{"id":"https://openalex.org/W4401035236","doi":"https://doi.org/10.1021/acs.jcim.4c00512","title":"BartSmiles: Generative Masked Language Models for Molecular Representations","display_name":"BartSmiles: Generative Masked Language Models for Molecular Representations","publication_year":2024,"publication_date":"2024-07-26","ids":{"openalex":"https://openalex.org/W4401035236","doi":"https://doi.org/10.1021/acs.jcim.4c00512","pmid":"https://pubmed.ncbi.nlm.nih.gov/39054761"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.4c00512","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00512","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/A5048395606","display_name":"Gayane Chilingaryan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gayane Chilingaryan","raw_affiliation_strings":["YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074874570","display_name":"Hovhannes Tamoyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hovhannes Tamoyan","raw_affiliation_strings":["YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053167026","display_name":"Ani Tevosyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094371","display_name":"Scientific Center of Zoology and Hydroecology","ror":"https://ror.org/00t5ymp38","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210094371","https://openalex.org/I99064381"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Ani Tevosyan","raw_affiliation_strings":["Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia","YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia","institution_ids":["https://openalex.org/I4210094371"]},{"raw_affiliation_string":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050797011","display_name":"Nelly Babayan","orcid":"https://orcid.org/0000-0001-9205-7693"},"institutions":[{"id":"https://openalex.org/I4210094371","display_name":"Scientific Center of Zoology and Hydroecology","ror":"https://ror.org/00t5ymp38","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210094371","https://openalex.org/I99064381"]},{"id":"https://openalex.org/I4210133976","display_name":"Institute of Molecular Biology","ror":"https://ror.org/03t8mqd25","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210133976","https://openalex.org/I99064381"]},{"id":"https://openalex.org/I99064381","display_name":"National Academy of Sciences of Armenia","ror":"https://ror.org/04mczx267","country_code":"AM","type":"government","lineage":["https://openalex.org/I99064381"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Nelly Babayan","raw_affiliation_strings":["Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia","Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia","institution_ids":["https://openalex.org/I99064381","https://openalex.org/I4210133976"]},{"raw_affiliation_string":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia","institution_ids":["https://openalex.org/I4210094371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111041350","display_name":"Karen Hambardzumyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karen Hambardzumyan","raw_affiliation_strings":["YerevaNN, Charents str. 20, 0025 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011162032","display_name":"Zaven Navoyan","orcid":null},"institutions":[{"id":"https://openalex.org/I4210094371","display_name":"Scientific Center of Zoology and Hydroecology","ror":"https://ror.org/00t5ymp38","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210094371","https://openalex.org/I99064381"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Zaven Navoyan","raw_affiliation_strings":["Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia","institution_ids":["https://openalex.org/I4210094371"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062471396","display_name":"Armen Aghajanyan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Armen Aghajanyan","raw_affiliation_strings":["Meta AI Research, 1 Hacker Wy, Menlo Park, California 94025, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta AI Research, 1 Hacker Wy, Menlo Park, California 94025, United States","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005769994","display_name":"Hrant Khachatrian","orcid":"https://orcid.org/0000-0002-1544-5649"},"institutions":[{"id":"https://openalex.org/I196551433","display_name":"Yerevan State University","ror":"https://ror.org/00s8vne50","country_code":"AM","type":"education","lineage":["https://openalex.org/I196551433"]}],"countries":["AM"],"is_corresponding":false,"raw_author_name":"Hrant Khachatrian","raw_affiliation_strings":["YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","Yerevan State University, Alex Manoogian str. 1, 0025 Yerevan, Armenia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"YerevaNN, Charents str. 20, 0025 Yerevan, Armenia","institution_ids":[]},{"raw_affiliation_string":"Yerevan State University, Alex Manoogian str. 1, 0025 Yerevan, Armenia","institution_ids":["https://openalex.org/I196551433"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013131159","display_name":"Lusine Khondkaryan","orcid":"https://orcid.org/0000-0003-0578-0758"},"institutions":[{"id":"https://openalex.org/I4210094371","display_name":"Scientific Center of Zoology and Hydroecology","ror":"https://ror.org/00t5ymp38","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210094371","https://openalex.org/I99064381"]},{"id":"https://openalex.org/I4210133976","display_name":"Institute of Molecular Biology","ror":"https://ror.org/03t8mqd25","country_code":"AM","type":"facility","lineage":["https://openalex.org/I4210133976","https://openalex.org/I99064381"]},{"id":"https://openalex.org/I99064381","display_name":"National Academy of Sciences of Armenia","ror":"https://ror.org/04mczx267","country_code":"AM","type":"government","lineage":["https://openalex.org/I99064381"]}],"countries":["AM"],"is_corresponding":true,"raw_author_name":"Lusine Khondkaryan","raw_affiliation_strings":["Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia","Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia"],"raw_orcid":"https://orcid.org/0000-0003-0578-0758","affiliations":[{"raw_affiliation_string":"Institute of Molecular Biology, NAS RA, Hasratyan 7, 0014 Yerevan, Armenia","institution_ids":["https://openalex.org/I99064381","https://openalex.org/I4210133976"]},{"raw_affiliation_string":"Toxometris.ai, Sarmen str. 7, 0019 Yerevan, Armenia","institution_ids":["https://openalex.org/I4210094371"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5013131159"],"corresponding_institution_ids":["https://openalex.org/I4210094371","https://openalex.org/I4210133976","https://openalex.org/I99064381"],"apc_list":null,"apc_paid":null,"fwci":2.0844,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.90635969,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"64","issue":"15","first_page":"5832","last_page":"5843"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9998999834060669,"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/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/T10044","display_name":"Protein Structure and Dynamics","score":0.974399983882904,"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/interpretability","display_name":"Interpretability","score":0.9209093451499939},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7631057500839233},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6448141932487488},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6418589353561401},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6317864656448364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6065945029258728},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5903253555297852},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5881085395812988},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5413683652877808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5052564740180969},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5023133754730225},{"id":"https://openalex.org/keywords/series","display_name":"Series (stratigraphy)","score":0.4291069507598877},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.06553345918655396}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9209093451499939},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7631057500839233},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6448141932487488},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6418589353561401},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6317864656448364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6065945029258728},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5903253555297852},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5881085395812988},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5413683652877808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5052564740180969},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5023133754730225},{"id":"https://openalex.org/C143724316","wikidata":"https://www.wikidata.org/wiki/Q312468","display_name":"Series (stratigraphy)","level":2,"score":0.4291069507598877},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.06553345918655396},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[{"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":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.4c00512","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.4c00512","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:39054761","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39054761","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":[{"id":"https://openalex.org/G3066684086","display_name":null,"funder_award_id":"23LCG-1F002","funder_id":"https://openalex.org/F4320324101","funder_display_name":"State Committee of Science"}],"funders":[{"id":"https://openalex.org/F4320324101","display_name":"State Committee of Science","ror":"https://ror.org/01ptpr676"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1982597534","https://openalex.org/W1988037271","https://openalex.org/W2044834685","https://openalex.org/W2060531713","https://openalex.org/W2066532920","https://openalex.org/W2290847742","https://openalex.org/W2406943157","https://openalex.org/W2527197703","https://openalex.org/W2594183968","https://openalex.org/W2769423117","https://openalex.org/W2773131117","https://openalex.org/W2777416523","https://openalex.org/W2887447356","https://openalex.org/W2895067160","https://openalex.org/W2903262661","https://openalex.org/W2907657781","https://openalex.org/W2923014074","https://openalex.org/W2933138175","https://openalex.org/W2947423323","https://openalex.org/W2963250244","https://openalex.org/W2963396480","https://openalex.org/W2966357564","https://openalex.org/W2968734407","https://openalex.org/W2973114758","https://openalex.org/W3088265803","https://openalex.org/W3094640617","https://openalex.org/W3094771832","https://openalex.org/W3098530784","https://openalex.org/W3100157108","https://openalex.org/W3103092523","https://openalex.org/W3116202926","https://openalex.org/W3198429080","https://openalex.org/W4214868967","https://openalex.org/W4221151574","https://openalex.org/W4226159083","https://openalex.org/W4242320552","https://openalex.org/W4281553035","https://openalex.org/W4313156423","https://openalex.org/W4313485929"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571","https://openalex.org/W3174044702","https://openalex.org/W2967848559","https://openalex.org/W4299831724"],"abstract_inverted_index":{"We":[0,67],"discover":[1],"a":[2,16,29,61,97,103],"robust":[3],"self-supervised":[4,41,52],"strategy":[5],"tailored":[6],"toward":[7],"molecular":[8,42,75],"representations":[9,53,81],"for":[10],"generative":[11],"masked":[12],"language":[13],"models":[14],"through":[15],"series":[17],"of":[18,35,88,111,141],"tailored,":[19],"in-depth":[20],"ablations.":[21],"Using":[22],"this":[23],"pretraining":[24],"strategy,":[25],"we":[26,100,120],"train":[27],"BARTSmiles,":[28,99,130],"BART-like":[30],"model":[31,104,115,147],"with":[32],"an":[33],"order":[34],"magnitude":[36],"more":[37],"compute":[38],"than":[39],"previous":[40],"representations.":[43],"In-depth":[44],"evaluations":[45],"show":[46,69,121],"that":[47,70,82,122,134],"BARTSmiles":[48],"consistently":[49],"outperforms":[50],"other":[51],"across":[54],"classification,":[55],"regression,":[56],"and":[57,145],"generation":[58],"tasks,":[59],"setting":[60],"new":[62],"state-of-the-art":[63],"on":[64,116],"eight":[65],"tasks.":[66],"then":[68],"when":[71,127],"applied":[72,128],"to":[73,129,137],"the":[74,77,112],"domain,":[76],"BART":[78],"objective":[79],"learns":[80],"implicitly":[83],"encode":[84],"our":[85],"downstream":[86],"tasks":[87],"interest.":[89],"For":[90],"example,":[91],"by":[92],"selecting":[93],"seven":[94],"neurons":[95],"from":[96],"frozen":[98],"can":[101],"obtain":[102],"having":[105],"performance":[106],"within":[107],"two":[108],"percentage":[109],"points":[110],"full":[113],"fine-tuned":[114],"task":[117],"Clintox.":[118],"Lastly,":[119],"standard":[123],"attribution":[124],"interpretability":[125],"methods,":[126],"highlight":[131],"certain":[132],"substructures":[133],"chemists":[135],"use":[136],"explain":[138],"specific":[139],"properties":[140],"molecules.":[142],"The":[143],"code":[144],"pretrained":[146],"are":[148],"publicly":[149],"available.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-27T08:28:00.272161","created_date":"2025-10-10T00:00:00"}