{"id":"https://openalex.org/W3138781613","doi":"https://doi.org/10.1021/acs.jcim.0c01127","title":"SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning","display_name":"SMILES Pair Encoding: A Data-Driven Substructure Tokenization Algorithm for Deep Learning","publication_year":2021,"publication_date":"2021-03-15","ids":{"openalex":"https://openalex.org/W3138781613","doi":"https://doi.org/10.1021/acs.jcim.0c01127","mag":"3138781613","pmid":"https://pubmed.ncbi.nlm.nih.gov/33715361"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c01127","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01127","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":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/SMILES_Pair_Encoding_A_Data-Driven_Substructure_Tokenization_Algorithm_for_Deep_Learning/14214827","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048357912","display_name":"Xinhao Li","orcid":"https://orcid.org/0000-0002-1821-2680"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinhao Li","raw_affiliation_strings":["Department of Chemistry, Bioinformatics Research Center, North Carolina State University, Raleigh, North Carolina 27695, United States"],"raw_orcid":"https://orcid.org/0000-0002-1821-2680","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Bioinformatics Research Center, North Carolina State University, Raleigh, North Carolina 27695, United States","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072029339","display_name":"Denis Fourches","orcid":"https://orcid.org/0000-0001-5642-8303"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Denis Fourches","raw_affiliation_strings":["Department of Chemistry, Bioinformatics Research Center, North Carolina State University, Raleigh, North Carolina 27695, United States"],"raw_orcid":"https://orcid.org/0000-0001-5642-8303","affiliations":[{"raw_affiliation_string":"Department of Chemistry, Bioinformatics Research Center, North Carolina State University, Raleigh, North Carolina 27695, United States","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072029339"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":11.6116,"has_fulltext":false,"cited_by_count":129,"citation_normalized_percentile":{"value":0.98778589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"61","issue":"4","first_page":"1560","last_page":"1569"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9677000045776367,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9638000130653381,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9577999711036682,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/substructure","display_name":"Substructure","score":0.8403992652893066},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7478286027908325},{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.7154037952423096},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6604987978935242},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5896319150924683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4902935326099396},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3713452219963074},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07316970825195312}],"concepts":[{"id":"https://openalex.org/C99679407","wikidata":"https://www.wikidata.org/wiki/Q56761637","display_name":"Substructure","level":2,"score":0.8403992652893066},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7478286027908325},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.7154037952423096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6604987978935242},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5896319150924683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4902935326099396},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3713452219963074},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07316970825195312},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.0c01127","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c01127","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:33715361","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33715361","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},{"id":"pmh:oai:figshare.com:article/14214827","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/SMILES_Pair_Encoding_A_Data-Driven_Substructure_Tokenization_Algorithm_for_Deep_Learning/14214827","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/14214827","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/SMILES_Pair_Encoding_A_Data-Driven_Substructure_Tokenization_Algorithm_for_Deep_Learning/14214827","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6941981723","display_name":null,"funder_award_id":"W911NF1810315","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"},{"id":"https://openalex.org/G7738662574","display_name":null,"funder_award_id":"W911NF1810315","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1598796236","https://openalex.org/W1832693441","https://openalex.org/W1975147762","https://openalex.org/W2008381136","https://openalex.org/W2022476850","https://openalex.org/W2038702914","https://openalex.org/W2060531713","https://openalex.org/W2096541451","https://openalex.org/W2291927426","https://openalex.org/W2578240541","https://openalex.org/W2622206241","https://openalex.org/W2626778328","https://openalex.org/W2743945814","https://openalex.org/W2771577156","https://openalex.org/W2790808809","https://openalex.org/W2795247881","https://openalex.org/W2798405286","https://openalex.org/W2890097032","https://openalex.org/W2895677720","https://openalex.org/W2900694120","https://openalex.org/W2903425689","https://openalex.org/W2914757825","https://openalex.org/W2920582597","https://openalex.org/W2925830236","https://openalex.org/W2945551948","https://openalex.org/W2953128081","https://openalex.org/W2962784628","https://openalex.org/W2963026768","https://openalex.org/W2964677890","https://openalex.org/W2989615256","https://openalex.org/W2997058986","https://openalex.org/W3005353977","https://openalex.org/W3006436762","https://openalex.org/W3007309629","https://openalex.org/W3007488165","https://openalex.org/W3009321976","https://openalex.org/W3023042104","https://openalex.org/W3030978062","https://openalex.org/W3032781902","https://openalex.org/W3045928028","https://openalex.org/W3092539261","https://openalex.org/W3098350627","https://openalex.org/W3108004614","https://openalex.org/W3174976929","https://openalex.org/W4229590462","https://openalex.org/W4245372219","https://openalex.org/W4300870773"],"related_works":["https://openalex.org/W3153444835","https://openalex.org/W2153916713","https://openalex.org/W2023846184","https://openalex.org/W2703419385","https://openalex.org/W2329056228","https://openalex.org/W2284584236","https://openalex.org/W2950955148","https://openalex.org/W1979083399","https://openalex.org/W2344320748","https://openalex.org/W2374530195"],"abstract_inverted_index":{"Simplified":[0],"molecular":[1,94],"input":[2],"line":[3],"entry":[4],"system":[5],"(SMILES)-based":[6],"deep":[7,63,163],"learning":[8,64,164],"models":[9,108,134],"are":[10],"slowly":[11],"emerging":[12],"as":[13,81],"an":[14],"important":[15],"research":[16],"topic":[17],"in":[18,114],"cheminformatics.":[19],"In":[20,103],"this":[21,175],"study,":[22],"we":[23],"introduce":[24],"SMILES":[25,40,52,79],"pair":[26],"encoding":[27],"(SPE),":[28],"a":[29,36,43,157],"data-driven":[30],"tokenization":[31,72,112,159],"algorithm.":[32],"SPE":[33,66,87,142,154],"first":[34],"learns":[35],"vocabulary":[37,57],"of":[38,62,117,130],"high-frequency":[39],"substrings":[41,80],"from":[42],"large":[44],"chemical":[45],"dataset":[46],"(e.g.,":[47],"ChEMBL)":[48],"and":[49,76,96,120,150,177],"then":[50],"tokenizes":[51],"based":[53],"on":[54,92],"the":[55,59,68,105,110,115,124],"learned":[56],"for":[58,161],"actual":[60],"training":[61,125],"models.":[65,165],"augments":[67],"widely":[69],"used":[70],"atom-level":[71,111,149],"by":[73],"adding":[74],"human-readable":[75],"chemically":[77],"explainable":[78],"tokens.":[82],"Case":[83],"studies":[84],"show":[85],"that":[86],"can":[88],"achieve":[89],"superior":[90],"performances":[91],"both":[93],"generation":[95],"quantitative":[97],"structure\u2013activity":[98],"relationship":[99],"(QSAR)":[100],"prediction":[101,133],"tasks.":[102],"particular,":[104],"SPE-based":[106,131],"generative":[107],"outperformed":[109],"model":[113],"aspects":[116],"novelty,":[118],"diversity,":[119],"ability":[121],"to":[122,173],"resemble":[123],"set":[126],"distribution.":[127],"The":[128],"performance":[129],"QSAR":[132],"were":[135],"evaluated":[136],"using":[137],"24":[138],"benchmark":[139],"datasets":[140],"where":[141],"consistently":[143],"either":[144],"did":[145],"match":[146],"or":[147],"outperform":[148],"k-mer":[151],"tokenization.":[152],"Therefore,":[153],"could":[155],"be":[156],"promising":[158],"method":[160],"SMILES-based":[162],"An":[166],"open-source":[167],"Python":[168],"package":[169],"SmilesPE":[170],"was":[171],"developed":[172],"implement":[174],"algorithm":[176],"is":[178],"now":[179],"freely":[180],"available":[181],"at":[182],"https://github.com/XinhaoLi74/SmilesPE.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":38},{"year":2024,"cited_by_count":32},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":23},{"year":2021,"cited_by_count":7}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}