{"id":"https://openalex.org/W3210249913","doi":"https://doi.org/10.48550/arxiv.2110.11875","title":"GeneDisco: A Benchmark for Experimental Design in Drug Discovery","display_name":"GeneDisco: A Benchmark for Experimental Design in Drug Discovery","publication_year":2021,"publication_date":"2021-10-22","ids":{"openalex":"https://openalex.org/W3210249913","doi":"https://doi.org/10.48550/arxiv.2110.11875","mag":"3210249913"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2110.11875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11875","pdf_url":"https://arxiv.org/pdf/2110.11875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2110.11875","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014522247","display_name":"Arash Mehrjou","orcid":"https://orcid.org/0000-0002-3832-7784","observed_orcids":["https://orcid.org/0000-0002-3832-7784"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehrjou, Arash","raw_affiliation_strings":["GlaxoSmithKline , Artificial Intelligence & Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GlaxoSmithKline , Artificial Intelligence & Machine Learning","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037886840","display_name":"Ashkan Soleymani","orcid":"https://orcid.org/0009-0006-7278-9014","observed_orcids":["https://orcid.org/0009-0006-7278-9014"]},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soleymani, Ashkan","raw_affiliation_strings":["MIT ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIT ,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062787323","display_name":"Andrew Jesson","orcid":"https://orcid.org/0000-0002-1082-8587","observed_orcids":["https://orcid.org/0000-0002-1082-8587"]},"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":"Jesson, Andrew","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067110406","display_name":"Pascal Notin","orcid":"https://orcid.org/0000-0002-1877-8983","observed_orcids":["https://orcid.org/0000-0002-1877-8983"]},"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":"Notin, Pascal","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029186201","display_name":"Yarin Gal","orcid":"https://orcid.org/0000-0002-2733-2078","observed_orcids":["https://orcid.org/0000-0002-2733-2078"]},"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":"Gal, Yarin","raw_affiliation_strings":["Department of Computer Science , University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018488407","display_name":"Stefan Bauer","orcid":"https://orcid.org/0000-0003-1712-060X","observed_orcids":["https://orcid.org/0000-0003-1712-060X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bauer, Stefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5033154792","display_name":"Patrick Schwab","orcid":"https://orcid.org/0000-0002-2868-7794","observed_orcids":["https://orcid.org/0000-0002-2868-7794"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schwab, Patrick","raw_affiliation_strings":["GlaxoSmithKline , Artificial Intelligence & Machine Learning"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GlaxoSmithKline , Artificial Intelligence & Machine Learning","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.673799991607666,"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":0.673799991607666,"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/T11798","display_name":"Optimal Experimental Design Methods","score":0.08649999648332596,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.06120000034570694,"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/benchmark","display_name":"benchmark","score":0.5059999823570251},{"id":"https://openalex.org/keywords/experimental-design","display_name":"experimental design","score":0.921999990940094},{"id":"https://openalex.org/keywords/active-learning-machine-learning","display_name":"active learning (machine learning)","score":0.8349999785423279},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7950000166893005},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"drug discovery","score":0.7329999804496765},{"id":"https://openalex.org/keywords/crispr-screening","display_name":"CRISPR screen","score":0.6769999861717224},{"id":"https://openalex.org/keywords/target-validation","display_name":"target validation","score":0.9210000038146973}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7058414220809937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6922666430473328},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6244480609893799},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5347147583961487},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.5054850578308105},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4868399500846863},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45837923884391785},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.45452913641929626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4160372018814087},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4135468006134033},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1442422866821289},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.12138810753822327},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"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/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2110.11875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11875","pdf_url":"https://arxiv.org/pdf/2110.11875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3210249913","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2110.11875.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2110.11875","doi":"https://doi.org/10.48550/arxiv.2110.11875","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.11875","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2110.11875","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.11875","pdf_url":"https://arxiv.org/pdf/2110.11875","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":93,"referenced_works":["https://openalex.org/W71499226","https://openalex.org/W582134693","https://openalex.org/W1516659296","https://openalex.org/W1541824660","https://openalex.org/W1543507677","https://openalex.org/W1583833196","https://openalex.org/W1861492603","https://openalex.org/W1872312298","https://openalex.org/W1995008770","https://openalex.org/W1997362383","https://openalex.org/W2009291347","https://openalex.org/W2011986160","https://openalex.org/W2023348596","https://openalex.org/W2028279608","https://openalex.org/W2031912356","https://openalex.org/W2044424923","https://openalex.org/W2047229728","https://openalex.org/W2054912906","https://openalex.org/W2064903582","https://openalex.org/W2073307618","https://openalex.org/W2101234009","https://openalex.org/W2108598243","https://openalex.org/W2111051539","https://openalex.org/W2114533766","https://openalex.org/W2118822739","https://openalex.org/W2140508053","https://openalex.org/W2157177751","https://openalex.org/W2162690533","https://openalex.org/W2178888844","https://openalex.org/W2273267066","https://openalex.org/W2279949369","https://openalex.org/W2339234571","https://openalex.org/W2460937040","https://openalex.org/W2556519015","https://openalex.org/W2561754210","https://openalex.org/W2589658059","https://openalex.org/W2597787948","https://openalex.org/W2606043510","https://openalex.org/W2610148085","https://openalex.org/W2611138580","https://openalex.org/W2620038827","https://openalex.org/W2725988230","https://openalex.org/W2768599997","https://openalex.org/W2773987374","https://openalex.org/W2789816271","https://openalex.org/W2790008564","https://openalex.org/W2790808809","https://openalex.org/W2791058611","https://openalex.org/W2795523207","https://openalex.org/W2800013084","https://openalex.org/W2805002767","https://openalex.org/W2808177712","https://openalex.org/W2809499620","https://openalex.org/W2885096157","https://openalex.org/W2894488843","https://openalex.org/W2900694120","https://openalex.org/W2901411193","https://openalex.org/W2903241977","https://openalex.org/W2903538854","https://openalex.org/W2911373802","https://openalex.org/W2937307539","https://openalex.org/W2939923004","https://openalex.org/W2940242941","https://openalex.org/W2948367246","https://openalex.org/W2950195808","https://openalex.org/W2962411443","https://openalex.org/W2963614225","https://openalex.org/W2963902936","https://openalex.org/W2966546269","https://openalex.org/W2979174981","https://openalex.org/W2981767049","https://openalex.org/W2995245946","https://openalex.org/W2996553179","https://openalex.org/W2998213596","https://openalex.org/W3001475835","https://openalex.org/W3007309629","https://openalex.org/W3016077459","https://openalex.org/W3016722055","https://openalex.org/W3019734328","https://openalex.org/W3022153309","https://openalex.org/W3034183699","https://openalex.org/W3091948595","https://openalex.org/W3103098434","https://openalex.org/W3107527779","https://openalex.org/W3137440186","https://openalex.org/W3165173494","https://openalex.org/W3165996121","https://openalex.org/W3167750552","https://openalex.org/W3173311388","https://openalex.org/W3175260249","https://openalex.org/W3197621371","https://openalex.org/W3212454505","https://openalex.org/W4210396037"],"related_works":["https://openalex.org/W4389501023","https://openalex.org/W1921677569","https://openalex.org/W7098367379","https://openalex.org/W4412157335","https://openalex.org/W7212322317","https://openalex.org/W2523098403","https://openalex.org/W4404312274","https://openalex.org/W4311090921","https://openalex.org/W7034086570","https://openalex.org/W4404573462"],"abstract_inverted_index":{"In":[0],"vitro":[1,51],"cellular":[2],"experimentation":[3],"with":[4],"genetic":[5,52],"interventions,":[6],"using":[7],"for":[8,49,136,158,163,191],"example":[9],"CRISPR":[10],"technologies,":[11],"is":[12,54],"an":[13],"essential":[14],"step":[15],"in":[16,50,69,74,95,146,166],"early-stage":[17],"drug":[18,167],"discovery":[19],"and":[20,35,57,90,133,140,194],"target":[21],"validation":[22],"that":[23],"serves":[24],"to":[25,43,76,114,149],"assess":[26],"initial":[27],"hypotheses":[28,42],"about":[29],"causal":[30],"associations":[31],"between":[32],"biological":[33,81,100],"mechanisms":[34],"disease":[36],"pathologies.":[37],"With":[38],"billions":[39],"of":[40,79,118,174,186],"potential":[41],"test,":[44],"the":[45,58,65,70,77,98,119],"experimental":[46,60,120,164,178,192],"design":[47,121,165,193],"space":[48,101,122],"experiments":[53],"extremely":[55],"vast,":[56],"available":[59,125,177],"capacity":[61],"-":[62,72],"even":[63],"at":[64],"largest":[66],"research":[67,142],"institutions":[68],"world":[71],"pales":[73],"relation":[75],"size":[78],"this":[80,137,147],"hypothesis":[82],"space.":[83],"Machine":[84],"learning":[85,161,189],"methods,":[86],"such":[87],"as":[88,110,112,181,183],"active":[89,160,188],"reinforcement":[91],"learning,":[92],"could":[93],"aid":[94],"optimally":[96],"exploring":[97],"vast":[99],"by":[102],"integrating":[103],"prior":[104],"knowledge":[105],"from":[106],"various":[107],"information":[108],"sources":[109],"well":[111,182],"extrapolating":[113],"yet":[115],"unexplored":[116],"areas":[117],"based":[123],"on":[124],"data.":[126],"However,":[127],"there":[128],"exist":[129],"no":[130],"standardised":[131],"benchmarks":[132],"data":[134,179],"sets":[135,180],"challenging":[138],"task":[139],"little":[141],"has":[143],"been":[144],"conducted":[145],"area":[148],"date.":[150],"Here,":[151],"we":[152],"introduce":[153],"GeneDisco,":[154],"a":[155,171],"benchmark":[156],"suite":[157],"evaluating":[159],"algorithms":[162],"discovery.":[168],"GeneDisco":[169],"contains":[170],"curated":[172],"set":[173],"multiple":[175],"publicly":[176],"open-source":[184],"implementations":[185],"state-of-the-art":[187],"policies":[190],"exploration.":[195]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2021-11-08T00:00:00"}