{"id":"https://openalex.org/W7126068308","doi":"https://doi.org/10.1109/bibm66473.2025.11356672","title":"Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis","display_name":"Copy-Augmented Representation for Structure Invariant Template-Free Retrosynthesis","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126068308","doi":"https://doi.org/10.1109/bibm66473.2025.11356672"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","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":"https://openalex.org/A5027540894","display_name":"Jiaxi Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxi Zhuang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124172603","display_name":"Yu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhang","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liang Dou","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Dou","raw_affiliation_strings":["School of Computer Science and Technology, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065275675","display_name":"Aimin Zhou","orcid":"https://orcid.org/0000-0001-6469-6279"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aimin Zhou","raw_affiliation_strings":["Shanghai Institute of Artificial Intelligence for Education, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101444861","display_name":"Ying Qian","orcid":"https://orcid.org/0000-0003-4961-5842"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Qian","raw_affiliation_strings":["Shanghai Institute of Artificial Intelligence for Education, East China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Artificial Intelligence for Education, East China Normal University","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5115","last_page":"5122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.6689000129699707,"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":0.6689000129699707,"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":0.23330000042915344,"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":0.010999999940395355,"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/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.7294999957084656},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6891999840736389},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6337000131607056},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5509999990463257},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.43059998750686646},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.37290000915527344},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.31189998984336853}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.7294999957084656},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6891999840736389},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6337000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5670999884605408},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5509999990463257},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.45660001039505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4530999958515167},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.37290000915527344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.349700003862381},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C58312451","wikidata":"https://www.wikidata.org/wiki/Q4817200","display_name":"Atom (system on chip)","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26930001378059387},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C116409475","wikidata":"https://www.wikidata.org/wiki/Q1385056","display_name":"External Data Representation","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356672","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356672","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8079301387","display_name":null,"funder_award_id":"2024YFC3308500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1970259423","https://openalex.org/W1975147762","https://openalex.org/W1996585089","https://openalex.org/W2001496974","https://openalex.org/W2035301451","https://openalex.org/W2041548070","https://openalex.org/W2164948578","https://openalex.org/W2183341477","https://openalex.org/W2255466643","https://openalex.org/W2551217916","https://openalex.org/W2606974598","https://openalex.org/W2747592475","https://openalex.org/W2769756736","https://openalex.org/W2947423323","https://openalex.org/W2994678679","https://openalex.org/W3088265803","https://openalex.org/W3104565655","https://openalex.org/W3152975457","https://openalex.org/W3174318304","https://openalex.org/W3189262114","https://openalex.org/W4226159083","https://openalex.org/W4229040393","https://openalex.org/W4230167402","https://openalex.org/W4286901673","https://openalex.org/W4378219995","https://openalex.org/W4385245566","https://openalex.org/W4401108625"],"related_works":[],"abstract_inverted_index":{"Retrosynthesis":[0],"prediction":[1,48],"is":[2],"fundamental":[3],"to":[4,25,41,89,107],"drug":[5,163],"discovery":[6],"and":[7,46,74,124,137],"chemical":[8,32],"synthesis,":[9],"requiring":[10],"the":[11,27,99],"identification":[12],"of":[13],"reactants":[14,73],"that":[15,57,85],"can":[16],"produce":[17],"a":[18,53,82,151],"target":[19],"molecule.":[20],"Current":[21],"templatefree":[22],"methods":[23],"struggle":[24],"capture":[26],"structural":[28],"invariance":[29],"inherent":[30],"in":[31,145,161],"reactions,":[33],"where":[34],"substantial":[35],"molecular":[36,55,96,156],"scaffolds":[37],"remain":[38],"unchanged,":[39],"leading":[40],"unnecessarily":[42],"large":[43],"search":[44],"spaces":[45],"reduced":[47],"accuracy.":[49],"We":[50],"introduce":[51],"C-SMILES,":[52],"novel":[54],"representation":[56],"decomposes":[58],"traditional":[59],"SMILES":[60,104],"into":[61],"element-token":[62],"pairs":[63],"with":[64,111,141,158],"five":[65],"special":[66],"tokens,":[67],"effectively":[68],"minimizing":[69],"editing":[70],"distance":[71],"between":[72],"products.":[75],"Building":[76],"upon":[77],"this":[78],"representation,":[79],"we":[80],"incorporate":[81],"copy-augmented":[83],"mechanism":[84],"dynamically":[86],"determines":[87],"whether":[88],"generate":[90],"new":[91,152],"tokens":[92],"or":[93],"preserve":[94],"unchanged":[95],"fragments":[97],"from":[98],"product.":[100],"Our":[101],"approach":[102],"integrates":[103],"alignment":[105],"guidance":[106],"enhance":[108],"attention":[109],"consistency":[110],"ground-truth":[112],"atom":[113],"mappings,":[114],"enabling":[115],"more":[116],"chemically":[117],"coherent":[118],"predictions.":[119],"Comprehensive":[120],"evaluation":[121],"on":[122,135,139],"USPTO-50K":[123,136],"large-scale":[125],"USPTO-FULL":[126],"datasets":[127],"demonstrates":[128],"significant":[129],"improvements:":[130],"67.2":[131],"%":[132,143],"top-1":[133],"accuracy":[134],"50.8%":[138],"USPTO-FULL,":[140],"99.9":[142],"validity":[144],"generated":[146],"molecules.":[147],"This":[148],"work":[149],"establishes":[150],"paradigm":[153],"for":[154],"structure-aware":[155],"generation":[157],"direct":[159],"applications":[160],"computational":[162],"discovery.":[164]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-30T00:00:00"}