{"id":"https://openalex.org/W3108004614","doi":"https://doi.org/10.1021/acs.jcim.0c01328","title":"Comparative Study of Deep Generative Models on Chemical Space Coverage","display_name":"Comparative Study of Deep Generative Models on Chemical Space Coverage","publication_year":2021,"publication_date":"2021-05-20","ids":{"openalex":"https://openalex.org/W3108004614","doi":"https://doi.org/10.1021/acs.jcim.0c01328","mag":"3108004614","pmid":"https://pubmed.ncbi.nlm.nih.gov/34015916"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c01328","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01328","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":"article","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/A5100644079","display_name":"Jie Zhang","orcid":"https://orcid.org/0000-0002-5575-303X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I2802148028","display_name":"Guangzhou Institutes of Biomedicine and Health","ror":"https://ror.org/02c31t502","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802148028"]},{"id":"https://openalex.org/I4210107668","display_name":"Guangzhou Regenerative Medicine and Health Guangdong Laboratory","ror":"https://ror.org/01n179w26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210107668"]},{"id":"https://openalex.org/I4210131955","display_name":"Guangdong Laboratory Animals Monitoring Institute","ror":"https://ror.org/02mxq6q49","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210131955"]},{"id":"https://openalex.org/I4210154954","display_name":"State Key Laboratory of Respiratory Disease","ror":"https://ror.org/04hja5e04","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210154954"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jie Zhang","raw_affiliation_strings":["Bioland Laboratory (Guangzhou Regenerative Medicine and Health\u2212Guangdong Laboratory), Guangzhou 510530, P. R. China","Guangdong Provincial Key Laboratory of Laboratory Animals, Guangdong Laboratory Animals Monitoring Institute, Guangzhou 510663, P. R. China","State Key Laboratory of Respiratory Disease, Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-5575-303X","affiliations":[{"raw_affiliation_string":"Bioland Laboratory (Guangzhou Regenerative Medicine and Health\u2212Guangdong Laboratory), Guangzhou 510530, P. R. China","institution_ids":["https://openalex.org/I4210107668"]},{"raw_affiliation_string":"Guangdong Provincial Key Laboratory of Laboratory Animals, Guangdong Laboratory Animals Monitoring Institute, Guangzhou 510663, P. R. China","institution_ids":["https://openalex.org/I4210131955"]},{"raw_affiliation_string":"State Key Laboratory of Respiratory Disease, Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, P. R. China","institution_ids":["https://openalex.org/I2802148028","https://openalex.org/I4210154954","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090993508","display_name":"Roc\u00edo Mercado","orcid":"https://orcid.org/0000-0002-6170-6088"},"institutions":[{"id":"https://openalex.org/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Roc\u00edo Mercado","raw_affiliation_strings":["Discovery Sciences, R&D, AstraZeneca, Gothenburg 43183, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Discovery Sciences, R&D, AstraZeneca, Gothenburg 43183, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"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/I4210143795","display_name":"AstraZeneca (Sweden)","ror":"https://ror.org/04wwrrg31","country_code":"SE","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210143795"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Ola Engkvist","raw_affiliation_strings":["Discovery Sciences, R&D, AstraZeneca, Gothenburg 43183, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-4970-6461","affiliations":[{"raw_affiliation_string":"Discovery Sciences, R&D, AstraZeneca, Gothenburg 43183, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100729955","display_name":"Hongming Chen","orcid":"https://orcid.org/0000-0002-4470-876X"},"institutions":[{"id":"https://openalex.org/I4210107668","display_name":"Guangzhou Regenerative Medicine and Health Guangdong Laboratory","ror":"https://ror.org/01n179w26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210107668"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hongming Chen","raw_affiliation_strings":["Bioland Laboratory (Guangzhou Regenerative Medicine and Health\u2212Guangdong Laboratory), Guangzhou 510530, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bioland Laboratory (Guangzhou Regenerative Medicine and Health\u2212Guangdong Laboratory), Guangzhou 510530, P. R. China","institution_ids":["https://openalex.org/I4210107668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100729955"],"corresponding_institution_ids":["https://openalex.org/I4210107668"],"apc_list":null,"apc_paid":null,"fwci":7.1178,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.97445446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"61","issue":"6","first_page":"2572","last_page":"2581"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9847999811172485,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.7973126173019409},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7662645578384399},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.728289008140564},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7033166885375977},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.662392258644104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6435568332672119},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5944761037826538},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5889925360679626},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5704570412635803},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5540244579315186},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5014500617980957},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4124314785003662},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2202776074409485},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.08800286054611206},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.08495426177978516},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.07505437731742859},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06773459911346436}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.7973126173019409},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7662645578384399},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.728289008140564},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7033166885375977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662392258644104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6435568332672119},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5944761037826538},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5889925360679626},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5704570412635803},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5540244579315186},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5014500617980957},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4124314785003662},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2202776074409485},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.08800286054611206},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.08495426177978516},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07505437731742859},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06773459911346436},{"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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}],"mesh":[{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.0c01328","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01328","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:34015916","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34015916","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}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307770","display_name":"AstraZeneca","ror":"https://ror.org/04r9x1a08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1592238003","https://openalex.org/W1999241626","https://openalex.org/W2041686943","https://openalex.org/W2110114082","https://openalex.org/W2120615054","https://openalex.org/W2141125852","https://openalex.org/W2145287260","https://openalex.org/W2153693853","https://openalex.org/W2257979135","https://openalex.org/W2273267066","https://openalex.org/W2310460235","https://openalex.org/W2529996553","https://openalex.org/W2550821151","https://openalex.org/W2567534979","https://openalex.org/W2578240541","https://openalex.org/W2592725663","https://openalex.org/W2610148085","https://openalex.org/W2618625858","https://openalex.org/W2622206241","https://openalex.org/W2765224015","https://openalex.org/W2790808809","https://openalex.org/W2807841289","https://openalex.org/W2900694120","https://openalex.org/W2925830236","https://openalex.org/W2942023275","https://openalex.org/W2953128081","https://openalex.org/W2963445908","https://openalex.org/W2963575853","https://openalex.org/W2989615256","https://openalex.org/W2991736596","https://openalex.org/W2999242200","https://openalex.org/W3003257820","https://openalex.org/W3012413014","https://openalex.org/W3024423177","https://openalex.org/W3025593963","https://openalex.org/W3038022805","https://openalex.org/W3042595256","https://openalex.org/W3094686696","https://openalex.org/W3098269892","https://openalex.org/W3103145119","https://openalex.org/W3103787556","https://openalex.org/W3107551345","https://openalex.org/W3111676828","https://openalex.org/W3116865743","https://openalex.org/W6610423178"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W2075445622","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"molecular":[0,71,92],"design.":[1],"Thanks":[2],"to":[3,40],"the":[4,53,79,102,113,132,135,142,149,153,162,174],"rapid":[5],"advance":[6],"of":[7,48,57,83,89,101,124,134,152,164],"deep":[8,11,43,70],"learning":[9,12],"techniques,":[10],"architectures":[13],"such":[14,147],"as":[15],"recurrent":[16],"neural":[17],"networks,":[18],"variational":[19],"autoencoders,":[20],"and":[21,65,106,168,189],"adversarial":[22],"networks":[23],"have":[24,37],"been":[25,38],"successfully":[26],"employed":[27],"for":[28,68,126,187],"constructing":[29],"generative":[30,44,72,93,136,154,191],"models.":[31,45,73,175,192],"Recently,":[32],"quite":[33],"a":[34,63,84,121,179],"few":[35],"metrics":[36,50,144],"proposed":[39],"evaluate":[41,52],"these":[42,49],"However,":[46],"many":[47],"cannot":[51],"chemical":[54,80],"space":[55,81],"coverage":[56,82],"sampled":[58],"molecules.":[59],"This":[60],"work":[61],"presents":[62],"novel":[64],"complementary":[66],"metric":[67,75,182],"evaluating":[69,188],"The":[74,87,128],"is":[76],"based":[77],"on":[78],"reference":[85,116],"dataset-GDB-13.":[86],"performance":[88,133],"seven":[90],"different":[91],"models":[94,137,155],"was":[95],"compared":[96,172],"by":[97],"calculating":[98],"what":[99],"fraction":[100,123],"structures,":[103],"ring":[104,166],"systems,":[105],"functional":[107,169],"groups":[108,170],"could":[109],"be":[110,157,185],"reproduced":[111],"from":[112],"largely":[114],"unseen":[115],"set":[117],"when":[118],"using":[119,141],"only":[120],"small":[122],"GDB-13":[125,165],"training.":[127],"results":[129],"show":[130],"that":[131,148,183],"studied":[138],"varies":[139],"significantly":[140],"benchmark":[143],"introduced":[145],"herein,":[146],"generalization":[150],"capabilities":[151],"can":[156,184],"clearly":[158],"differentiated.":[159],"In":[160],"addition,":[161],"coverages":[163],"systems":[167],"were":[171],"between":[173],"Our":[176],"study":[177],"provides":[178],"useful":[180],"new":[181],"used":[186],"comparing":[190]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11}],"updated_date":"2026-04-28T14:05:53.105641","created_date":"2025-10-10T00:00:00"}