{"id":"https://openalex.org/W4412785228","doi":"https://doi.org/10.1186/s13321-025-01056-7","title":"$$\\texttt {DiffER}$$: categorical diffusion ensembles for single-step chemical retrosynthesis","display_name":"$$\\texttt {DiffER}$$: categorical diffusion ensembles for single-step chemical retrosynthesis","publication_year":2025,"publication_date":"2025-07-29","ids":{"openalex":"https://openalex.org/W4412785228","doi":"https://doi.org/10.1186/s13321-025-01056-7","pmid":"https://pubmed.ncbi.nlm.nih.gov/40734176"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01056-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01056-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01056-7.pdf","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://link.springer.com/content/pdf/10.1186/s13321-025-01056-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078612353","display_name":"Sean Current","orcid":"https://orcid.org/0000-0002-3510-6919"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sean Current","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA. current.33@osu.edu"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA. current.33@osu.edu","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100715928","display_name":"Ziqi Chen","orcid":"https://orcid.org/0009-0007-4778-8826"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ziqi Chen","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052537844","display_name":"Daniel Adu\u2010Ampratwum","orcid":"https://orcid.org/0000-0001-9392-2431"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Adu-Ampratwum","raw_affiliation_strings":["College of Pharmacy, The Ohio State University, Columbus, 43210, OH, USA"],"affiliations":[{"raw_affiliation_string":"College of Pharmacy, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028997621","display_name":"Xia Ning","orcid":"https://orcid.org/0000-0002-6842-1165"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xia Ning","raw_affiliation_strings":["Biomedical Informatics, The Ohio State University, Columbus, 43210, OH, USA","College of Pharmacy, The Ohio State University, Columbus, 43210, OH, USA","Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA","Translational Data Analytics Institute, The Ohio State University, Columbus, 43210, OH, USA"],"affiliations":[{"raw_affiliation_string":"Biomedical Informatics, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"College of Pharmacy, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Translational Data Analytics Institute, The Ohio State University, Columbus, 43210, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100755351","display_name":"Srinivasan Parthasarathy","orcid":"https://orcid.org/0000-0002-6062-6449"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivasan Parthasarathy","raw_affiliation_strings":["Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA. srini@cse.ohio-state.edu"],"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, The Ohio State University, Columbus, 43210, OH, USA. srini@cse.ohio-state.edu","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078612353"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17041475,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"112","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9779999852180481,"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"}},"topics":[{"id":"https://openalex.org/T12285","display_name":"Surface Chemistry and Catalysis","score":0.9779999852180481,"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"}},{"id":"https://openalex.org/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9627000093460083,"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"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.954200029373169,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.8139387369155884},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7567861080169678},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7051124572753906},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5738113522529602},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44445550441741943},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.42394334077835083},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32582592964172363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32043886184692383},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.07370272278785706}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.8139387369155884},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567861080169678},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7051124572753906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5738113522529602},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44445550441741943},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.42394334077835083},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32582592964172363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32043886184692383},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.07370272278785706},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/s13321-025-01056-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01056-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01056-7.pdf","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:40734176","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40734176","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:bafa542ff7ac450aa66597e4fdf10ba0","is_oa":true,"landing_page_url":"https://doaj.org/article/bafa542ff7ac450aa66597e4fdf10ba0","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 1-16 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12309231","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12309231","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-025-01056-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01056-7","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-025-01056-7.pdf","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":[{"score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G5433473004","display_name":null,"funder_award_id":"2133650","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7427039554","display_name":null,"funder_award_id":"IIS-2133650","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8459309708","display_name":null,"funder_award_id":"1R01LM014385","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412785228.pdf","grobid_xml":"https://content.openalex.org/works/W4412785228.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W1978890358","https://openalex.org/W2001496974","https://openalex.org/W2022708431","https://openalex.org/W2062601468","https://openalex.org/W2109885290","https://openalex.org/W2551217916","https://openalex.org/W2580919858","https://openalex.org/W2621742623","https://openalex.org/W2747592475","https://openalex.org/W2769756736","https://openalex.org/W2988975212","https://openalex.org/W3034999214","https://openalex.org/W3119022334","https://openalex.org/W3138801267","https://openalex.org/W3152975457","https://openalex.org/W3181403764","https://openalex.org/W3189262114","https://openalex.org/W3202979417","https://openalex.org/W3207248525","https://openalex.org/W4226159083","https://openalex.org/W4229040393","https://openalex.org/W4286901673","https://openalex.org/W4312388283","https://openalex.org/W4378783602","https://openalex.org/W4385569744","https://openalex.org/W4389518872","https://openalex.org/W4390873054","https://openalex.org/W4401042320","https://openalex.org/W4409365581","https://openalex.org/W6977367121"],"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/W4385784463","https://openalex.org/W4390658374","https://openalex.org/W4285584547"],"abstract_inverted_index":{"Methods":[0],"for":[1,16,61,94,100,118],"automatic":[2],"chemical":[3,38],"retrosynthesis":[4,63],"have":[5,27],"found":[6],"recent":[7],"success":[8],"through":[9,21],"the":[10,34,66,73],"application":[11],"of":[12,37,48,68,87,122,128,132],"models":[13,26,89],"traditionally":[14],"built":[15],"natural":[17],"language":[18],"processing,":[19],"primarily":[20],"transformer":[22],"neural":[23],"networks.":[24],"These":[25],"demonstrated":[28],"significant":[29],"ability":[30],"to":[31,78],"translate":[32],"between":[33],"SMILES":[35,76],"encodings":[36],"products":[39],"and":[40,97,103,125],"reactants,":[41],"but":[42],"are":[43],"constrained":[44],"as":[45],"a":[46,115,119,130],"result":[47],"their":[49],"autoregressive":[50],"nature.":[51],"We":[52,83,109],"propose":[53],"<mml:math":[54,112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"><mml:mi>DiffER</mml:mi></mml:math>":[55,113],",":[56],"an":[57,85],"alternative":[58],"template-free":[59,107,123],"method":[60],"single-step":[62],"prediction":[64],"in":[65,81,136],"form":[67],"categorical":[69],"diffusion,":[70],"which":[71,90],"allows":[72],"entire":[74],"output":[75],"sequence":[77],"be":[79],"predicted":[80],"unison.":[82],"construct":[84],"ensemble":[86],"diffusion":[88],"achieves":[91],"state-of-the-art":[92],"performance":[93,99],"top-1":[95],"accuracy":[96,105],"competitive":[98],"top-3,":[101],"top-5,":[102],"top-10":[104],"among":[106],"methods.":[108],"prove":[110],"that":[111],"is":[114,126],"strong":[116],"baseline":[117],"new":[120],"class":[121],"model":[124],"capable":[127],"learning":[129],"variety":[131],"synthetic":[133],"techniques":[134],"used":[135],"laboratory":[137],"settings.":[138]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-07-31T00:00:00"}
