{"id":"https://openalex.org/W2925830236","doi":"https://doi.org/10.1186/s13321-019-0341-z","title":"Exploring the GDB-13 chemical space using deep generative models","display_name":"Exploring the GDB-13 chemical space using deep generative models","publication_year":2019,"publication_date":"2019-03-12","ids":{"openalex":"https://openalex.org/W2925830236","doi":"https://doi.org/10.1186/s13321-019-0341-z","mag":"2925830236","pmid":"https://pubmed.ncbi.nlm.nih.gov/30868314"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-019-0341-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0341-z","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0341-z","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0341-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025373665","display_name":"Josep Ar\u00fas\u2010Pous","orcid":"https://orcid.org/0000-0002-9860-2944"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]},{"id":"https://openalex.org/I4210109524","display_name":"AstraZeneca (Australia)","ror":"https://ror.org/018nw3344","country_code":"AU","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210109524"]},{"id":"https://openalex.org/I4210128490","display_name":"AstraZeneca (Japan)","ror":"https://ror.org/047k23798","country_code":"JP","type":"company","lineage":["https://openalex.org/I105036370","https://openalex.org/I4210128490"]},{"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":["AU","CH","JP","SE"],"is_corresponding":true,"raw_author_name":"Josep Ar\u00fas-Pous","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. josep.arus@dcb.unibe.ch","Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden. josep.arus@dcb.unibe.ch","Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-9860-2944","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland. josep.arus@dcb.unibe.ch","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden. josep.arus@dcb.unibe.ch","institution_ids":["https://openalex.org/I4210109524","https://openalex.org/I4210128490"]},{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108013441","display_name":"Thomas Blaschke","orcid":"https://orcid.org/0000-0003-2674-799X"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]},{"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":["DE","SE"],"is_corresponding":false,"raw_author_name":"Thomas Blaschke","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19C, 53115, Bonn, Germany","Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Endenicher Allee 19C, 53115, Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]},{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009475636","display_name":"Silas Ulander","orcid":null},"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":"Silas Ulander","raw_affiliation_strings":["Medicinal Chemistry, Cardiovascular, Renal and Metabolism, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Cardiovascular, Renal and Metabolism, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040848839","display_name":"Jean\u2010Louis Reymond","orcid":"https://orcid.org/0000-0003-2724-2942"},"institutions":[{"id":"https://openalex.org/I118564535","display_name":"University of Bern","ror":"https://ror.org/02k7v4d05","country_code":"CH","type":"education","lineage":["https://openalex.org/I118564535"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Jean-Louis Reymond","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Freiestrasse 3, 3012, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729955","display_name":"Hongming Chen","orcid":"https://orcid.org/0000-0002-4470-876X"},"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":"Hongming Chen","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"last","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":["Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Pepparedsleden 1, 43183, M\u00f6lndal, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025373665"],"corresponding_institution_ids":["https://openalex.org/I118564535","https://openalex.org/I4210109524","https://openalex.org/I4210128490","https://openalex.org/I4210143795"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":25.0507,"has_fulltext":true,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99735351,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"1","first_page":"20","last_page":"20"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.996999979019165,"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":0.9367610812187195},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7494154572486877},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6414414644241333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5792416334152222},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5649884343147278},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.553678035736084},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.514912486076355},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46767696738243103},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4501979351043701},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.44763147830963135},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.42992645502090454},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41839057207107544},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.41482454538345337},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3814139664173126},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.37935593724250793},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.17232182621955872},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.12424007058143616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11056175827980042}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.9367610812187195},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7494154572486877},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6414414644241333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5792416334152222},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5649884343147278},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.553678035736084},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.514912486076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46767696738243103},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4501979351043701},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44763147830963135},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.42992645502090454},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41839057207107544},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41482454538345337},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3814139664173126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37935593724250793},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.17232182621955872},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.12424007058143616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11056175827980042},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/s13321-019-0341-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0341-z","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0341-z","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:30868314","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30868314","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 cheminformatics","raw_type":null},{"id":"pmh:oai:boris.unibe.ch:138445","is_oa":true,"landing_page_url":"https://boris.unibe.ch/138445/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401747","display_name":"BORIS (University Library Bern)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210103840","host_organization_name":"Nakuru County Council","host_organization_lineage":["https://openalex.org/I4210103840"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Ar\u00fas-Pous, Josep; Blaschke, Thomas; Ulander, Silas; Reymond, Jean-Louis; Chen, Hongming; Engkvist, Ola (2019). Exploring the GDB-13 chemical space using deep generative models. Journal of cheminformatics, 11(1), p. 20. Springer 10.1186/s13321-019-0341-z <http://dx.doi.org/10.1186/s13321-019-0341-z>","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:doaj.org/article:d00759cc1b6b43e9ad5bd2a310b1372a","is_oa":false,"landing_page_url":"https://doaj.org/article/d00759cc1b6b43e9ad5bd2a310b1372a","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 11, Iss 1, Pp 1-14 (2019)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:5416867","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/6419837","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:zenodo.org:3514957","is_oa":true,"landing_page_url":"https://zenodo.org/record/3514957","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/article"},{"id":"doi:10.7892/boris.138445","is_oa":true,"landing_page_url":"https://doi.org/10.7892/boris.138445","pdf_url":null,"source":{"id":"https://openalex.org/S7407053152","display_name":"Open Access CRIS of the University of Bern","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"JournalArticle"}],"best_oa_location":{"id":"doi:10.1186/s13321-019-0341-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-019-0341-z","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0341-z","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1002412395","display_name":"Big Data in Chemistry","funder_award_id":"676434","funder_id":"https://openalex.org/F4320338337","funder_display_name":"H2020 Marie Sk\u0142odowska-Curie Actions"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5103510783","display_name":"Big Data in Chemistry","funder_award_id":"676434","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320338337","display_name":"H2020 Marie Sk\u0142odowska-Curie Actions","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2925830236.pdf","grobid_xml":"https://content.openalex.org/works/W2925830236.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1581242383","https://openalex.org/W1899504021","https://openalex.org/W1975147762","https://openalex.org/W1980581986","https://openalex.org/W1992156271","https://openalex.org/W2011301426","https://openalex.org/W2016589492","https://openalex.org/W2027482274","https://openalex.org/W2052933929","https://openalex.org/W2064675550","https://openalex.org/W2076063813","https://openalex.org/W2076459491","https://openalex.org/W2086306822","https://openalex.org/W2096541451","https://openalex.org/W2097117768","https://openalex.org/W2114704115","https://openalex.org/W2117043211","https://openalex.org/W2128084896","https://openalex.org/W2145287260","https://openalex.org/W2146453976","https://openalex.org/W2153693853","https://openalex.org/W2157331557","https://openalex.org/W2164700406","https://openalex.org/W2166478947","https://openalex.org/W2177317049","https://openalex.org/W2206840988","https://openalex.org/W2244414922","https://openalex.org/W2257979135","https://openalex.org/W2542459869","https://openalex.org/W2550821151","https://openalex.org/W2560316200","https://openalex.org/W2578240541","https://openalex.org/W2583093513","https://openalex.org/W2603958666","https://openalex.org/W2610148085","https://openalex.org/W2746340587","https://openalex.org/W2763694886","https://openalex.org/W2786103815","https://openalex.org/W2790808809","https://openalex.org/W2883968630","https://openalex.org/W2887447356","https://openalex.org/W2895624154","https://openalex.org/W2895677720","https://openalex.org/W2899771611","https://openalex.org/W2963445908","https://openalex.org/W3209466372","https://openalex.org/W3210517829","https://openalex.org/W4252520800"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"Recent":[0],"applications":[1],"of":[2,29,48,53,73,131,140,155],"recurrent":[3],"neural":[4],"networks":[5],"(RNN)":[6],"enable":[7],"training":[8,75],"models":[9],"that":[10,39,93,117],"sample":[11],"the":[12,30,49,54,71,74,89,95,128,141,153],"chemical":[13,143],"space.":[14],"In":[15],"this":[16,118],"study":[17],"we":[18,82,104],"train":[19],"RNN":[20],"with":[21,26,43,159],"molecular":[22,133],"string":[23],"representations":[24],"(SMILES)":[25],"a":[27,40,67,84,124],"subset":[28],"enumerated":[31],"database":[32,56],"GDB-13":[33],"(975":[34],"million":[35,45],"molecules).":[36],"We":[37,64,114],"show":[38],"model":[41,86,97,135],"trained":[42,96],"1":[44],"structures":[46],"(0.1%":[47],"database)":[50],"reproduces":[51],"68.9%":[52],"entire":[55],"after":[57],"training,":[58],"when":[59],"sampling":[60],"2":[61],"billion":[62],"molecules.":[63],"also":[65,115],"developed":[66],"method":[68,119],"to":[69,98,107,126,152,167],"assess":[70],"quality":[72],"process":[76],"using":[77],"negative":[78],"log-likelihood":[79],"plots.":[80],"Furthermore,":[81],"use":[83],"mathematical":[85],"based":[87],"on":[88],"\"coupon":[90],"collector":[91],"problem\"":[92],"compares":[94],"an":[99,138],"upper":[100],"bound":[101],"and":[102,162],"thus":[103],"are":[105,164],"able":[106],"quantify":[108],"how":[109],"much":[110],"it":[111],"has":[112],"learned.":[113],"suggest":[116],"can":[120],"be":[121],"used":[122],"as":[123],"tool":[125],"benchmark":[127],"learning":[129],"capabilities":[130],"any":[132],"generative":[134],"architecture.":[136],"Additionally,":[137],"analysis":[139],"generated":[142],"space":[144],"was":[145],"performed,":[146],"which":[147],"shows":[148],"that,":[149],"mostly":[150],"due":[151],"syntax":[154],"SMILES,":[156],"complex":[157],"molecules":[158],"many":[160],"rings":[161],"heteroatoms":[163],"more":[165],"difficult":[166],"sample.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":19},{"year":2024,"cited_by_count":26},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":32},{"year":2021,"cited_by_count":56},{"year":2020,"cited_by_count":37},{"year":2019,"cited_by_count":16}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}