{"id":"https://openalex.org/W2973114758","doi":"https://doi.org/10.1145/3307339.3342186","title":"SMILES-BERT","display_name":"SMILES-BERT","publication_year":2019,"publication_date":"2019-09-04","ids":{"openalex":"https://openalex.org/W2973114758","doi":"https://doi.org/10.1145/3307339.3342186","mag":"2973114758"},"language":"en","primary_location":{"id":"doi:10.1145/3307339.3342186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3307339.3342186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5100371324","display_name":"Sheng Wang","orcid":"https://orcid.org/0000-0003-4210-1670"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sheng Wang","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008281887","display_name":"Yuzhi Guo","orcid":"https://orcid.org/0000-0002-8993-1818"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuzhi Guo","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413978","display_name":"Yuhong Wang","orcid":"https://orcid.org/0000-0002-4729-3424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuhong Wang","raw_affiliation_strings":["NIH, Rockville, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIH, Rockville, MD, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085327490","display_name":"Hongmao Sun","orcid":"https://orcid.org/0000-0003-4042-6498"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongmao Sun","raw_affiliation_strings":["NIH, Rockville, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NIH, Rockville, MD, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068865316","display_name":"Junzhou Huang","orcid":"https://orcid.org/0000-0002-9548-1227"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Junzhou Huang","raw_affiliation_strings":["University of Texas at Arlington, Arlington, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.7802,"has_fulltext":false,"cited_by_count":404,"citation_normalized_percentile":{"value":0.99964305,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"436"},"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":0.9986000061035156,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9782000184059143,"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":0.8196955323219299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6936464309692383},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.649347186088562},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6100978255271912},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5985129475593567},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.568405032157898},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5224634408950806},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5069051384925842},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4943861961364746},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46291878819465637},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4241953492164612},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4217241704463959},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4210317134857178}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8196955323219299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6936464309692383},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.649347186088562},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6100978255271912},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5985129475593567},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.568405032157898},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5224634408950806},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5069051384925842},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4943861961364746},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46291878819465637},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4241953492164612},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4217241704463959},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4210317134857178},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3307339.3342186","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3307339.3342186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4399999976158142,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320332622","display_name":"University of California, San Francisco","ror":"https://ror.org/043mz5j54"},{"id":"https://openalex.org/F4320337351","display_name":"National Cancer Institute","ror":"https://ror.org/040gcmg81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1560202902","https://openalex.org/W1738019091","https://openalex.org/W1902237438","https://openalex.org/W1975147762","https://openalex.org/W1982792699","https://openalex.org/W1988037271","https://openalex.org/W2003209620","https://openalex.org/W2027482274","https://openalex.org/W2044834685","https://openalex.org/W2062875420","https://openalex.org/W2096560421","https://openalex.org/W2133564696","https://openalex.org/W2173027866","https://openalex.org/W2214665483","https://openalex.org/W2269544137","https://openalex.org/W2290847742","https://openalex.org/W2461470610","https://openalex.org/W2526712471","https://openalex.org/W2613904329","https://openalex.org/W2618245351","https://openalex.org/W2626778328","https://openalex.org/W2745940724","https://openalex.org/W2749279690","https://openalex.org/W2788633781","https://openalex.org/W2888164077","https://openalex.org/W2946750843","https://openalex.org/W2949888546","https://openalex.org/W2952509486","https://openalex.org/W2952729433","https://openalex.org/W2963341956","https://openalex.org/W2963446712","https://openalex.org/W2963495494","https://openalex.org/W2963970792","https://openalex.org/W3100157108"],"related_works":["https://openalex.org/W4380075502","https://openalex.org/W4223943233","https://openalex.org/W4312200629","https://openalex.org/W4360585206","https://openalex.org/W4364306694","https://openalex.org/W4380086463","https://openalex.org/W4225161397","https://openalex.org/W3014300295","https://openalex.org/W2889705046","https://openalex.org/W3176808018"],"abstract_inverted_index":{"With":[0],"the":[1,33,45,54,85,119,128,144,146,150,158,169],"rapid":[2],"progress":[3],"of":[4,44,56,104,160,168],"AI":[5],"in":[6,20,35,61],"both":[7],"academia":[8],"and":[9,27,164],"industry,":[10],"Deep":[11,51,70],"Learning":[12,52,71],"has":[13,41,114],"been":[14,42,115],"widely":[15],"introduced":[16],"into":[17,135],"various":[18],"areas":[19],"drug":[21,36],"discovery":[22],"to":[23,78,83,117],"accelerate":[24],"its":[25],"pace":[26],"cut":[28],"R&D":[29],"costs.":[30],"Among":[31],"all":[32,154],"problems":[34],"discovery,":[37],"molecular":[38,62,137],"property":[39,63,138],"prediction":[40,86,139],"one":[43],"most":[46],"important":[47],"problems.":[48],"Unlike":[49],"general":[50],"applications,":[53],"scale":[55],"labeled":[57,90],"data":[58,82,113],"is":[59],"limited":[60],"prediction.":[64],"To":[65],"better":[66],"solve":[67],"this":[68,93],"problem,":[69],"methods":[72,152],"have":[73],"started":[74],"focusing":[75],"on":[76,88,153],"how":[77],"utilize":[79],"tremendous":[80],"unlabeled":[81,112],"improve":[84],"performance":[87],"small-scale":[89],"data.":[91],"In":[92,143],"paper,":[94],"we":[95],"propose":[96],"a":[97,122],"semi-supervised":[98],"model":[99,120,130],"named":[100],"SMILES-BERT,":[101],"which":[102],"consists":[103],"attention":[105],"mechanism":[106],"based":[107],"Transformer":[108],"Layer.":[109],"A":[110],"large-scale":[111],"used":[116],"pre-train":[118],"through":[121],"Masked":[123],"SMILES":[124],"Recovery":[125],"task.":[126],"Then":[127],"pre-trained":[129,170],"could":[131],"easily":[132],"be":[133],"generalized":[134],"different":[136],"tasks":[140],"via":[141],"fine-tuning.":[142],"experiments,":[145],"proposed":[147],"SMILES-BERT":[148],"outperforms":[149],"state-of-the-art":[151],"three":[155],"datasets,":[156],"showing":[157],"effectiveness":[159],"our":[161],"unsupervised":[162],"pre-training":[163],"great":[165],"generalization":[166],"capability":[167],"model.":[171]},"counts_by_year":[{"year":2026,"cited_by_count":48},{"year":2025,"cited_by_count":111},{"year":2024,"cited_by_count":85},{"year":2023,"cited_by_count":68},{"year":2022,"cited_by_count":42},{"year":2021,"cited_by_count":36},{"year":2020,"cited_by_count":14}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2019-09-19T00:00:00"}