{"id":"https://openalex.org/W3158543275","doi":"https://doi.org/10.1186/s13321-021-00512-4","title":"STOUT: SMILES to IUPAC names using neural machine translation","display_name":"STOUT: SMILES to IUPAC names using neural machine translation","publication_year":2021,"publication_date":"2021-04-27","ids":{"openalex":"https://openalex.org/W3158543275","doi":"https://doi.org/10.1186/s13321-021-00512-4","mag":"3158543275","pmid":"https://pubmed.ncbi.nlm.nih.gov/33906675"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-021-00512-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00512-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00512-4","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/track/pdf/10.1186/s13321-021-00512-4","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":"https://orcid.org/0000-0001-6966-0814","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":1606,"currency":"EUR","value_usd":1732},"fwci":6.2424,"has_fulltext":true,"cited_by_count":59,"citation_normalized_percentile":{"value":0.96903722,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"13","issue":"1","first_page":"34","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9909999966621399,"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":0.9861999750137329,"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":0.968098521232605},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.8547223806381226},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347032427787781},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6319319605827332},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.59807950258255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5747568011283875},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.540604829788208},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5395954847335815},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.45417022705078125},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.4503799378871918},{"id":"https://openalex.org/keywords/nomenclature","display_name":"Nomenclature","score":0.41942453384399414},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.36722487211227417},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.3166903257369995},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1532350778579712},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1260107457637787},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.09122982621192932},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.09031742811203003}],"concepts":[{"id":"https://openalex.org/C125832229","wikidata":"https://www.wikidata.org/wiki/Q6503924","display_name":"Chemical nomenclature","level":2,"score":0.968098521232605},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8547223806381226},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347032427787781},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6319319605827332},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.59807950258255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5747568011283875},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.540604829788208},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5395954847335815},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45417022705078125},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.4503799378871918},{"id":"https://openalex.org/C514705636","wikidata":"https://www.wikidata.org/wiki/Q863247","display_name":"Nomenclature","level":3,"score":0.41942453384399414},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.36722487211227417},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.3166903257369995},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1532350778579712},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1260107457637787},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.09122982621192932},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.09031742811203003},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13321-021-00512-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00512-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00512-4","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:33906675","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33906675","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:doaj.org/article:047c066be151498aaa46e25b8ed3f0c2","is_oa":true,"landing_page_url":"https://doaj.org/article/047c066be151498aaa46e25b8ed3f0c2","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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 13, Iss 1, Pp 1-14 (2021)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8077691","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8077691","pdf_url":null,"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:www.db-thueringen.de:dbt_mods_00056075","is_oa":true,"landing_page_url":"https://www.db-thueringen.de/receive/dbt_mods_00056075","pdf_url":null,"source":{"id":"https://openalex.org/S4306400120","display_name":"Common Library Network (Der Gemeinsame Bibliotheksverbund)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210149878","host_organization_name":"Verbundzentrale des GBV","host_organization_lineage":["https://openalex.org/I4210149878"],"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":"","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s13321-021-00512-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-021-00512-4","pdf_url":"https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-021-00512-4","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":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.49000000953674316}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313941","display_name":"Friedrich-Schiller-Universit\u00e4t Jena","ror":"https://ror.org/05qpz1x62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3158543275.pdf","grobid_xml":"https://content.openalex.org/works/W3158543275.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W568917201","https://openalex.org/W653966990","https://openalex.org/W1508604947","https://openalex.org/W1902237438","https://openalex.org/W1975147762","https://openalex.org/W2034354062","https://openalex.org/W2049654081","https://openalex.org/W2101105183","https://openalex.org/W2133564696","https://openalex.org/W2148797284","https://openalex.org/W2169678694","https://openalex.org/W2325049946","https://openalex.org/W2344597831","https://openalex.org/W2895677720","https://openalex.org/W2896457183","https://openalex.org/W2899070097","https://openalex.org/W2978153005","https://openalex.org/W3009321976","https://openalex.org/W3045928028","https://openalex.org/W3097598035","https://openalex.org/W3137038343","https://openalex.org/W3186326839","https://openalex.org/W3200621845","https://openalex.org/W4229590462","https://openalex.org/W4235912386","https://openalex.org/W4244590267"],"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":{"Chemical":[0],"compounds":[1],"can":[2],"be":[3],"identified":[4],"through":[5],"a":[6,9,14,38,49,63,83,95,135,147],"graphical":[7],"depiction,":[8],"suitable":[10],"string":[11,101,112],"representation,":[12],"or":[13],"chemical":[15,51],"name.":[16,116],"A":[17],"universally":[18],"accepted":[19],"naming":[20],"scheme":[21],"for":[22,56,94],"chemistry":[23],"was":[24],"established":[25],"by":[26],"the":[27,44,91,105,110,114,120],"International":[28],"Union":[29],"of":[30,40,46,131,139],"Pure":[31],"and":[32,59,134,152],"Applied":[33],"Chemistry":[34],"(IUPAC)":[35],"based":[36],"on":[37],"set":[39],"rules.":[41],"Due":[42],"to":[43,89,124],"complexity":[45],"this":[47,71],"ruleset":[48],"correct":[50],"name":[52,93],"assignment":[53],"remains":[54],"challenging":[55],"human":[57],"beings":[58],"there":[60],"are":[61],"only":[62],"few":[64],"rule-based":[65],"cheminformatics":[66],"toolkits":[67],"available":[68],"that":[69],"support":[70],"task":[72],"in":[73],"an":[74,127],"automated":[75],"manner.":[76],"Here":[77],"we":[78],"present":[79],"STOUT":[80],"(SMILES-TO-IUPAC-name":[81],"translator),":[82],"deep-learning":[84],"neural":[85],"machine":[86],"translation":[87],"approach":[88],"generate":[90],"IUPAC":[92,115],"given":[96],"molecule":[97],"from":[98,113],"its":[99],"SMILES":[100,111],"as":[102,104],"well":[103],"reverse":[106],"translation,":[107],"i.e.":[108],"predicting":[109],"In":[117],"both":[118],"cases,":[119],"system":[121],"is":[122],"able":[123],"predict":[125],"with":[126],"average":[128],"BLEU":[129],"score":[130],"about":[132],"90%":[133],"Tanimoto":[136],"similarity":[137,149],"index":[138],"more":[140],"than":[141],"0.9.":[142],"Also":[143],"incorrect":[144],"predictions":[145],"show":[146],"remarkable":[148],"between":[150],"true":[151],"predicted":[153],"compounds.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
