{"id":"https://openalex.org/W4412363088","doi":"https://doi.org/10.1186/s13321-025-01016-1","title":"A transformer based generative chemical language AI model for structural elucidation of organic compounds","display_name":"A transformer based generative chemical language AI model for structural elucidation of organic compounds","publication_year":2025,"publication_date":"2025-07-12","ids":{"openalex":"https://openalex.org/W4412363088","doi":"https://doi.org/10.1186/s13321-025-01016-1","pmid":"https://pubmed.ncbi.nlm.nih.gov/40652284"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01016-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01016-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01016-1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/s13321-025-01016-1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061450403","display_name":"Xiaofeng Tan","orcid":"https://orcid.org/0000-0002-1114-3571"},"institutions":[{"id":"https://openalex.org/I4210101205","display_name":"NOVA Scientific (United States)","ror":"https://ror.org/015snna87","country_code":"US","type":"company","lineage":["https://openalex.org/I4210101205"]},{"id":"https://openalex.org/I4210141097","display_name":"T\u00e2n T\u1ea1o University","ror":"https://ror.org/03q6f0894","country_code":"VN","type":"education","lineage":["https://openalex.org/I4210141097"]}],"countries":["US","VN"],"is_corresponding":true,"raw_author_name":"Xiaofeng Tan","raw_affiliation_strings":["X Scientific, 1 Bramble Way, Acton, MA, 01720, USA. x.tan@jhu.edu","X Scientific, 1 Bramble Way, Acton, MA, 01720, USA"],"raw_orcid":"https://orcid.org/0000-0002-1114-3571","affiliations":[{"raw_affiliation_string":"X Scientific, 1 Bramble Way, Acton, MA, 01720, USA. x.tan@jhu.edu","institution_ids":["https://openalex.org/I4210141097"]},{"raw_affiliation_string":"X Scientific, 1 Bramble Way, Acton, MA, 01720, USA","institution_ids":["https://openalex.org/I4210101205"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061450403"],"corresponding_institution_ids":["https://openalex.org/I4210101205","https://openalex.org/I4210141097"],"apc_list":{"value":2190,"currency":"USD","value_usd":2190},"apc_paid":{"value":2190,"currency":"USD","value_usd":2190},"fwci":8.7524,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.98133645,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"17","issue":"1","first_page":"103","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9962000250816345,"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":0.9143999814987183,"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/transformer","display_name":"Transformer","score":0.7230896949768066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6662917137145996},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.6111372113227844},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4317823648452759},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4002060294151306},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3816964030265808},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1302259862422943},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.08243885636329651}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7230896949768066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6662917137145996},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6111372113227844},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4317823648452759},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4002060294151306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3816964030265808},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1302259862422943},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.08243885636329651},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01016-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01016-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01016-1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:40652284","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40652284","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:34992881cbbe42478fa3a4199a2645d1","is_oa":true,"landing_page_url":"https://doaj.org/article/34992881cbbe42478fa3a4199a2645d1","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 17, Iss 1, Pp 1-14 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11060938","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12255981","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01016-1","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01016-1","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01016-1","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2","score":0.47999998927116394,"display_name":"Zero hunger"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412363088.pdf","grobid_xml":"https://content.openalex.org/works/W4412363088.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1964220924","https://openalex.org/W1975147762","https://openalex.org/W1980139576","https://openalex.org/W1988521080","https://openalex.org/W1999638776","https://openalex.org/W2020843065","https://openalex.org/W2038702914","https://openalex.org/W2055168683","https://openalex.org/W2057785351","https://openalex.org/W2060531713","https://openalex.org/W2068546873","https://openalex.org/W2071887528","https://openalex.org/W2076009699","https://openalex.org/W2077396836","https://openalex.org/W2080635178","https://openalex.org/W2089830231","https://openalex.org/W2094498700","https://openalex.org/W2108581180","https://openalex.org/W2114704115","https://openalex.org/W2119813631","https://openalex.org/W2146172880","https://openalex.org/W2162476010","https://openalex.org/W2194775991","https://openalex.org/W2206991991","https://openalex.org/W2551276392","https://openalex.org/W2618530766","https://openalex.org/W2768356390","https://openalex.org/W2793166270","https://openalex.org/W2800536572","https://openalex.org/W2899070097","https://openalex.org/W2937203476","https://openalex.org/W2942881993","https://openalex.org/W3010185406","https://openalex.org/W3010662401","https://openalex.org/W3032893151","https://openalex.org/W3047885487","https://openalex.org/W3102068512","https://openalex.org/W3164743754","https://openalex.org/W3177525997","https://openalex.org/W3211299256","https://openalex.org/W4213019189","https://openalex.org/W4213099919","https://openalex.org/W4221053795","https://openalex.org/W4226085666","https://openalex.org/W4231250337","https://openalex.org/W4255146965","https://openalex.org/W4293199734","https://openalex.org/W4318192371","https://openalex.org/W4321603581","https://openalex.org/W4376612719","https://openalex.org/W4377704731","https://openalex.org/W4385808309","https://openalex.org/W4388623498","https://openalex.org/W4391828182","https://openalex.org/W4391966553","https://openalex.org/W4396721167","https://openalex.org/W4400460362","https://openalex.org/W4402816203","https://openalex.org/W4404755712","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4391584540","https://openalex.org/W3204019825","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4395044357","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071"],"abstract_inverted_index":{"For":[0],"over":[1],"half":[2],"a":[3,50,138,142,146,189,195],"century,":[4],"computer-aided":[5],"structural":[6,37,82,127,184,199],"elucidation":[7,128,200,228],"systems":[8,18,24,207],"(CASE)":[9],"for":[10,29,77,180,201],"organic":[11,202],"compounds":[12,31],"have":[13],"relied":[14],"on":[15,115,141,174],"complex":[16,30],"expert":[17],"with":[19,131,208,234],"explicitly":[20],"programmed":[21],"algorithms.":[22],"These":[23],"are":[25],"often":[26],"computationally":[27],"inefficient":[28],"due":[32],"to":[33,66,94,100,133,161,170,198,221],"the":[34,68,73,103,110,154,216,227],"vast":[35],"chemical":[36,55,106],"space":[38],"that":[39,108],"must":[40],"be":[41],"explored":[42],"and":[43,70,79,90,121,230],"filtered.":[44],"In":[45],"this":[46],"study,":[47],"we":[48],"present":[49],"proof-of-concept":[51],"transformer":[52,157,219],"based":[53,158,173],"generative":[54,159,191],"language":[56,98],"artificial":[57],"intelligence":[58],"(AI)":[59],"model,":[60],"an":[61,87,209],"innovative":[62],"end-to-end":[63,210],"architecture":[64,89],"designed":[65],"replace":[67],"logic":[69],"workflow":[71],"of":[72,129,149,156,218],"classic":[74],"CASE":[75,206,223],"framework":[76],"ultra-fast":[78],"accurate":[80],"spectroscopic-based":[81],"elucidation.":[83,185],"Our":[84],"model":[85,193],"employs":[86],"encoder-decoder":[88,211],"self-attention":[91],"mechanisms,":[92],"similar":[93],"those":[95],"in":[96,136,183],"large":[97],"models,":[99],"directly":[101],"generate":[102],"most":[104],"probable":[105],"structures":[107],"match":[109],"input":[111],"spectroscopic":[112],"data.":[113,236],"Trained":[114],"~":[116],"102":[117],"k":[118],"IR,":[119],"UV,":[120],"1H":[122],"NMR":[123],"spectra,":[124],"it":[125],"performs":[126],"molecules":[130],"up":[132],"29":[134],"atoms":[135],"just":[137],"few":[139],"seconds":[140],"modern":[143],"CPU,":[144],"achieving":[145],"top-15":[147],"accuracy":[148],"83%.":[150],"This":[151,186,213],"approach":[152,197],"demonstrates":[153,215],"potential":[155,179,217],"AI":[160,192],"accelerate":[162],"traditional":[163,205],"scientific":[164],"problem-solving":[165],"processes.":[166],"The":[167],"model's":[168],"ability":[169],"iterate":[171],"quickly":[172],"new":[175,235],"data":[176],"highlights":[177],"its":[178],"rapid":[181,232],"advancements":[182],"study":[187],"introduces":[188],"transformer-based":[190],"as":[194],"novel":[196],"compounds,":[203],"replacing":[204],"architecture.":[212],"work":[214],"models":[220],"revolutionize":[222],"by":[224],"significantly":[225],"accelerating":[226],"process":[229],"enabling":[231],"iterations":[233]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-08T01:25:22.217667","created_date":"2025-10-10T00:00:00"}