{"id":"https://openalex.org/W4417339085","doi":"https://doi.org/10.1109/ictai66417.2025.00091","title":"A Transformer Model for Predicting Chemical Products from Generic SMARTS Templates with Data Augmentation","display_name":"A Transformer Model for Predicting Chemical Products from Generic SMARTS Templates with Data Augmentation","publication_year":2025,"publication_date":"2025-11-03","ids":{"openalex":"https://openalex.org/W4417339085","doi":"https://doi.org/10.1109/ictai66417.2025.00091"},"language":null,"primary_location":{"id":"doi:10.1109/ictai66417.2025.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Derin Ozer","orcid":null},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Derin Ozer","raw_affiliation_strings":["Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000"],"affiliations":[{"raw_affiliation_string":"Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071891236","display_name":"Sylvain Lamprier","orcid":null},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Sylvain Lamprier","raw_affiliation_strings":["Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000"],"affiliations":[{"raw_affiliation_string":"Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055740979","display_name":"Nicolas Gutowski","orcid":"https://orcid.org/0000-0002-5765-9901"},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Gutowski","raw_affiliation_strings":["Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000"],"affiliations":[{"raw_affiliation_string":"Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018380335","display_name":"Benoit Da Mota","orcid":"https://orcid.org/0000-0003-0807-8892"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210137122","display_name":"Institut des Sciences et Technologies Mol\u00e9culaires d'Angers","ror":"https://ror.org/039yyx623","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I4210128300","https://openalex.org/I4210137122","https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Benoit Da Mota","raw_affiliation_strings":["Univ Angers, CNRS, MOLTECH-ANJOU, SFR MATRIX,Angers,France,F-49000"],"affiliations":[{"raw_affiliation_string":"Univ Angers, CNRS, MOLTECH-ANJOU, SFR MATRIX,Angers,France,F-49000","institution_ids":["https://openalex.org/I4210137122","https://openalex.org/I1294671590"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027991232","display_name":"Thomas Cauchy","orcid":"https://orcid.org/0000-0003-4259-3257"},"institutions":[{"id":"https://openalex.org/I49451733","display_name":"Universit\u00e9 d'Angers","ror":"https://ror.org/04yrqp957","country_code":"FR","type":"education","lineage":["https://openalex.org/I49451733"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Thomas Cauchy","raw_affiliation_strings":["Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000"],"affiliations":[{"raw_affiliation_string":"Univ Angers, LERIA, SFR MATHSTIC,Angers,France,F-49000","institution_ids":["https://openalex.org/I49451733"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I49451733"],"apc_list":null,"apc_paid":null,"fwci":0.4667,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68260053,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"630","last_page":"636"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9729999899864197,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9729999899864197,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.00860000029206276,"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/T11281","display_name":"Asymmetric Hydrogenation and Catalysis","score":0.00419999985024333,"subfield":{"id":"https://openalex.org/subfields/1604","display_name":"Inorganic Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.8464000225067139},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6144999861717224},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.5889000296592712},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5564000010490417},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4034999907016754},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.3614000082015991},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.8464000225067139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6797999739646912},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6144999861717224},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.5889000296592712},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5564000010490417},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4034999907016754},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.28110000491142273},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2773999869823456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C2991944050","wikidata":"https://www.wikidata.org/wiki/Q36534","display_name":"Reaction conditions","level":3,"score":0.2646999955177307},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26429998874664307},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.26350000500679016},{"id":"https://openalex.org/C189474733","wikidata":"https://www.wikidata.org/wiki/Q917912","display_name":"Model building","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C148043351","wikidata":"https://www.wikidata.org/wiki/Q4456944","display_name":"Current (fluid)","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictai66417.2025.00091","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictai66417.2025.00091","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2160592148","https://openalex.org/W2947423323","https://openalex.org/W3010145447","https://openalex.org/W3087570960","https://openalex.org/W3094640617","https://openalex.org/W3189262114","https://openalex.org/W3204208927","https://openalex.org/W3209056694","https://openalex.org/W4226159083","https://openalex.org/W4313485929"],"related_works":[],"abstract_inverted_index":{"The":[0],"accurate":[1],"prediction":[2],"of":[3,28,77,85,142],"chemical":[4],"reaction":[5,22,48,91,144],"outcomes":[6],"is":[7],"a":[8,43,53,66,131],"major":[9],"challenge":[10],"in":[11,51],"computational":[12],"chemistry.":[13],"Current":[14],"models":[15],"rely":[16],"heavily":[17],"on":[18,114],"either":[19],"highly":[20],"specific":[21],"templates":[23,49],"or":[24],"template-free":[25],"methods,":[26,138],"both":[27],"which":[29,105],"present":[30],"limitations.":[31],"To":[32,93],"address":[33],"these,":[34],"this":[35],"work":[36],"proposes":[37],"the":[38,75,80,99,110,140],"Broad":[39],"Reaction":[40],"Set":[41],"(BRS),":[42],"set":[44],"featuring":[45],"20":[46],"generic":[47],"written":[50],"SMARTS,":[52,104],"pattern-based":[54],"notation":[55],"designed":[56],"to":[57,74,124,136],"describe":[58],"substructures":[59],"and":[60,88,122,133],"reactivity.":[61],"Additionally,":[62],"we":[63,97],"introduce":[64],"ProPreT5,":[65],"T5-based":[67],"model":[68,83],"specifically":[69],"adapted":[70],"for":[71,103],"chemistry":[72],"and,":[73],"best":[76],"our":[78],"knowledge,":[79],"first":[81,100],"language":[82],"capable":[84],"directly":[86],"handling":[87],"applying":[89],"SMARTS":[90],"templates.":[92],"further":[94],"improve":[95],"generalization,":[96],"propose":[98],"augmentation":[101],"strategy":[102],"injects":[106],"structural":[107],"diversity":[108],"at":[109],"pattern":[111],"level.":[112],"Trained":[113],"augmented":[115],"templates,":[116],"ProPreT5":[117],"demonstrates":[118],"strong":[119],"predictive":[120],"performance":[121],"generalization":[123],"unseen":[125],"reactions.":[126],"Together,":[127],"these":[128],"contributions":[129],"provide":[130],"novel":[132],"practical":[134],"alternative":[135],"current":[137],"advancing":[139],"field":[141],"template-based":[143],"prediction.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-11-28T00:00:00"}