{"id":"https://openalex.org/W4286901673","doi":"https://doi.org/10.1021/acs.jcim.2c00321","title":"Permutation Invariant Graph-to-Sequence Model for Template-Free Retrosynthesis and Reaction Prediction","display_name":"Permutation Invariant Graph-to-Sequence Model for Template-Free Retrosynthesis and Reaction Prediction","publication_year":2022,"publication_date":"2022-07-26","ids":{"openalex":"https://openalex.org/W4286901673","doi":"https://doi.org/10.1021/acs.jcim.2c00321","pmid":"https://pubmed.ncbi.nlm.nih.gov/35881916"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.2c00321","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00321","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":"review","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/A5087516855","display_name":"Zhengkai Tu","orcid":"https://orcid.org/0000-0003-1715-5773"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhengkai Tu","raw_affiliation_strings":["Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Computational Science and Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076162644","display_name":"Connor W. Coley","orcid":"https://orcid.org/0000-0002-8271-8723"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Connor W. Coley","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States"],"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5076162644"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":9.1506,"has_fulltext":false,"cited_by_count":133,"citation_normalized_percentile":{"value":0.99051884,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"62","issue":"15","first_page":"3503","last_page":"3513"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9941999912261963,"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/T10028","display_name":"Topic Modeling","score":0.9891999959945679,"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":0.7203415632247925},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.5876739025115967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5380162596702576},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5284379124641418},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.52084881067276},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.47494104504585266},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4391612112522125},{"id":"https://openalex.org/keywords/machine-translation","display_name":"Machine translation","score":0.43545931577682495},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33248481154441833}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7203415632247925},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.5876739025115967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5380162596702576},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5284379124641418},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.52084881067276},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.47494104504585266},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4391612112522125},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.43545931577682495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33248481154441833},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","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.2c00321","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.2c00321","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:35881916","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35881916","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W1490308602","https://openalex.org/W1560202902","https://openalex.org/W1975147762","https://openalex.org/W1988037271","https://openalex.org/W1995426752","https://openalex.org/W1997974358","https://openalex.org/W2010754031","https://openalex.org/W2058426370","https://openalex.org/W2064000318","https://openalex.org/W2157331557","https://openalex.org/W2324964582","https://openalex.org/W2580919858","https://openalex.org/W2621742623","https://openalex.org/W2769423117","https://openalex.org/W2769756736","https://openalex.org/W2892181857","https://openalex.org/W2903262661","https://openalex.org/W2910734083","https://openalex.org/W2913668833","https://openalex.org/W2947423323","https://openalex.org/W2947722296","https://openalex.org/W2950955377","https://openalex.org/W2963212250","https://openalex.org/W2963396480","https://openalex.org/W2964110616","https://openalex.org/W2966357564","https://openalex.org/W2970550739","https://openalex.org/W2970764640","https://openalex.org/W2994678679","https://openalex.org/W2999373911","https://openalex.org/W3009202547","https://openalex.org/W3088265803","https://openalex.org/W3094771832","https://openalex.org/W3103092523","https://openalex.org/W3119022334","https://openalex.org/W3138705992","https://openalex.org/W3152975457","https://openalex.org/W3174318304","https://openalex.org/W3175633940","https://openalex.org/W3181403764","https://openalex.org/W3189262114","https://openalex.org/W6601048975","https://openalex.org/W6605656274","https://openalex.org/W6609856777","https://openalex.org/W6618999356","https://openalex.org/W6631297034","https://openalex.org/W6635231071","https://openalex.org/W6828894009","https://openalex.org/W6851816929"],"related_works":["https://openalex.org/W3176018525","https://openalex.org/W2903533908","https://openalex.org/W3026554633","https://openalex.org/W2903810591","https://openalex.org/W4289548192","https://openalex.org/W2888520903","https://openalex.org/W2963499882","https://openalex.org/W2903399267","https://openalex.org/W2949454572","https://openalex.org/W3098873988"],"abstract_inverted_index":{"Synthesis":[0],"planning":[1],"and":[2,46,127,135,178],"reaction":[3,179],"outcome":[4,180],"prediction":[5],"are":[6,59],"two":[7],"fundamental":[8],"problems":[9],"in":[10,158],"computer-aided":[11],"organic":[12],"chemistry":[13],"for":[14,43,62,94,109,133,155,175],"which":[15,164],"a":[16,31,36,83,116,152],"variety":[17],"of":[18,50,73,91,101],"data-driven":[19],"approaches":[20,25],"have":[21],"emerged.":[22],"Natural":[23],"language":[24],"that":[26,87,105],"model":[27,54,86],"each":[28],"problem":[29],"as":[30,68,151],"SMILES-to-SMILES":[32],"translation":[33,53],"lead":[34],"to":[35,76,169],"simple":[37],"end-to-end":[38,145],"formulation,":[39],"reduce":[40],"the":[41,48,71,89,98,107,128,156],"need":[42,108],"data":[44,111],"preprocessing,":[45],"enable":[47],"use":[49],"well-optimized":[51],"machine":[52],"architectures.":[55],"However,":[56],"SMILES":[57,74],"representations":[58],"not":[60],"efficient":[61],"capturing":[63],"information":[64],"about":[65],"molecular":[66,102],"structures,":[67],"evidenced":[69],"by":[70,139],"success":[72],"augmentation":[75],"boost":[77],"empirical":[78],"performance.":[79],"Here,":[80],"we":[81,165],"describe":[82],"novel":[84],"Graph2SMILES":[85,147],"combines":[88],"power":[90],"Transformer":[92,157],"models":[93],"text":[95],"generation":[96],"with":[97],"permutation":[99],"invariance":[100],"graph":[103],"encoders":[104],"mitigates":[106],"input":[110],"augmentation.":[112],"In":[113],"our":[114],"encoder,":[115],"directed":[117],"message":[118],"passing":[119],"neural":[120],"network":[121],"(D-MPNN)":[122],"captures":[123],"local":[124],"chemical":[125],"environments,":[126],"global":[129],"attention":[130],"encoder":[131],"allows":[132],"long-range":[134],"intermolecular":[136],"interactions,":[137],"enhanced":[138],"graph-aware":[140],"positional":[141],"embedding.":[142],"As":[143],"an":[144],"architecture,":[146],"can":[148],"be":[149],"used":[150],"drop-in":[153],"replacement":[154],"any":[159],"task":[160],"involving":[161],"molecule(s)-to-molecule(s)":[162],"transformations,":[163],"empirically":[166],"demonstrate":[167],"leads":[168],"improved":[170],"performance":[171],"on":[172],"existing":[173],"benchmarks":[174],"both":[176],"retrosynthesis":[177],"prediction.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":49},{"year":2024,"cited_by_count":40},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":8}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}