{"id":"https://openalex.org/W4353014847","doi":"https://doi.org/10.1021/acs.jcim.2c01302","title":"G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training","display_name":"G2GT: Retrosynthesis Prediction with Graph-to-Graph Attention Neural Network and Self-Training","publication_year":2023,"publication_date":"2023-03-22","ids":{"openalex":"https://openalex.org/W4353014847","doi":"https://doi.org/10.1021/acs.jcim.2c01302","pmid":"https://pubmed.ncbi.nlm.nih.gov/36946514"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c01302","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01302","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5025545438","display_name":"Zaiyun Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zaiyun Lin","raw_affiliation_strings":["Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089"],"affiliations":[{"raw_affiliation_string":"Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046861536","display_name":"Shiqiu Yin","orcid":"https://orcid.org/0000-0001-8125-0367"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiqiu Yin","raw_affiliation_strings":["Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089"],"affiliations":[{"raw_affiliation_string":"Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039118568","display_name":"Lei Shi","orcid":"https://orcid.org/0000-0001-6012-7810"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Shi","raw_affiliation_strings":["Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089"],"affiliations":[{"raw_affiliation_string":"Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100524959","display_name":"Wenbiao Zhou","orcid":"https://orcid.org/0000-0001-8277-2765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenbiao Zhou","raw_affiliation_strings":["Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089"],"affiliations":[{"raw_affiliation_string":"Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070861971","display_name":"Yingsheng Zhang","orcid":"https://orcid.org/0000-0003-2520-3923"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yingsheng John Zhang","raw_affiliation_strings":["Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089"],"affiliations":[{"raw_affiliation_string":"Stone Wise, Room 918, Eighth Floor, Building 1, No. 6 Danling Street, Haidian District, Beijing, China 100089","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5025545438"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.3373,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.8876741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"63","issue":"7","first_page":"1894","last_page":"1905"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9986000061035156,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9789000153541565,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/computer-science","display_name":"Computer science","score":0.7480944395065308},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.6761487126350403},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5930263996124268},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.568438708782196},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5349757671356201},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5149043798446655},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4827129542827606},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4654237926006317},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44925034046173096},{"id":"https://openalex.org/keywords/molecular-graph","display_name":"Molecular graph","score":0.4413524866104126},{"id":"https://openalex.org/keywords/data-sampling","display_name":"Data sampling","score":0.4116228520870209},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37385016679763794},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.32614946365356445}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7480944395065308},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.6761487126350403},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5930263996124268},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.568438708782196},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349757671356201},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5149043798446655},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4827129542827606},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4654237926006317},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44925034046173096},{"id":"https://openalex.org/C2780022179","wikidata":"https://www.wikidata.org/wiki/Q1986794","display_name":"Molecular graph","level":3,"score":0.4413524866104126},{"id":"https://openalex.org/C2985946229","wikidata":"https://www.wikidata.org/wiki/Q49908","display_name":"Data sampling","level":2,"score":0.4116228520870209},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37385016679763794},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.32614946365356445},{"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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007858","descriptor_name":"Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011211","descriptor_name":"Electric Power Supplies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.2c01302","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c01302","pdf_url":null,"source":{"id":"https://openalex.org/S167262187","display_name":"Journal of Chemical Information and Modeling","issn_l":"1549-9596","issn":["1549-9596","1549-960X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320006","host_organization_name":"American Chemical Society","host_organization_lineage":["https://openalex.org/P4310320006"],"host_organization_lineage_names":["American Chemical Society"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:36946514","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36946514","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 chemical information and modeling","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1975147762","https://openalex.org/W2001496974","https://openalex.org/W2020996919","https://openalex.org/W2064535969","https://openalex.org/W2481382694","https://openalex.org/W2580919858","https://openalex.org/W2606363443","https://openalex.org/W2621742623","https://openalex.org/W2766164908","https://openalex.org/W2797884766","https://openalex.org/W2938704169","https://openalex.org/W2950079015","https://openalex.org/W2972608805","https://openalex.org/W2981452123","https://openalex.org/W2994678679","https://openalex.org/W3005552578","https://openalex.org/W3045208635","https://openalex.org/W3088265803","https://openalex.org/W3094771832","https://openalex.org/W3113177135","https://openalex.org/W3152975457","https://openalex.org/W3177828909","https://openalex.org/W3181403764","https://openalex.org/W3189262114","https://openalex.org/W4221161859","https://openalex.org/W4287237978","https://openalex.org/W4287829537","https://openalex.org/W4297733535"],"related_works":["https://openalex.org/W4385784498","https://openalex.org/W3013312987","https://openalex.org/W3034926403","https://openalex.org/W2965165771","https://openalex.org/W3174318304","https://openalex.org/W2135107501","https://openalex.org/W3176905117","https://openalex.org/W4353014847","https://openalex.org/W4211047554","https://openalex.org/W2108225227"],"abstract_inverted_index":{"Retrosynthesis":[0],"prediction,":[1],"the":[2,43,56,71,74,115,126,137],"task":[3],"of":[4,58,73,134,148],"identifying":[5],"reactant":[6],"molecules":[7],"that":[8,64],"can":[9,156],"be":[10,158],"used":[11],"to":[12,103,113,160],"synthesize":[13],"product":[14],"molecules,":[15],"is":[16,40,111],"a":[17,32,60,82,131,145],"fundamental":[18],"challenge":[19],"in":[20,69],"organic":[21],"chemistry":[22],"and":[23,47,51,90,100,136,150,167],"related":[24],"fields.":[25],"To":[26,76],"address":[27],"this":[28],"challenge,":[29],"we":[30,54,80],"propose":[31,81],"novel":[33],"graph-to-graph":[34,163],"transformation":[35,164],"model,":[36],"G2GT.":[37],"The":[38],"model":[39,155],"built":[41],"on":[42,124],"standard":[44],"transformer":[45],"structure":[46],"utilizes":[48,65],"graph":[49],"encoders":[50],"decoders.":[52],"Additionally,":[53],"demonstrate":[55],"effectiveness":[57],"self-training,":[59],"data":[61,128,142],"augmentation":[62],"technique":[63],"unlabeled":[66],"molecular":[67],"data,":[68],"improving":[70],"performance":[72],"model.":[75],"further":[77],"enhance":[78],"diversity,":[79],"weak":[83],"ensemble":[84,91],"method,":[85],"inspired":[86],"by":[87],"reaction-type":[88],"labels":[89],"learning.":[92],"This":[93],"method":[94],"incorporates":[95],"beam":[96],"search,":[97],"nucleus":[98],"sampling,":[99],"top-<i>k</i>":[101],"sampling":[102],"improve":[104],"inference":[105],"diversity.":[106],"A":[107],"simple":[108],"ranking":[109],"algorithm":[110],"employed":[112],"retrieve":[114],"final":[116],"top-10":[117,152],"results.":[118,153],"We":[119],"achieved":[120],"new":[121],"state-of-the-art":[122],"results":[123],"both":[125],"USPTO-50K":[127],"set,":[129,143],"with":[130,144],"top-1":[132,146],"accuracy":[133,147],"54%,":[135],"larger":[138],"more":[139],"challenging":[140],"USPTO-Full":[141],"49.3%":[149],"competitive":[151],"Our":[154],"also":[157],"generalized":[159],"all":[161],"other":[162],"tasks.":[165],"Data":[166],"code":[168],"are":[169],"available":[170],"at":[171],"https://github.com/Anonnoname/G2GT_2.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}