{"id":"https://openalex.org/W4413331274","doi":"https://doi.org/10.1186/s13321-025-01075-4","title":"ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data","display_name":"ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data","publication_year":2025,"publication_date":"2025-08-19","ids":{"openalex":"https://openalex.org/W4413331274","doi":"https://doi.org/10.1186/s13321-025-01075-4","pmid":"https://pubmed.ncbi.nlm.nih.gov/40830907"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01075-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01075-4","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01075-4","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/counter/pdf/10.1186/s13321-025-01075-4","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066797499","display_name":"Tatsuya Sagawa","orcid":null},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I25998863","display_name":"Kyoto Pharmaceutical University","ror":"https://ror.org/01ytgve10","country_code":"JP","type":"education","lineage":["https://openalex.org/I25998863"]},{"id":"https://openalex.org/I4210116810","display_name":"RIKEN Center for Biosystems Dynamics Research","ror":"https://ror.org/023rffy11","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210116810"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Sagawa","raw_affiliation_strings":["Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto, 606-8501, Japan","RIKEN BDR, Kobe, 650-0047, Japan","Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto, 606\u20138501, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto, 606-8501, Japan","institution_ids":["https://openalex.org/I25998863","https://openalex.org/I22299242"]},{"raw_affiliation_string":"RIKEN BDR, Kobe, 650-0047, Japan","institution_ids":["https://openalex.org/I4210116810","https://openalex.org/I4210129730"]},{"raw_affiliation_string":"Graduate School of Pharmaceutical Sciences, Kyoto University, Kyoto, 606\u20138501, Japan","institution_ids":["https://openalex.org/I25998863"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013489463","display_name":"Ryosuke Kojima","orcid":"https://orcid.org/0000-0003-1095-8864"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryosuke Kojima","raw_affiliation_strings":["Graduate School of Medicine, Kyoto University, Kyoto, 606-8501, Japan. kojima.ryosuke.8e@kyoto-u.ac.jp","RIKEN BDR, Kobe, 650-0047, Japan. kojima.ryosuke.8e@kyoto-u.ac.jp","Graduate School of Medicine, Kyoto University, Kyoto, 606\u20138501, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Kyoto, 606-8501, Japan. kojima.ryosuke.8e@kyoto-u.ac.jp","institution_ids":[]},{"raw_affiliation_string":"RIKEN BDR, Kobe, 650-0047, Japan. kojima.ryosuke.8e@kyoto-u.ac.jp","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Medicine, Kyoto University, Kyoto, 606\u20138501, Japan","institution_ids":["https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5013489463"],"corresponding_institution_ids":["https://openalex.org/I22299242"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":4.0439,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.94392071,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"17","issue":"1","first_page":"126","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994999766349792,"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.9569000005722046,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.7808585166931152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.727618932723999},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6325823068618774},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.5152543187141418},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5097005367279053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44507962465286255},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4412415027618408},{"id":"https://openalex.org/keywords/chemical-space","display_name":"Chemical space","score":0.4182332158088684},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11309868097305298},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.10382267832756042},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10321739315986633}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.7808585166931152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.727618932723999},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6325823068618774},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.5152543187141418},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5097005367279053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44507962465286255},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4412415027618408},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.4182332158088684},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11309868097305298},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.10382267832756042},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10321739315986633},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"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/C35753019","wikidata":"https://www.wikidata.org/wiki/Q644785","display_name":"Total synthesis","level":2,"score":0.0},{"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/s13321-025-01075-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01075-4","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01075-4","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:40830907","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40830907","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:7fc8b933dc9f450ab907423ed0e65b6f","is_oa":true,"landing_page_url":"https://doaj.org/article/7fc8b933dc9f450ab907423ed0e65b6f","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:pubmedcentral.nih.gov:12366004","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12366004","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"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01075-4","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01075-4","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01075-4","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":[],"awards":[{"id":"https://openalex.org/G1231356974","display_name":null,"funder_award_id":"JPMJMS2024","funder_id":"https://openalex.org/F4320338247","funder_display_name":"Moonshot Research and Development Program"},{"id":"https://openalex.org/G2427697568","display_name":null,"funder_award_id":"JPMJCR22D3","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G2792802287","display_name":null,"funder_award_id":"KAKENHI","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3282004645","display_name":null,"funder_award_id":"JPMJCR","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G3670916553","display_name":null,"funder_award_id":"21H05","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G5439046914","display_name":null,"funder_award_id":"JP21H05221","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7314194600","display_name":null,"funder_award_id":"RIKEN","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7463278839","display_name":null,"funder_award_id":"21H05221","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7475791421","display_name":null,"funder_award_id":"21H05207","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G958268131","display_name":null,"funder_award_id":"JP21H05207","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320335125","display_name":"RIKEN","ror":"https://ror.org/01sjwvz98"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338247","display_name":"Moonshot Research and Development Program","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413331274.pdf","grobid_xml":"https://content.openalex.org/works/W4413331274.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W29374554","https://openalex.org/W1975147762","https://openalex.org/W2269544137","https://openalex.org/W2606363443","https://openalex.org/W2621742623","https://openalex.org/W2769423117","https://openalex.org/W2785942661","https://openalex.org/W2903262661","https://openalex.org/W2947423323","https://openalex.org/W2963250244","https://openalex.org/W2973114758","https://openalex.org/W2994678679","https://openalex.org/W3001279689","https://openalex.org/W3011411500","https://openalex.org/W3012519883","https://openalex.org/W3093934881","https://openalex.org/W3094640617","https://openalex.org/W3103092523","https://openalex.org/W3118349318","https://openalex.org/W3123901912","https://openalex.org/W3209726219","https://openalex.org/W4214868967","https://openalex.org/W4220902634","https://openalex.org/W4226271314","https://openalex.org/W4288089799","https://openalex.org/W4293569541","https://openalex.org/W4294243662","https://openalex.org/W4294362894","https://openalex.org/W4308609991","https://openalex.org/W4382239609","https://openalex.org/W4385767952","https://openalex.org/W4394997205","https://openalex.org/W4398796626","https://openalex.org/W4410003735"],"related_works":["https://openalex.org/W1443743067","https://openalex.org/W4385784498","https://openalex.org/W4385842036","https://openalex.org/W4288371066","https://openalex.org/W4285670373","https://openalex.org/W2910734083","https://openalex.org/W3101473090","https://openalex.org/W3152975457","https://openalex.org/W2155289933","https://openalex.org/W3181403764"],"abstract_inverted_index":{"Accurate":[0],"chemical":[1,21,107],"reaction":[2,22,34,108,114],"prediction":[3],"is":[4],"critical":[5],"for":[6,38],"reducing":[7],"both":[8],"cost":[9],"and":[10,42,60,104],"time":[11],"in":[12,54,58,67],"drug":[13],"development.":[14],"This":[15],"study":[16],"introduces":[17],"ReactionT5,":[18,71],"a":[19,61,76],"transformer-based":[20],"foundation":[23],"model":[24,101],"pre-trained":[25],"on":[26,83,88],"the":[27,89,93,100,106],"Open":[28],"Reaction":[29],"Database-a":[30],"large":[31],"publicly":[32],"available":[33],"dataset.":[35,91],"In":[36],"benchmarks":[37],"product":[39,55],"prediction,":[40,44,56],"retrosynthesis,":[41,59],"yield":[43,68],"ReactionT5":[45,50,96],"outperformed":[46],"existing":[47],"models.":[48],"Specifically,":[49],"achieved":[51,81],"97.5%":[52],"accuracy":[53],"71.0%":[57],"coefficient":[62],"of":[63,65,79,95,113],"determination":[64],"0.947":[66],"prediction.":[69],"Remarkably,":[70],"when":[72],"fine-tuned":[73,87],"with":[74,85],"only":[75],"limited":[77],"dataset":[78],"reactions,":[80],"performance":[82],"par":[84],"models":[86],"complete":[90],"Additionally,":[92],"visualization":[94],"embeddings":[97],"illustrates":[98],"that":[99],"successfully":[102],"captures":[103],"represents":[105],"space,":[109],"indicating":[110],"effective":[111],"learning":[112],"properties.":[115]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}