{"id":"https://openalex.org/W4405828862","doi":"https://doi.org/10.1186/s13321-024-00941-x","title":"STOUT V2.0: SMILES to IUPAC name conversion using transformer models","display_name":"STOUT V2.0: SMILES to IUPAC name conversion using transformer models","publication_year":2024,"publication_date":"2024-12-27","ids":{"openalex":"https://openalex.org/W4405828862","doi":"https://doi.org/10.1186/s13321-024-00941-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/39731139"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-024-00941-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00941-x","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00941-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00941-x","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017832889","display_name":"Kohulan Rajan","orcid":"https://orcid.org/0000-0003-1066-7792"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Kohulan Rajan","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089744377","display_name":"Achim Zielesny","orcid":"https://orcid.org/0000-0003-0722-4229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Achim Zielesny","raw_affiliation_strings":["Institute for Bioinformatics and Chemoinformatics, Westphalian University of Applied Sciences, August-Schmidt-Ring 10, 45665, Recklinghausen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Bioinformatics and Chemoinformatics, Westphalian University of Applied Sciences, August-Schmidt-Ring 10, 45665, Recklinghausen, Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040194803","display_name":"Christoph Steinbeck","orcid":"https://orcid.org/0000-0001-6966-0814"},"institutions":[{"id":"https://openalex.org/I76198965","display_name":"Friedrich Schiller University Jena","ror":"https://ror.org/05qpz1x62","country_code":"DE","type":"education","lineage":["https://openalex.org/I76198965"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Christoph Steinbeck","raw_affiliation_strings":["Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany. christoph.steinbeck@uni-jena.de","Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany. christoph.steinbeck@uni-jena.de","institution_ids":["https://openalex.org/I76198965"]},{"raw_affiliation_string":"Institute for Inorganic and Analytical Chemistry, Friedrich Schiller University Jena, Lessingstr. 8, 07743, Jena, Germany","institution_ids":["https://openalex.org/I76198965"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040194803"],"corresponding_institution_ids":["https://openalex.org/I76198965"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":2.8348,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91967997,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"16","issue":"1","first_page":"146","last_page":"146"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.998199999332428,"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":0.998199999332428,"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":0.996999979019165,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9958000183105469,"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/chemical-nomenclature","display_name":"Chemical nomenclature","score":0.9842522144317627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7261918783187866},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5343469977378845},{"id":"https://openalex.org/keywords/nomenclature","display_name":"Nomenclature","score":0.49142205715179443},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4482175409793854},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38221532106399536},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35926687717437744},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3241351246833801},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.2675941288471222},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.21130967140197754},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1520567238330841}],"concepts":[{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.9842522144317627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7261918783187866},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5343469977378845},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.49142205715179443},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4482175409793854},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38221532106399536},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35926687717437744},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3241351246833801},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.2675941288471222},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.21130967140197754},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1520567238330841},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"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/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-024-00941-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00941-x","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00941-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:39731139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/39731139","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 cheminformatics","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:11673719","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/11673719","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC11673719/pdf/13321_2024_Article_941.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:eb7068ea06ef41828fa282d747bc0711","is_oa":false,"landing_page_url":"https://doaj.org/article/eb7068ea06ef41828fa282d747bc0711","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 16, Iss 1, Pp 1-27 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-024-00941-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-024-00941-x","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-024-00941-x","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G6646511001","display_name":"SFB 1127: Chemische Mediatoren in komplexen Biosystemen (ChemBioSys)","funder_award_id":"239748522","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320313941","display_name":"Friedrich-Schiller-Universit\u00e4t Jena","ror":"https://ror.org/05qpz1x62"},{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405828862.pdf","grobid_xml":"https://content.openalex.org/works/W4405828862.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W2031450906","https://openalex.org/W2034354062","https://openalex.org/W2055888446","https://openalex.org/W2101105183","https://openalex.org/W2148797284","https://openalex.org/W2162651021","https://openalex.org/W2165698076","https://openalex.org/W2344597831","https://openalex.org/W2610148085","https://openalex.org/W2622236128","https://openalex.org/W2769423117","https://openalex.org/W2947411064","https://openalex.org/W2994270865","https://openalex.org/W3097598035","https://openalex.org/W3137038343","https://openalex.org/W3158543275","https://openalex.org/W3182207208","https://openalex.org/W3186326839","https://openalex.org/W4230927156","https://openalex.org/W4307468223","https://openalex.org/W4318912574","https://openalex.org/W4366988472","https://openalex.org/W4381252028","https://openalex.org/W4385188297","https://openalex.org/W4386001223","https://openalex.org/W4400811249"],"related_works":["https://openalex.org/W37902791","https://openalex.org/W4306291275","https://openalex.org/W4298847056","https://openalex.org/W4237911218","https://openalex.org/W2764713382","https://openalex.org/W4318710619","https://openalex.org/W2603795397","https://openalex.org/W4230503499","https://openalex.org/W4290641096","https://openalex.org/W2765073883"],"abstract_inverted_index":{"Naming":[0],"chemical":[1,61,83,106,138,150,171,197],"compounds":[2,62],"systematically":[3],"is":[4,71,206],"a":[5,10,98,113,207],"complex":[6,137],"task":[7],"governed":[8],"by":[9,15,32,96,176],"set":[11],"of":[12,19,60,81,105,115,189],"rules":[13,26],"established":[14,162],"the":[16,78,166,187,224],"International":[17],"Union":[18],"Pure":[20],"and":[21,29,121,147,157,220,226,231,239],"Applied":[22],"Chemistry":[23],"(IUPAC).":[24],"These":[25],"are":[27],"universal":[28],"widely":[30],"accepted":[31],"chemists":[33],"worldwide,":[34],"but":[35],"their":[36,67,122],"complexity":[37],"makes":[38],"it":[39,74,153],"challenging":[40],"for":[41,136,169],"individuals":[42],"to":[43,54,143,154,178,192,235],"consistently":[44],"apply":[45],"them":[46],"accurately.":[47],"A":[48],"translation":[49,59],"method":[50],"can":[51,75],"be":[52],"employed":[53],"address":[55],"this":[56,94],"challenge.":[57],"Accurate":[58],"from":[63,210],"SMILES":[64,119],"notation":[65],"into":[66,108],"corresponding":[68,123],"IUPAC":[69,109,124,133,159],"names":[70],"crucial,":[72],"as":[73],"significantly":[76],"streamline":[77],"laborious":[79],"process":[80],"naming":[82],"structures.":[84,139],"Here,":[85],"we":[86,233],"present":[87],"STOUT":[88,126,200],"(SMILES-TO-IUPAC-name":[89],"translator)":[90],"V2,":[91,201],"which":[92],"addresses":[93],"challenge":[95],"introducing":[97],"transformer-based":[99,204],"model":[100,225],"that":[101],"translates":[102],"string":[103],"representations":[104],"structures":[107,151],"names.":[110,160],"Trained":[111],"on":[112],"dataset":[114],"nearly":[116],"1":[117],"billion":[118],"strings":[120],"names,":[125,134],"V2":[127],"demonstrates":[128,186],"exceptional":[129],"accuracy":[130],"in":[131,196],"generating":[132],"even":[135],"The":[140,214],"model's":[141],"ability":[142],"capture":[144],"intricate":[145],"patterns":[146],"relationships":[148],"within":[149],"enables":[152],"generate":[155],"precise":[156],"standardised":[158],"While":[161],"deterministic":[163],"algorithms":[164],"remain":[165],"gold":[167],"standard":[168],"systematic":[170],"naming,":[172],"our":[173,211],"work,":[174],"enabled":[175],"access":[177],"OpenEye's":[179],"Lexichem":[180],"software":[181],"through":[182],"an":[183],"academic":[184],"license,":[185],"potential":[188],"neural":[190],"approaches":[191],"complement":[193],"existing":[194],"tools":[195],"nomenclature.Scientific":[198],"contribution":[199],"built":[202],"upon":[203],"models,":[205],"significant":[208],"advancement":[209],"previous":[212],"work.":[213],"web":[215],"application":[216],"enhances":[217],"its":[218],"accessibility":[219],"utility.":[221],"By":[222],"making":[223],"source":[227],"code":[228],"fully":[229],"open":[230],"well-documented,":[232],"aim":[234],"promote":[236],"unrestricted":[237],"use":[238],"encourage":[240],"further":[241],"development.":[242]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":4}],"updated_date":"2026-06-22T08:00:12.763002","created_date":"2025-10-10T00:00:00"}
