{"id":"https://openalex.org/W4414360322","doi":"https://doi.org/10.24963/ijcai.2025/1022","title":"Diversity-Aware Reinforcement Learning for de novo Drug Design","display_name":"Diversity-Aware Reinforcement Learning for de novo Drug Design","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360322","doi":"https://doi.org/10.24963/ijcai.2025/1022"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/1022","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5021208329","display_name":"Hampus Gummesson Svensson","orcid":"https://orcid.org/0000-0003-0765-1837"},"institutions":[{"id":"https://openalex.org/I4210116875","display_name":"AstraZeneca (Brazil)","ror":"https://ror.org/026m9xy48","country_code":"BR","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210116875"]},{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["BR","SE"],"is_corresponding":false,"raw_author_name":"Hampus Gummesson Svensson","raw_affiliation_strings":["AstraZeneca","Chalmers University of Technology and University of Gothenburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca","institution_ids":["https://openalex.org/I4210116875"]},{"raw_affiliation_string":"Chalmers University of Technology and University of Gothenburg","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051401603","display_name":"Christian Tyrchan","orcid":"https://orcid.org/0000-0002-6470-984X"},"institutions":[{"id":"https://openalex.org/I4210116875","display_name":"AstraZeneca (Brazil)","ror":"https://ror.org/026m9xy48","country_code":"BR","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210116875"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Christian Tyrchan","raw_affiliation_strings":["AstraZeneca"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca","institution_ids":["https://openalex.org/I4210116875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076975589","display_name":"Ola Engkvist","orcid":"https://orcid.org/0000-0003-4970-6461"},"institutions":[{"id":"https://openalex.org/I4210116875","display_name":"AstraZeneca (Brazil)","ror":"https://ror.org/026m9xy48","country_code":"BR","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210116875"]},{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["BR","SE"],"is_corresponding":false,"raw_author_name":"Ola Engkvist","raw_affiliation_strings":["AstraZeneca","Chalmers University of Technology and University of Gothenburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AstraZeneca","institution_ids":["https://openalex.org/I4210116875"]},{"raw_affiliation_string":"Chalmers University of Technology and University of Gothenburg","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015876","display_name":"Morteza Haghir Chehreghani","orcid":"https://orcid.org/0000-0002-2912-7422"},"institutions":[{"id":"https://openalex.org/I66862912","display_name":"Chalmers University of Technology","ror":"https://ror.org/040wg7k59","country_code":"SE","type":"education","lineage":["https://openalex.org/I66862912"]},{"id":"https://openalex.org/I881427289","display_name":"University of Gothenburg","ror":"https://ror.org/01tm6cn81","country_code":"SE","type":"education","lineage":["https://openalex.org/I881427289"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Morteza Haghir Chehreghani","raw_affiliation_strings":["Chalmers University of Technology and University of Gothenburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chalmers University of Technology and University of Gothenburg","institution_ids":["https://openalex.org/I66862912","https://openalex.org/I881427289"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9194","last_page":"9204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.7558000087738037,"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":0.7558000087738037,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.6934999823570251,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.6906999945640564,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8198000192642212},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5884000062942505},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.571399986743927},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5375999808311462},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5364999771118164},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.38850000500679016},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.37209999561309814}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8198000192642212},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6033999919891357},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5884000062942505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.571399986743927},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5375999808311462},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5033000111579895},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4068000018596649},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2913999855518341},{"id":"https://openalex.org/C2780035454","wikidata":"https://www.wikidata.org/wiki/Q8386","display_name":"Drug","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C64903051","wikidata":"https://www.wikidata.org/wiki/Q2198549","display_name":"Drug development","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2547000050544739}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/1022","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/1022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Fine-tuning":[0],"a":[1,21,32,69,85,96,149],"pre-trained":[2],"generative":[3],"model":[4],"has":[5,104,126],"demonstrated":[6],"good":[7],"performance":[8],"in":[9,41,59,68,77,188],"generating":[10],"promising":[11,100],"drug":[12,38,80],"molecules.":[13,39,101,143,174],"The":[14,62],"fine-tuning":[15],"task":[16],"is":[17,92],"often":[18],"formulated":[19],"as":[20,84],"reinforcement":[22],"learning":[23],"problem,":[24],"where":[25],"previous":[26],"methods":[27,155,183],"efficiently":[28],"learn":[29],"to":[30,35,75,94,158],"optimize":[31],"reward":[33,51,107,136],"function":[34,108,137],"generate":[36,95],"potential":[37,86],"Nevertheless,":[40],"the":[42,50,53,65,78,106,135,139,160,167,170],"absence":[43],"of":[44,64,99,141,152,169,172,190],"an":[45],"adaptive":[46,131],"update":[47,132],"mechanism":[48],"for":[49,134],"function,":[52],"optimization":[54,71,81],"process":[55,82],"can":[56],"become":[57],"stuck":[58],"local":[60,70],"optima.":[61],"efficacy":[63],"optimal":[66],"molecule":[67],"may":[72],"not":[73],"translate":[74],"usefulness":[76],"subsequent":[79],"or":[83],"standalone":[87],"clinical":[88],"candidate.":[89],"Therefore,":[90],"it":[91],"important":[93],"diverse":[97],"set":[98,171],"Prior":[102],"work":[103],"modified":[105],"by":[109],"penalizing":[110],"structurally":[111],"similar":[112],"molecules,":[113],"primarily":[114],"focusing":[115],"on":[116],"finding":[117],"molecules":[118],"with":[119],"higher":[120],"rewards.":[121],"To":[122],"date,":[123],"no":[124],"study":[125],"comprehensively":[127],"examined":[128],"how":[129,164],"different":[130],"mechanisms":[133],"influence":[138],"diversity":[140,168],"generated":[142,173],"In":[144],"this":[145],"work,":[146],"we":[147],"investigate":[148],"wide":[150],"range":[151],"intrinsic":[153],"motivation":[154],"and":[156,163,181],"strategies":[157],"penalize":[159],"extrinsic":[161],"reward,":[162],"they":[165],"affect":[166],"Our":[175],"experiments":[176],"reveal":[177],"that":[178],"combining":[179],"structure-":[180],"prediction-based":[182],"generally":[184],"yields":[185],"better":[186],"results":[187],"terms":[189],"diversity.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}