{"id":"https://openalex.org/W3214740101","doi":"https://doi.org/10.1021/acs.jcim.1c01289","title":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","display_name":"Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention","publication_year":2021,"publication_date":"2021-12-02","ids":{"openalex":"https://openalex.org/W3214740101","doi":"https://doi.org/10.1021/acs.jcim.1c01289","mag":"3214740101","pmid":"https://pubmed.ncbi.nlm.nih.gov/34855384"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c01289","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01289","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":["arxiv","crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.00213","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029567228","display_name":"Hyunseung Kim","orcid":"https://orcid.org/0000-0002-8840-4784"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyunseung Kim","raw_affiliation_strings":["School of Chemical and Biological Engineering, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-8840-4784","affiliations":[{"raw_affiliation_string":"School of Chemical and Biological Engineering, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018459520","display_name":"Jonggeol Na","orcid":"https://orcid.org/0000-0002-1106-9500"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Jonggeol Na","raw_affiliation_strings":["Department of Chemical Engineering and Materials Science, Graduate Program in System Health Science and Engineering, Ewha Womans University, Seoul 03760, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-1106-9500","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering and Materials Science, Graduate Program in System Health Science and Engineering, Ewha Womans University, Seoul 03760, Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083571587","display_name":"Won Bo Lee","orcid":"https://orcid.org/0000-0001-7801-083X"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Won Bo Lee","raw_affiliation_strings":["School of Chemical and Biological Engineering, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-7801-083X","affiliations":[{"raw_affiliation_string":"School of Chemical and Biological Engineering, Seoul National University, Gwanak-ro 1, Gwanak-gu, Seoul 08826, Republic of Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5018459520","https://openalex.org/A5083571587"],"corresponding_institution_ids":["https://openalex.org/I138925566","https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":8.4789,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.98085358,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"61","issue":"12","first_page":"5804","last_page":"5814"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9969000220298767,"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":0.9969000220298767,"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":0.9850999712944031,"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.930400013923645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7026835083961487},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6656504273414612},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5563002228736877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47254228591918945},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.38616037368774414},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35242724418640137},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15627822279930115}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7026835083961487},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6656504273414612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5563002228736877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47254228591918945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.38616037368774414},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35242724418640137},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15627822279930115},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"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":"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":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007802","descriptor_name":"Language","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","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":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.1c01289","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01289","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:34855384","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34855384","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:arXiv.org:2103.00213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.00213","pdf_url":"https://arxiv.org/pdf/2103.00213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.00213","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.00213","pdf_url":"https://arxiv.org/pdf/2103.00213","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G2247933849","display_name":null,"funder_award_id":"NRF-2018M3D1A1058633","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3830273528","display_name":null,"funder_award_id":"NRF-2019R1A2C1085081","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5036554334","display_name":null,"funder_award_id":"NRF-2021R1C1C1012031","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1508604947","https://openalex.org/W1757990252","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1999638776","https://openalex.org/W2022476850","https://openalex.org/W2034549041","https://openalex.org/W2038702914","https://openalex.org/W2060531713","https://openalex.org/W2110791536","https://openalex.org/W2133564696","https://openalex.org/W2188365844","https://openalex.org/W2529996553","https://openalex.org/W2567534979","https://openalex.org/W2578240541","https://openalex.org/W2610148085","https://openalex.org/W2747592475","https://openalex.org/W2763220183","https://openalex.org/W2769836604","https://openalex.org/W2786308452","https://openalex.org/W2786722833","https://openalex.org/W2887447356","https://openalex.org/W2896457183","https://openalex.org/W2901476322","https://openalex.org/W2910135751","https://openalex.org/W2910636130","https://openalex.org/W2950784811","https://openalex.org/W2951670304","https://openalex.org/W2956961449","https://openalex.org/W2963223306","https://openalex.org/W2963445908","https://openalex.org/W2977044154","https://openalex.org/W2985931096","https://openalex.org/W2989615256","https://openalex.org/W2991736596","https://openalex.org/W2995724889","https://openalex.org/W3025593963","https://openalex.org/W3034772996","https://openalex.org/W3043096321","https://openalex.org/W3043969542","https://openalex.org/W3098269892","https://openalex.org/W3116865743","https://openalex.org/W3160789623","https://openalex.org/W3193917007","https://openalex.org/W4232186742","https://openalex.org/W4233151585","https://openalex.org/W4240795200","https://openalex.org/W4241677786","https://openalex.org/W4242836807","https://openalex.org/W4253105429","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4385245566","https://openalex.org/W4391602018"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Discovering":[0],"new":[1],"materials":[2],"better":[3],"suited":[4],"to":[5,73,134],"specific":[6],"purposes":[7],"is":[8,41,86],"an":[9],"important":[10],"issue":[11],"in":[12,50],"improving":[13,135],"the":[14,60,91,94,114,119,136,143],"quality":[15,92,137],"of":[16,38,56,62,78,93,138,145],"human":[17,139],"life.":[18],"Here,":[19],"a":[20,35,53,126],"neural":[21],"network":[22],"that":[23,26,103],"creates":[24],"molecules":[25],"meet":[27],"some":[28],"desired":[29,146],"multiple":[30,120],"target":[31,121],"conditions":[32],"based":[33],"on":[34],"deep":[36],"understanding":[37,55],"chemical":[39,44,63,101,106],"language":[40,64,79],"proposed":[42],"(generative":[43],"Transformer,":[45],"GCT).":[46],"The":[47,76],"attention":[48,72],"mechanism":[49],"GCT":[51,97],"allows":[52],"deeper":[54],"molecular":[57,83],"structures":[58],"beyond":[59],"limitations":[61],"itself":[65],"which":[66],"cause":[67],"semantic":[68],"discontinuity":[69],"by":[70,88,141],"paying":[71],"characters":[74],"sparsely.":[75],"significance":[77],"models":[80],"for":[81,125],"inverse":[82],"design":[84],"problems":[85],"investigated":[87],"quantitatively":[89],"evaluating":[90],"generated":[95,115],"molecules.":[96],"generates":[98],"highly":[99],"realistic":[100],"strings":[102,116],"satisfy":[104,118],"both":[105],"and":[107,123],"linguistic":[108],"grammar":[109],"rules.":[110],"Molecules":[111],"parsed":[112],"from":[113],"simultaneously":[117],"properties":[122],"vary":[124],"single":[127],"condition":[128],"set.":[129],"These":[130],"advances":[131],"will":[132],"contribute":[133],"life":[140],"accelerating":[142],"process":[144],"material":[147],"discovery.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":25},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":9}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}