{"id":"https://openalex.org/W4210840458","doi":"https://doi.org/10.1021/acs.jcim.1c01545","title":"Analysis of Training and Seed Bias in Small Molecules Generated with a Conditional Graph-Based Variational Autoencoder\u2500Insights for Practical AI-Driven Molecule Generation","display_name":"Analysis of Training and Seed Bias in Small Molecules Generated with a Conditional Graph-Based Variational Autoencoder\u2500Insights for Practical AI-Driven Molecule Generation","publication_year":2022,"publication_date":"2022-02-07","ids":{"openalex":"https://openalex.org/W4210840458","doi":"https://doi.org/10.1021/acs.jcim.1c01545","pmid":"https://pubmed.ncbi.nlm.nih.gov/35130440"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c01545","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01545","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/A5084603123","display_name":"Seung-Gu Kang","orcid":"https://orcid.org/0000-0002-4010-0829"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Seung-gu Kang","raw_affiliation_strings":["Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States"],"raw_orcid":"https://orcid.org/0000-0002-4010-0829","affiliations":[{"raw_affiliation_string":"Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072958773","display_name":"Joseph A. Morrone","orcid":"https://orcid.org/0000-0001-8550-4854"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph A. Morrone","raw_affiliation_strings":["Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States"],"raw_orcid":"https://orcid.org/0000-0001-8550-4854","affiliations":[{"raw_affiliation_string":"Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011490535","display_name":"Jeffrey K. Weber","orcid":"https://orcid.org/0000-0002-5241-9036"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey K. Weber","raw_affiliation_strings":["Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071633654","display_name":"Wendy D. Cornell","orcid":"https://orcid.org/0000-0002-7339-0201"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wendy D. Cornell","raw_affiliation_strings":["Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational Biology Center, IBM Thomas J. Watson Research Center, 1101 Kitchawan Road, Yorktown Heights, New York 10594, United States","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5084603123"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":1.8263,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.86588613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"62","issue":"4","first_page":"801","last_page":"816"},"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":0.9997000098228455,"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":0.9695000052452087,"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/autoencoder","display_name":"Autoencoder","score":0.8507358431816101},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.8202941417694092},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.7198171615600586},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6239740252494812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6107453107833862},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6101953387260437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6019461750984192},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5868454575538635},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5833998918533325},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5321910381317139},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.46723467111587524},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32653921842575073},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.30206388235092163},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.15488764643669128},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.12305119633674622},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.09947395324707031}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8507358431816101},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8202941417694092},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7198171615600586},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6239740252494812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6107453107833862},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6101953387260437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6019461750984192},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5868454575538635},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5833998918533325},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5321910381317139},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.46723467111587524},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32653921842575073},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.30206388235092163},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.15488764643669128},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.12305119633674622},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.09947395324707031},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017448","descriptor_name":"Receptors, Dopamine D2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D017448","descriptor_name":"Receptors, Dopamine D2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D017448","descriptor_name":"Receptors, Dopamine D2","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c01545","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01545","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:35130440","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35130440","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1994859764","https://openalex.org/W1997388207","https://openalex.org/W2014203427","https://openalex.org/W2034549041","https://openalex.org/W2051786044","https://openalex.org/W2160592148","https://openalex.org/W2529996553","https://openalex.org/W2559655401","https://openalex.org/W2565684601","https://openalex.org/W2604314403","https://openalex.org/W2714724074","https://openalex.org/W2735246657","https://openalex.org/W2753738274","https://openalex.org/W2900694120","https://openalex.org/W2901476322","https://openalex.org/W2909929882","https://openalex.org/W2912171584","https://openalex.org/W2915175970","https://openalex.org/W2918239264","https://openalex.org/W2942173509","https://openalex.org/W2963028280","https://openalex.org/W2969325194","https://openalex.org/W2971690404","https://openalex.org/W2978132989","https://openalex.org/W2980210687","https://openalex.org/W2989615256","https://openalex.org/W3009321976","https://openalex.org/W3019166713","https://openalex.org/W3023042104","https://openalex.org/W3027325047","https://openalex.org/W3032963903","https://openalex.org/W3043969542","https://openalex.org/W3045928028","https://openalex.org/W3106162654","https://openalex.org/W3133523400","https://openalex.org/W3135156311","https://openalex.org/W4289436753","https://openalex.org/W6912665054"],"related_works":["https://openalex.org/W4309969736","https://openalex.org/W4394785709","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2470043383","https://openalex.org/W3034474024","https://openalex.org/W2770818364","https://openalex.org/W4317242571","https://openalex.org/W4237416477","https://openalex.org/W3127641366"],"abstract_inverted_index":{"The":[0],"application":[1],"of":[2,47,55,108,110,140],"deep":[3,117],"learning":[4,118],"to":[5,35,69,80,120],"generative":[6,76,123],"molecule":[7,150],"design":[8],"has":[9],"shown":[10,79],"early":[11],"promise":[12],"for":[13,102,147],"accelerating":[14],"lead":[15],"series":[16],"development.":[17],"However,":[18],"questions":[19],"remain":[20],"concerning":[21],"how":[22],"factors":[23],"like":[24],"training,":[25],"data":[26,66],"set,":[27],"and":[28,37,49,87,113,133],"seed":[29,48],"bias":[30,51],"impact":[31,46],"the":[32,45,53,70,103,122],"technology's":[33],"utility":[34],"medicinal":[36],"computational":[38],"chemists.":[39],"In":[40],"this":[41],"work,":[42],"we":[43,114,126],"analyze":[44],"training":[50,134],"on":[52],"output":[54],"an":[56,97],"activity-conditioned":[57],"graph-based":[58,75],"variational":[59],"autoencoder":[60],"(VAE).":[61],"Leveraging":[62],"a":[63,138],"massive,":[64],"labeled":[65],"set":[67,135],"corresponding":[68],"dopamine":[71],"D2":[72],"receptor,":[73],"our":[74],"model":[77],"is":[78],"excel":[81],"in":[82,92],"producing":[83],"desired":[84],"conditioned":[85],"activities":[86],"favorable":[88],"unconditioned":[89],"physical":[90],"properties":[91],"generated":[93],"molecules.":[94],"We":[95],"implement":[96],"activity-swapping":[98],"method":[99],"that":[100],"allows":[101],"activation,":[104],"deactivation,":[105],"or":[106],"retention":[107],"activity":[109],"molecular":[111,131],"seeds,":[112,132],"apply":[115],"independent":[116],"classifiers":[119],"verify":[121],"results.":[124],"Overall,":[125],"uncover":[127],"relationships":[128],"between":[129],"noise,":[130],"selection":[136],"across":[137],"range":[139],"latent-space":[141],"sampling":[142],"procedures,":[143],"providing":[144],"important":[145],"insights":[146],"practical":[148],"AI-driven":[149],"generation.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}