{"id":"https://openalex.org/W2904656109","doi":"https://doi.org/10.1021/acs.jcim.8b00626","title":"De Novo Molecule Design by Translating from Reduced Graphs to SMILES","display_name":"De Novo Molecule Design by Translating from Reduced Graphs to SMILES","publication_year":2018,"publication_date":"2018-12-11","ids":{"openalex":"https://openalex.org/W2904656109","doi":"https://doi.org/10.1021/acs.jcim.8b00626","mag":"2904656109","pmid":"https://pubmed.ncbi.nlm.nih.gov/30525594"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00626","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00626","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/A5032112911","display_name":"P\u00e9ter Pog\u00e1ny","orcid":"https://orcid.org/0000-0003-3536-0746"},"institutions":[{"id":"https://openalex.org/I188950975","display_name":"GlaxoSmithKline (United Kingdom)","ror":"https://ror.org/01xsqw823","country_code":"GB","type":"company","lineage":["https://openalex.org/I188950975"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Peter Pog\u00e1ny","raw_affiliation_strings":["Computational and Modeling Sciences, GlaxoSmithKline, Gunnels Wood Road, Stevenage, Herts SG1 2NY, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computational and Modeling Sciences, GlaxoSmithKline, Gunnels Wood Road, Stevenage, Herts SG1 2NY, United Kingdom","institution_ids":["https://openalex.org/I188950975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084652936","display_name":"Navot Arad","orcid":null},"institutions":[{"id":"https://openalex.org/I188950975","display_name":"GlaxoSmithKline (United Kingdom)","ror":"https://ror.org/01xsqw823","country_code":"GB","type":"company","lineage":["https://openalex.org/I188950975"]},{"id":"https://openalex.org/I4210092990","display_name":"Tessella (United Kingdom)","ror":"https://ror.org/00fpcwp04","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210092990"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Navot Arad","raw_affiliation_strings":["GlaxoSmithKline-Tessella Analytics Partnership, Tessella Ltd, Walkern Road, Stevenage, Herts SG1 3QP, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GlaxoSmithKline-Tessella Analytics Partnership, Tessella Ltd, Walkern Road, Stevenage, Herts SG1 3QP, United Kingdom","institution_ids":["https://openalex.org/I4210092990","https://openalex.org/I188950975"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054936633","display_name":"Sam Genway","orcid":null},"institutions":[{"id":"https://openalex.org/I188950975","display_name":"GlaxoSmithKline (United Kingdom)","ror":"https://ror.org/01xsqw823","country_code":"GB","type":"company","lineage":["https://openalex.org/I188950975"]},{"id":"https://openalex.org/I4210092990","display_name":"Tessella (United Kingdom)","ror":"https://ror.org/00fpcwp04","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210092990"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sam Genway","raw_affiliation_strings":["GlaxoSmithKline-Tessella Analytics Partnership, Tessella Ltd, Walkern Road, Stevenage, Herts SG1 3QP, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GlaxoSmithKline-Tessella Analytics Partnership, Tessella Ltd, Walkern Road, Stevenage, Herts SG1 3QP, United Kingdom","institution_ids":["https://openalex.org/I4210092990","https://openalex.org/I188950975"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079075074","display_name":"Stephen D. Pickett","orcid":"https://orcid.org/0000-0002-0958-9830"},"institutions":[{"id":"https://openalex.org/I188950975","display_name":"GlaxoSmithKline (United Kingdom)","ror":"https://ror.org/01xsqw823","country_code":"GB","type":"company","lineage":["https://openalex.org/I188950975"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Stephen D. Pickett","raw_affiliation_strings":["Computational and Modeling Sciences, GlaxoSmithKline, Gunnels Wood Road, Stevenage, Herts SG1 2NY, United Kingdom"],"raw_orcid":"https://orcid.org/0000-0002-0958-9830","affiliations":[{"raw_affiliation_string":"Computational and Modeling Sciences, GlaxoSmithKline, Gunnels Wood Road, Stevenage, Herts SG1 2NY, United Kingdom","institution_ids":["https://openalex.org/I188950975"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5079075074"],"corresponding_institution_ids":["https://openalex.org/I188950975"],"apc_list":null,"apc_paid":null,"fwci":6.8395,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.97485124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"59","issue":"3","first_page":"1136","last_page":"1146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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":0.996999979019165,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9901000261306763,"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/cheminformatics","display_name":"Cheminformatics","score":0.8977377414703369},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.8241854906082153},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6670735478401184},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.649875283241272},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5400941371917725},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5080809593200684},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5019886493682861},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47973862290382385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40330636501312256},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3269619345664978},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2162126898765564},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.1925692856311798},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.1637340784072876}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8977377414703369},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.8241854906082153},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6670735478401184},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.649875283241272},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5400941371917725},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5080809593200684},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5019886493682861},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47973862290382385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40330636501312256},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3269619345664978},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2162126898765564},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.1925692856311798},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.1637340784072876},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.8b00626","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00626","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:30525594","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30525594","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":[{"id":"https://openalex.org/F4320307773","display_name":"GlaxoSmithKline","ror":"https://ror.org/01xsqw823"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W155109449","https://openalex.org/W625776585","https://openalex.org/W1509196567","https://openalex.org/W1566256432","https://openalex.org/W1582109070","https://openalex.org/W1595350250","https://openalex.org/W1757990252","https://openalex.org/W1902237438","https://openalex.org/W1936338303","https://openalex.org/W1966657120","https://openalex.org/W1975147762","https://openalex.org/W1978644181","https://openalex.org/W1984994707","https://openalex.org/W1987752375","https://openalex.org/W1988548997","https://openalex.org/W1991286793","https://openalex.org/W1993165124","https://openalex.org/W2002063821","https://openalex.org/W2022476850","https://openalex.org/W2038702914","https://openalex.org/W2039472955","https://openalex.org/W2039693046","https://openalex.org/W2046344452","https://openalex.org/W2046550159","https://openalex.org/W2056910808","https://openalex.org/W2064675550","https://openalex.org/W2084771292","https://openalex.org/W2100014056","https://openalex.org/W2121216262","https://openalex.org/W2125109129","https://openalex.org/W2143612262","https://openalex.org/W2163237834","https://openalex.org/W2177317049","https://openalex.org/W2203775767","https://openalex.org/W2221103459","https://openalex.org/W2226310234","https://openalex.org/W2228999631","https://openalex.org/W2327438214","https://openalex.org/W2525356667","https://openalex.org/W2558999090","https://openalex.org/W2565684601","https://openalex.org/W2569884841","https://openalex.org/W2578240541","https://openalex.org/W2591883888","https://openalex.org/W2610148085","https://openalex.org/W2751756351","https://openalex.org/W2765224015","https://openalex.org/W2775714759","https://openalex.org/W2779119857","https://openalex.org/W2784270883","https://openalex.org/W2784920021","https://openalex.org/W2786785157","https://openalex.org/W2790808809","https://openalex.org/W2792130717","https://openalex.org/W2792672775","https://openalex.org/W2802224083","https://openalex.org/W2805002767","https://openalex.org/W2963445908","https://openalex.org/W4248107770"],"related_works":["https://openalex.org/W4382246684","https://openalex.org/W4387845407","https://openalex.org/W2902857455","https://openalex.org/W4207004502","https://openalex.org/W4212982662","https://openalex.org/W2160244398","https://openalex.org/W2907885506","https://openalex.org/W2022444336","https://openalex.org/W2601867172","https://openalex.org/W2904656109"],"abstract_inverted_index":{"A":[0],"key":[1,77],"component":[2],"of":[3,10,43,65,79,82,88,102,113,123,193,207,240,254],"automated":[4],"molecular":[5,31,47],"design":[6,32],"is":[7,174,179,212,303],"the":[8,59,76,100,111,117,142,154,177,191,202,244,262,275],"generation":[9,104,288],"compound":[11],"ideas":[12],"for":[13,127],"subsequent":[14,229],"filtering":[15],"and":[16,51,84,182,267,302,308],"assessment.":[17],"Recently":[18],"deep":[19,129,283],"learning":[20,35,39,130,284],"approaches":[21,53],"have":[22,243],"been":[23],"explored":[24],"as":[25,46,120,160,248],"alternatives":[26],"to":[27,57,62,90,98,148,157,170,198,204,210,222,236,270,286,305],"traditional":[28],"de":[29],"novo":[30],"techniques.":[33],"Deep":[34],"algorithms":[36],"rely":[37,292],"on":[38,214,293],"from":[40,167],"large":[41,216],"pools":[42],"molecules":[44,61,266],"represented":[45,159],"graphs":[48],"(generally":[49],"SMILES),":[50],"several":[52],"can":[54,95,233,268],"be":[55,87,96,158,223,234],"used":[56,97,235],"tailor":[58],"generated":[60],"defined":[63],"regions":[64],"chemical":[66,125],"space.":[67],"Cheminformatics":[68],"has":[69],"developed":[70],"alternative":[71,282],"higher-level":[72],"representations":[73,94],"that":[74,242,261,289],"capture":[75],"properties":[78],"a":[80,121,128,161,185,194,215,228],"set":[81],"molecules,":[83],"it":[85],"would":[86],"interest":[89],"understand":[91],"whether":[92],"such":[93,115],"constrain":[99],"output":[101],"molecule":[103,131,199,287],"algorithms.":[105],"In":[106,227],"this":[107,183,231],"work":[108],"we":[109,189,259],"explore":[110],"use":[112],"one":[114,203],"representation,":[116],"Reduced":[118,134,155,171,208,246,271],"Graph,":[119],"definition":[122],"target":[124],"space":[126,297],"generator.":[132],"The":[133,165,278],"Graph":[135,156,172,209,247],"replaces":[136],"functional":[137],"groups":[138],"with":[139],"superatoms":[140,147],"representing":[141],"pharmacophoric":[143],"features.":[144],"Assigning":[145],"these":[146],"specific":[149],"nonorganic":[150],"element":[151],"types":[152],"allows":[153],"valid":[162,265],"SMILES":[163,169,173,211],"string.":[164],"mapping":[166,206],"standard":[168],"well-defined,":[175],"however,":[176],"inverse":[178],"not":[180,291],"true,":[181],"presents":[184],"particular":[186],"challenge.":[187],"Here":[188],"present":[190],"results":[192],"novel":[195],"seq-to-seq":[196],"approach":[197,263,285],"generation,":[200,298],"where":[201],"many":[205],"learned":[213],"training":[217,220,276],"set.":[218,277],"This":[219],"needs":[221],"performed":[224],"only":[225],"once.":[226],"step,":[230],"model":[232],"generate":[237],"arbitrary":[238],"numbers":[239],"compounds":[241],"same":[245],"any":[249],"input":[250],"molecule.":[251],"Through":[252],"analysis":[253],"data":[255],"sets":[256],"in":[257,274,312],"ChEMBL":[258],"show":[260],"generates":[264],"extrapolate":[269],"Graphs":[272],"unseen":[273],"method":[279],"offers":[280],"an":[281],"does":[290],"transfer":[294],"learning,":[295],"latent":[296],"or":[299],"adversarial":[300],"networks":[301],"applicable":[304],"scaffold":[306],"hopping":[307],"other":[309],"cheminformatics":[310],"applications":[311],"drug":[313],"discovery.":[314]},"counts_by_year":[{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":13},{"year":2021,"cited_by_count":15},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}