{"id":"https://openalex.org/W3209056694","doi":"https://doi.org/10.1021/acs.jcim.1c00600","title":"MolGPT: Molecular Generation Using a Transformer-Decoder Model","display_name":"MolGPT: Molecular Generation Using a Transformer-Decoder Model","publication_year":2021,"publication_date":"2021-10-25","ids":{"openalex":"https://openalex.org/W3209056694","doi":"https://doi.org/10.1021/acs.jcim.1c00600","mag":"3209056694","pmid":"https://pubmed.ncbi.nlm.nih.gov/34694798"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c00600","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00600","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":"review","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/A5083698352","display_name":"Viraj Bagal","orcid":"https://orcid.org/0000-0002-0815-6865"},"institutions":[{"id":"https://openalex.org/I181996519","display_name":"Indian Institute of Science Education and Research Pune","ror":"https://ror.org/028qa3n13","country_code":"IN","type":"education","lineage":["https://openalex.org/I181996519"]},{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Viraj Bagal","raw_affiliation_strings":["Indian Institute of Science Education and Research, Pune 411 008, India","International Institute of Information Technology, Hyderabad 500 032, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Indian Institute of Science Education and Research, Pune 411 008, India","institution_ids":["https://openalex.org/I181996519"]},{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad 500 032, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016226933","display_name":"Rishal Aggarwal","orcid":"https://orcid.org/0000-0001-7062-2583"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishal Aggarwal","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad 500 032, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad 500 032, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060336051","display_name":"P. K. Vinod","orcid":"https://orcid.org/0000-0003-2968-498X"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"P. K. Vinod","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad 500 032, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad 500 032, India","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034329125","display_name":"U. Deva Priyakumar","orcid":"https://orcid.org/0000-0001-7114-3955"},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"U. Deva Priyakumar","raw_affiliation_strings":["International Institute of Information Technology, Hyderabad 500 032, India"],"raw_orcid":"https://orcid.org/0000-0001-7114-3955","affiliations":[{"raw_affiliation_string":"International Institute of Information Technology, Hyderabad 500 032, India","institution_ids":["https://openalex.org/I64189192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034329125"],"corresponding_institution_ids":["https://openalex.org/I64189192"],"apc_list":null,"apc_paid":null,"fwci":37.2041,"has_fulltext":false,"cited_by_count":516,"citation_normalized_percentile":{"value":0.99892481,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"62","issue":"9","first_page":"2064","last_page":"2076"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9975000023841858,"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":0.9527000188827515,"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/computer-science","display_name":"Computer science","score":0.7510671615600586},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.68535315990448},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6587110757827759},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.551315188407898},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5394635200500488},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5326437950134277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5007410049438477},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.4380120038986206},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11155787110328674}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7510671615600586},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.68535315990448},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6587110757827759},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.551315188407898},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5394635200500488},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5326437950134277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5007410049438477},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.4380120038986206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11155787110328674},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.1c00600","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c00600","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:34694798","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34694798","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":[{"score":0.800000011920929,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1981276685","https://openalex.org/W2023818227","https://openalex.org/W2034549041","https://openalex.org/W2060531713","https://openalex.org/W2094750196","https://openalex.org/W2160592148","https://openalex.org/W2176516200","https://openalex.org/W2177317049","https://openalex.org/W2529996553","https://openalex.org/W2558999090","https://openalex.org/W2559655401","https://openalex.org/W2578240541","https://openalex.org/W2610148085","https://openalex.org/W2612690371","https://openalex.org/W2736137960","https://openalex.org/W2765224015","https://openalex.org/W2773987374","https://openalex.org/W2790808809","https://openalex.org/W2793945656","https://openalex.org/W2805002767","https://openalex.org/W2883583109","https://openalex.org/W2886791556","https://openalex.org/W2887447356","https://openalex.org/W2891868449","https://openalex.org/W2900694120","https://openalex.org/W2903564615","https://openalex.org/W2913351693","https://openalex.org/W2947423323","https://openalex.org/W2953128081","https://openalex.org/W2956961449","https://openalex.org/W2962793481","https://openalex.org/W2963609389","https://openalex.org/W2972741532","https://openalex.org/W2989615256","https://openalex.org/W2991736596","https://openalex.org/W2995422623","https://openalex.org/W2998374989","https://openalex.org/W3025593963","https://openalex.org/W3030948478","https://openalex.org/W3097865746","https://openalex.org/W3098269892","https://openalex.org/W3100751385","https://openalex.org/W3103092523","https://openalex.org/W3116865743","https://openalex.org/W3185720802","https://openalex.org/W4234552385","https://openalex.org/W4289436753"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W2280377497","https://openalex.org/W3174044702","https://openalex.org/W4238433571","https://openalex.org/W2967848559","https://openalex.org/W4283803360","https://openalex.org/W4317695495","https://openalex.org/W4387506531"],"abstract_inverted_index":{"generation":[0,81,107,159],"of":[1,18,26,31,33,82,110,131,164,177,181],"molecules,":[2],"termed":[3],"as":[4,23,42,150,152],"inverse":[5],"molecular":[6,45,106,154],"design,":[7],"has":[8],"been":[9,57],"gaining":[10],"enormous":[11],"traction":[12],"in":[13,20,37,47,62,85,108],"drug":[14],"design.":[15],"The":[16],"representation":[17],"molecules":[19,84,146],"SMILES":[21,162],"notation":[22],"a":[24,68],"string":[25],"characters":[27],"enables":[28],"the":[29,34,71,80,121,132,139,158,175,178,182],"usage":[30],"state":[32],"art":[35],"models":[36,54],"natural":[38],"language":[39],"processing,":[40],"such":[41],"Transformers,":[43],"for":[44,79,105],"design":[46],"general.":[48],"Inspired":[49],"by":[50,156],"generative":[51,179],"pre-training":[52],"(GPT)":[53],"that":[55,90,120,138],"have":[56],"shown":[58],"to":[59,127,144],"be":[60,124,142],"successful":[61],"generating":[63,111],"meaningful":[64],"text,":[65],"we":[66,118,173],"train":[67],"transformer-decoder":[69],"on":[70,95,160],"next":[72],"token":[73],"prediction":[74],"task":[75],"using":[76],"masked":[77],"self-attention":[78],"druglike":[83],"this":[86],"study.":[87],"We":[88,135],"show":[89,137],"our":[91],"model,":[92],"MolGPT,":[93],"performs":[94],"par":[96],"with":[97,147],"other":[98],"previously":[99],"proposed":[100],"modern":[101],"machine":[102],"learning":[103],"frameworks":[104],"terms":[109],"valid,":[112],"unique,":[113],"and":[114,167],"novel":[115],"molecules.":[116,134],"Furthermore,":[117],"demonstrate":[119],"model":[122,140],"can":[123,141],"trained":[125],"conditionally":[126],"control":[128],"multiple":[129],"properties":[130,155],"generated":[133],"also":[136],"used":[143],"generate":[145],"desired":[148,153,165],"scaffolds":[149,166],"well":[151],"conditioning":[157],"scaffold":[161],"strings":[163],"property":[168],"values.":[169],"Using":[170],"saliency":[171],"maps,":[172],"highlight":[174],"interpretability":[176],"process":[180],"model.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":88},{"year":2025,"cited_by_count":175},{"year":2024,"cited_by_count":144},{"year":2023,"cited_by_count":84},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}