{"id":"https://openalex.org/W2973002062","doi":"https://doi.org/10.1007/978-3-030-30493-5_68","title":"Improving Deep Generative Models with Randomized SMILES","display_name":"Improving Deep Generative Models with Randomized SMILES","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2973002062","doi":"https://doi.org/10.1007/978-3-030-30493-5_68","mag":"2973002062"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-30493-5_68","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-30493-5_68","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-30493-5_68.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-30493-5_68.pdf","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/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":["CH","SE"],"is_corresponding":true,"raw_author_name":"Josep Ar\u00fas-Pous","raw_affiliation_strings":["Department of Chemistry and Biochemistry, University of Bern, Bern, Switzerland","Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-9860-2944","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, Bern, Switzerland","institution_ids":["https://openalex.org/I118564535"]},{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037160846","display_name":"Simon Johansson","orcid":"https://orcid.org/0000-0001-9139-6378"},"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":"Simon Johansson","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0001-9139-6378","affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050895359","display_name":"Oleksii Prykhodko","orcid":"https://orcid.org/0000-0002-9694-1192"},"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":"Oleksii Prykhodko","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-9694-1192","affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046421751","display_name":"Esben Jannik Bjerrum","orcid":"https://orcid.org/0000-0003-1614-7376"},"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":"Esben Jannik Bjerrum","raw_affiliation_strings":["Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-1614-7376","affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]},{"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/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":"Christian Tyrchan","raw_affiliation_strings":["Medicinal Chemistry, Cardiovascular, Renal and Metabolism, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-6470-984X","affiliations":[{"raw_affiliation_string":"Medicinal Chemistry, Cardiovascular, Renal and Metabolism, IMED Biotech Unit, AstraZeneca, Gothenburg, 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, Bern, Switzerland"],"raw_orcid":"https://orcid.org/0000-0003-2724-2942","affiliations":[{"raw_affiliation_string":"Department of Chemistry and Biochemistry, University of Bern, 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, Sweden"],"raw_orcid":"https://orcid.org/0000-0002-4470-876X","affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, 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, Sweden"],"raw_orcid":"https://orcid.org/0000-0003-4970-6461","affiliations":[{"raw_affiliation_string":"Hit Discovery, Discovery Sciences, IMED Biotech Unit, AstraZeneca, Gothenburg, Sweden","institution_ids":["https://openalex.org/I4210143795"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5025373665"],"corresponding_institution_ids":["https://openalex.org/I118564535","https://openalex.org/I4210143795"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":{"value":5000,"currency":"EUR","value_usd":5392},"fwci":0.626,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62738797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"747","last_page":"751"},"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":0.9994999766349792,"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/T12327","display_name":"Various Chemistry Research Topics","score":0.9632999897003174,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.837165117263794},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7754836082458496},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6880084276199341},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6388694047927856},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5486184358596802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.544868528842926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43402785062789917},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.41978174448013306},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4191684126853943},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34109002351760864},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.07723116874694824}],"concepts":[{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.837165117263794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7754836082458496},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6880084276199341},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6388694047927856},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5486184358596802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.544868528842926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43402785062789917},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.41978174448013306},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4191684126853943},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34109002351760864},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.07723116874694824},{"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/978-3-030-30493-5_68","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-30493-5_68","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-30493-5_68.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:zenodo.org:3515064","is_oa":true,"landing_page_url":"https://zenodo.org/record/3515064","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/conferencePaper"}],"best_oa_location":{"id":"doi:10.1007/978-3-030-30493-5_68","is_oa":true,"landing_page_url":"https://doi.org/10.1007/978-3-030-30493-5_68","pdf_url":"https://link.springer.com/content/pdf/10.1007%2F978-3-030-30493-5_68.pdf","source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[{"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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2973002062.pdf","grobid_xml":"https://content.openalex.org/works/W2973002062.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2153693853","https://openalex.org/W2578240541","https://openalex.org/W2604296437","https://openalex.org/W2610148085","https://openalex.org/W2925830236","https://openalex.org/W2939314313","https://openalex.org/W4231256756"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2902857455","https://openalex.org/W4321353415","https://openalex.org/W2745001401","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W4246352526","https://openalex.org/W2765324078","https://openalex.org/W2059632225"],"abstract_inverted_index":{"Abstract":[0],"A":[1],"Recurrent":[2],"Neural":[3],"Network":[4],"(RNN)":[5],"trained":[6,36,99,149],"with":[7,100,150],"a":[8,38,57,61,91],"set":[9,76,153],"of":[10,19,28,45],"molecules":[11,66,101,141],"represented":[12],"as":[13,56,121,123,142],"SMILES":[14,55,162],"strings":[15],"can":[16,63],"generate":[17,64,130],"millions":[18],"different":[20],"valid":[21],"and":[22,67,155],"meaningful":[23],"chemical":[24,112,135],"structures.":[25],"In":[26],"most":[27],"the":[29,32,74,103,116,133],"reported":[30],"architectures":[31],"models":[33,98,128,146],"have":[34],"been":[35,86],"using":[37,53,88,137,160],"canonical":[39],"(unique":[40],"for":[41],"each":[42],"molecule)":[43],"representation":[44],"SMILES.":[46],"Instead,":[47],"this":[48],"research":[49,89],"shows":[50,96],"that":[51,97,129],"when":[52,115,159],"randomized":[54,161],"data":[58],"amplification":[59],"technique,":[60],"model":[62],"more":[65],"those":[68],"are":[69],"going":[70],"to":[71,164],"accurately":[72],"represent":[73],"training":[75,143,152],"properties.":[77],"To":[78],"show":[79,156],"that,":[80],"an":[81],"extensive":[82],"benchmark":[83],"study":[84],"has":[85],"conducted":[87],"from":[90,102],"recently":[92],"published":[93],"article":[94],"which":[95],"GDB-13":[104,134],"database":[105],"(975":[106],"million":[107,140],"molecules)":[108],"achieve":[109],"better":[110],"overall":[111],"space":[113,136],"coverage":[114],"posterior":[117],"probability":[118],"distribution":[119],"is":[120],"uniform":[122],"possible.":[124],"Specifically,":[125],"we":[126],"created":[127],"nearly":[131],"all":[132],"only":[138],"1":[139],"set.":[144],"Lastly,":[145],"were":[147],"also":[148],"smaller":[151],"sizes":[154],"substantial":[157],"improvement":[158],"compared":[163],"canonical.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-04T08:18:43.703281","created_date":"2025-10-10T00:00:00"}