":"Taufiq Rahman","raw_affiliation_strings":["Department of Pharmacology, University of Cambridge, Cambridge, CB2 1PD, UK","CAM - University of Cambridge [UK] (The Old Schools, Trinity Lane, Cambridge CB2 1TN - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Department of Pharmacology, University of Cambridge, Cambridge, CB2 1PD, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"CAM - University of Cambridge [UK] (The Old Schools, Trinity Lane, Cambridge CB2 1TN - United Kingdom)","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005597587","display_name":"Pedro J. Ballester","orcid":"https://orcid.org/0000-0002-4078-743X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pedro J. Ballester","raw_affiliation_strings":["Department of Bioengineering, Imperial College London, London, SW7 2AZ, UK","Department of Bioengineering [Imperial College London] (Imperial College London, South Kensington Campus, SW7 2AZ London, UK  - United Kingdom)"],"affiliations":[{"raw_affiliation_string":"Department of Bioengineering, Imperial College London, London, SW7 2AZ, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Bioengineering [Imperial College London] (Imperial College London, South Kensington Campus, SW7 2AZ London, UK  - United Kingdom)","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5094177895"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":4.6076,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":{"value":0.95906916,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"16","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11914","display_name":"PARP inhibition in cancer therapy","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11914","display_name":"PARP inhibition in cancer therapy","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/2730","display_name":"Oncology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9984999895095825,"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/virtual-screening","display_name":"Virtual screening","score":0.8283228874206543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6949241161346436},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4210087060928345},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.3767290711402893},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.360365092754364},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3563711941242218},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.28123557567596436},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08814063668251038}],"concepts":[{"id":"https://openalex.org/C103697762","wikidata":"https://www.wikidata.org/wiki/Q4112105","display_name":"Virtual screening","level":3,"score":0.8283228874206543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6949241161346436},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4210087060928345},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3767290711402893},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.360365092754364},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3563711941242218},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.28123557567596436},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08814063668251038}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00832-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00832-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00832-1","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10999096","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10999096","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10999096/pdf/13321_2024_Article_832.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 Cheminform","raw_type":"Text"},{"id":"pmh:oai:HAL:hal-04587589v1","is_oa":false,"landing_page_url":"https://u-paris.hal.science/hal-04587589","pdf_url":null,"source":{"id":"https://openalex.org/S4406922466","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, 2024, 16, pp.40. ⟨10.1186/s13321-024-00832-1⟩","raw_type":"Journal articles"},{"id":"pmh:oai:doaj.org/article:a02fc69f5f844477a791bb844350e043","is_oa":true,"landing_page_url":"https://doaj.org/article/a02fc69f5f844477a791bb844350e043","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 1-17 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00832-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00832-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00832-1","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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320006","display_name":"Royal Society","ror":"https://ror.org/03wnrjx87"},{"id":"https://openalex.org/F4320320670","display_name":"Wolfson Foundation","ror":"https://ror.org/0333xzh65"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4394767381.pdf"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W1437335841","https://openalex.org/W1584549675","https://openalex.org/W1950993160","https://openalex.org/W1965006127","https://openalex.org/W1968319881","https://openalex.org/W1973268287","https://openalex.org/W1986240377","https://openalex.org/W1988037271","https://openalex.org/W1997701156","https://openalex.org/W2009007206","https://openalex.org/W2011476357","https://openalex.org/W2025526529","https://openalex.org/W2028629022","https://openalex.org/W2037535298","https://openalex.org/W2042110087","https://openalex.org/W2043068232","https://openalex.org/W2044757858","https://openalex.org/W2075020622","https://openalex.org/W2083618156","https://openalex.org/W2095798342","https://openalex.org/W2105668062","https://openalex.org/W2108245251","https://openalex.org/W2117269243","https://openalex.org/W2121895929","https://openalex.org/W2128983966","https://openalex.org/W2130479394","https://openalex.org/W2132629607","https://openalex.org/W2134967712","https://openalex.org/W2145200068","https://openalex.org/W2148512505","https://openalex.org/W2160466424","https://openalex.org/W2169678694","https://openalex.org/W2180511269","https://openalex.org/W2295598076","https://openalex.org/W2325814368","https://openalex.org/W2336411773","https://openalex.org/W2399340976","https://openalex.org/W2558999090","https://openalex.org/W2583907533","https://openalex.org/W2608559058","https://openalex.org/W2889677957","https://openalex.org/W2895884529","https://openalex.org/W2902886329","https://openalex.org/W2906986535","https://openalex.org/W2910350699","https://openalex.org/W2911964244","https://openalex.org/W2922063386","https://openalex.org/W2947607756","https://openalex.org/W2949923262","https://openalex.org/W2951058429","https://openalex.org/W2972485984","https://openalex.org/W2980234582","https://openalex.org/W2982082445","https://openalex.org/W2987630388","https://openalex.org/W2990484356","https://openalex.org/W3005417975","https://openalex.org/W3006045662","https://openalex.org/W3007134878","https://openalex.org/W3012107310","https://openalex.org/W3020257619","https://openalex.org/W3030018498","https://openalex.org/W3035777330","https://openalex.org/W3043660595","https://openalex.org/W3045609982","https://openalex.org/W3081569548","https://openalex.org/W3087491618","https://openalex.org/W3104705366","https://openalex.org/W3117358516","https://openalex.org/W3118248066","https://openalex.org/W3133989558","https://openalex.org/W3154040614","https://openalex.org/W3159430945","https://openalex.org/W3164081635","https://openalex.org/W3168430821","https://openalex.org/W3183970717","https://openalex.org/W3202428668","https://openalex.org/W3204453900","https://openalex.org/W4206018883","https://openalex.org/W4206912588","https://openalex.org/W4220779662","https://openalex.org/W4239510810","https://openalex.org/W4287448187","https://openalex.org/W4306965236","https://openalex.org/W4322422874","https://openalex.org/W4323966466","https://openalex.org/W4383216745","https://openalex.org/W4387673203","https://openalex.org/W4388456666","https://openalex.org/W4389617734","https://openalex.org/W4391256965"],"related_works":["https://openalex.org/W2059230675","https://openalex.org/W2961085424","https://openalex.org/W2376003823","https://openalex.org/W4306674287","https://openalex.org/W4402273478","https://openalex.org/W2594726310","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116"],"abstract_inverted_index":{"Abstract":[0],"Poly":[1],"ADP-ribose":[2],"polymerase":[3],"1":[4],"(PARP1)":[5],"is":[6,102],"an":[7],"attractive":[8],"therapeutic":[9],"target":[10],"for":[11],"cancer":[12],"treatment.":[13],"Machine-learning":[14],"scoring":[15,29,99,144,149],"functions":[16,30],"constitute":[17],"a":[18,115],"promising":[19],"approach":[20],"to":[21,47,68],"discovering":[22],"novel":[23],"PARP1":[24,42],"inhibitors.":[25],"Cutting-edge":[26],"PARP1-specific":[27,104],"machine-learning":[28],"were":[31],"investigated":[32,143],"using":[33,79],"semi-synthetic":[34],"training":[35,72],"data":[36],"from":[37,88],"docking":[38,89],"activity-labelled":[39],"molecules:":[40],"known":[41],"inhibitors,":[43],"hard-to-discriminate":[44],"decoys":[45],"property-matched":[46],"them":[48],"with":[49],"generative":[50],"graph":[51],"neural":[52],"networks":[53],"and":[54,84,91,136],"confirmed":[55],"inactives.":[56],"We":[57],"further":[58],"made":[59],"test":[60,127],"sets":[61],"harder":[62],"by":[63],"including":[64],"only":[65,93],"molecules":[66],"dissimilar":[67],"those":[69],"in":[70],"the":[71,103,121,125,147],"set.":[73],"Comprehensive":[74],"analysis":[75],"of":[76,133],"these":[77],"datasets":[78],"five":[80],"supervised":[81],"learning":[82],"algorithms,":[83],"protein\u2013ligand":[85],"fingerprints":[86],"extracted":[87],"poses":[90],"ligand":[92],"features":[94],"revealed":[95],"one":[96],"highly":[97],"predictive":[98,139],"function.":[100],"This":[101],"support":[105],"vector":[106],"machine-based":[107],"regressor,":[108],"when":[109],"employing":[110],"PLEC":[111],"fingerprints,":[112],"which":[113],"achieved":[114],"high":[116],"Normalized":[117],"Enrichment":[118],"Factor":[119],"at":[120],"top":[122],"1%":[123],"on":[124],"hardest":[126],"set":[128],"(NEF1%":[129],"=":[130],"0.588,":[131],"median":[132],"10":[134],"repetitions),":[135],"was":[137],"more":[138],"than":[140],"any":[141],"other":[142],"function,":[145],"especially":[146],"classical":[148],"function":[150],"employed":[151],"as":[152],"baseline.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}