{"id":"https://openalex.org/W2809489167","doi":"https://doi.org/10.1145/3219819.3219849","title":"PrePeP","display_name":"PrePeP","publication_year":2018,"publication_date":"2018-07-19","ids":{"openalex":"https://openalex.org/W2809489167","doi":"https://doi.org/10.1145/3219819.3219849","mag":"2809489167"},"language":"en","primary_location":{"id":"doi:10.1145/3219819.3219849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3219849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01939468v1/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051402160","display_name":"Maksim Koptelov","orcid":"https://orcid.org/0000-0001-9065-2827"},"institutions":[{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maksim Koptelov","raw_affiliation_strings":["Normandie Universit\u00e9, Caen, France","Equipe CODAG - Laboratoire GREYC - UMR6072","Groupe de Recherche en Informatique, Image et Instrumentation de Caen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Normandie Universit\u00e9, Caen, France","institution_ids":["https://openalex.org/I4210105918"]},{"raw_affiliation_string":"Equipe CODAG - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Groupe de Recherche en Informatique, Image et Instrumentation de Caen","institution_ids":["https://openalex.org/I4210139483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051531853","display_name":"Albrecht Zimmermann","orcid":"https://orcid.org/0000-0002-8319-7456"},"institutions":[{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Albrecht Zimmermann","raw_affiliation_strings":["Normandie Universit\u00e9, Caen, France","Equipe CODAG - Laboratoire GREYC - UMR6072","Groupe de Recherche en Informatique, Image et Instrumentation de Caen"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Normandie Universit\u00e9, Caen, France","institution_ids":["https://openalex.org/I4210105918"]},{"raw_affiliation_string":"Equipe CODAG - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]},{"raw_affiliation_string":"Groupe de Recherche en Informatique, Image et Instrumentation de Caen","institution_ids":["https://openalex.org/I4210139483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027241504","display_name":"Pascal Bonnet","orcid":"https://orcid.org/0000-0001-6485-138X"},"institutions":[{"id":"https://openalex.org/I12449238","display_name":"Universit\u00e9 d'Orl\u00e9ans","ror":"https://ror.org/014zrew76","country_code":"FR","type":"education","lineage":["https://openalex.org/I12449238"]},{"id":"https://openalex.org/I4210141565","display_name":"Institut de Chimie Organique et Analytique","ror":"https://ror.org/03ywn7d79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12449238","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I2738703131","https://openalex.org/I4210128300","https://openalex.org/I4210141565"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Pascal Bonnet","raw_affiliation_strings":["ICOA/University of Orl\u00e9ans, Orl\u00e9ans, France","Institut de Chimie Organique et Analytique"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ICOA/University of Orl\u00e9ans, Orl\u00e9ans, France","institution_ids":["https://openalex.org/I12449238"]},{"raw_affiliation_string":"Institut de Chimie Organique et Analytique","institution_ids":["https://openalex.org/I4210141565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091469186","display_name":"Ronan Bureau","orcid":"https://orcid.org/0000-0001-9404-8117"},"institutions":[{"id":"https://openalex.org/I98702875","display_name":"Universit\u00e9 de Caen Normandie","ror":"https://ror.org/051kpcy16","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Ronan Bureau","raw_affiliation_strings":["CERMN/University of Caen Normandy, Caen, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CERMN/University of Caen Normandy, Caen, France","institution_ids":["https://openalex.org/I98702875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108119396","display_name":"Bruno Cr\u00e9milleux","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105918","display_name":"Normandie Universit\u00e9","ror":"https://ror.org/01k40cz91","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210105918"]},{"id":"https://openalex.org/I4210139483","display_name":"GREYC","ror":"https://ror.org/043749971","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I194210350","https://openalex.org/I4210105918","https://openalex.org/I4210105918","https://openalex.org/I4210139483","https://openalex.org/I4210159245","https://openalex.org/I98702875"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Bruno Cr\u00e9milleux","raw_affiliation_strings":["Normandie Universit\u00e9, Caen, France","Equipe CODAG - Laboratoire GREYC - UMR6072"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Normandie Universit\u00e9, Caen, France","institution_ids":["https://openalex.org/I4210105918"]},{"raw_affiliation_string":"Equipe CODAG - Laboratoire GREYC - UMR6072","institution_ids":["https://openalex.org/I4210139483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0725,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.79586554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"7519","issue":null,"first_page":"462","last_page":"471"},"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9901000261306763,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9805999994277954,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.764643669128418},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6486382484436035},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5838444232940674},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5765123963356018},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5321651697158813},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5204046964645386},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33268314599990845},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3259250223636627},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09513181447982788}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.764643669128418},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6486382484436035},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5838444232940674},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5765123963356018},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5321651697158813},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5204046964645386},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33268314599990845},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3259250223636627},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09513181447982788},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3219819.3219849","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3219819.3219849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-01939468v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01939468","pdf_url":"https://hal.science/hal-01939468v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug 2018, Londres, United Kingdom. pp.462-471, ⟨10.1145/3219819.3219849⟩","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01939468v1","is_oa":true,"landing_page_url":"https://hal.science/hal-01939468","pdf_url":"https://hal.science/hal-01939468v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Aug 2018, Londres, United Kingdom. pp.462-471, ⟨10.1145/3219819.3219849⟩","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.4699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2809489167.pdf","grobid_xml":"https://content.openalex.org/works/W2809489167.grobid-xml"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1182581869","https://openalex.org/W1521790300","https://openalex.org/W1595059031","https://openalex.org/W1607305617","https://openalex.org/W1965769390","https://openalex.org/W1970259423","https://openalex.org/W1979600197","https://openalex.org/W1983691152","https://openalex.org/W2020859943","https://openalex.org/W2029817244","https://openalex.org/W2040523682","https://openalex.org/W2043509228","https://openalex.org/W2051766214","https://openalex.org/W2069950580","https://openalex.org/W2074682587","https://openalex.org/W2076063813","https://openalex.org/W2089966673","https://openalex.org/W2119821739","https://openalex.org/W2128428930","https://openalex.org/W2136593687","https://openalex.org/W2137262074","https://openalex.org/W2143010369","https://openalex.org/W2170726034","https://openalex.org/W2282821441","https://openalex.org/W2327974216","https://openalex.org/W2332896222","https://openalex.org/W2395911948","https://openalex.org/W2397609778","https://openalex.org/W2526759295","https://openalex.org/W2563678022","https://openalex.org/W2579340176","https://openalex.org/W2586253560","https://openalex.org/W2591766847","https://openalex.org/W2606217927","https://openalex.org/W2621548818","https://openalex.org/W2912934387","https://openalex.org/W3085162807","https://openalex.org/W4254763221","https://openalex.org/W6685146747"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Pan":[0],"Assays":[1],"Interference":[2],"Compounds":[3],"(PAINS)":[4],"are":[5,40,54,86,110],"a":[6,60,90],"significant":[7],"problem":[8],"in":[9,18,55,88],"modern":[10],"drug":[11],"discovery:":[12],"compounds":[13],"showing":[14],"non-target":[15],"specific":[16],"activity":[17],"high-throughput":[19],"screening":[20],"can":[21],"mislead":[22],"medicinal":[23],"chemists":[24,109],"during":[25],"hit":[26],"identification,":[27],"wasting":[28],"time":[29],"and":[30,66,127],"resources.":[31],"Recent":[32],"work":[33],"has":[34],"shown":[35],"that":[36,63,85,107,129,138],"existing":[37,135],"structural":[38,95],"alerts":[39,137],"not":[41],"up":[42],"to":[43,69],"the":[44,56,72,75,78,82,98,102,115,118,125],"task":[45],"of":[46,58,101,117,134],"identifying":[47],"PAINS.":[48],"To":[49],"address":[50],"this":[51],"short-coming,":[52],"we":[53,80,130],"process":[57],"developing":[59,89],"tool,":[61],"PrePeP,":[62],"predicts":[64],"PAINS,":[65],"allows":[67],"experts":[68],"visually":[70],"explore":[71],"reasons":[73],"for":[74],"prediction.":[76],"In":[77],"paper,":[79],"discuss":[81],"different":[83],"aspects":[84],"involved":[87],"functional":[91],"tool:":[92],"systematically":[93],"deriving":[94],"descriptors,":[96],"addressing":[97],"extreme":[99],"imbalance":[100],"data,":[103],"offering":[104],"visual":[105],"information":[106],"pharmacological":[108],"familiar":[111],"with.":[112],"We":[113],"evaluate":[114],"quality":[116],"approach":[119],"using":[120],"benchmark":[121],"data":[122],"sets":[123],"from":[124],"literature":[126],"show":[128],"correct":[131],"several":[132],"short-comings":[133],"PAINS":[136],"have":[139],"recently":[140],"been":[141],"pointed":[142],"out.":[143]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2018-06-29T00:00:00"}