{"id":"https://openalex.org/W4200030022","doi":"https://doi.org/10.1021/acs.jcim.1c01192","title":"Influence of Template Size, Canonicalization, and Exclusivity for Retrosynthesis and Reaction Prediction Applications","display_name":"Influence of Template Size, Canonicalization, and Exclusivity for Retrosynthesis and Reaction Prediction Applications","publication_year":2021,"publication_date":"2021-12-23","ids":{"openalex":"https://openalex.org/W4200030022","doi":"https://doi.org/10.1021/acs.jcim.1c01192","pmid":"https://pubmed.ncbi.nlm.nih.gov/34939786"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.1c01192","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1021/acs.jcim.1c01192","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018855407","display_name":"Esther Heid","orcid":"https://orcid.org/0000-0002-8404-6596"},"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":"Esther Heid","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States"],"raw_orcid":"https://orcid.org/0000-0002-8404-6596","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000593851","display_name":"Jiannan Liu","orcid":"https://orcid.org/0000-0003-4164-6812"},"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":"Jiannan Liu","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022571058","display_name":"Andrea Aude","orcid":null},"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":"Andrea Aude","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051475129","display_name":"William H. Green","orcid":"https://orcid.org/0000-0003-2603-9694"},"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":"William H. Green","raw_affiliation_strings":["Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States"],"raw_orcid":"https://orcid.org/0000-0003-2603-9694","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02\u2009139, United States","institution_ids":["https://openalex.org/I63966007"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051475129"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":1.3248,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.79191892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"62","issue":"1","first_page":"16","last_page":"26"},"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":0.9994000196456909,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9767000079154968,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.9305825233459473},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7362158298492432},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.734531819820404},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.704700231552124},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.6855030655860901},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6434839963912964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5375885963439941},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5222945213317871},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48192524909973145},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.43568509817123413},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.42073023319244385},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.41296589374542236},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1315036416053772}],"concepts":[{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.9305825233459473},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362158298492432},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.734531819820404},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.704700231552124},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.6855030655860901},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6434839963912964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5375885963439941},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5222945213317871},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48192524909973145},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.43568509817123413},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.42073023319244385},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41296589374542236},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1315036416053772},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000066506","descriptor_name":"Heuristics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003201","descriptor_name":"Computers","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1021/acs.jcim.1c01192","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:34939786","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34939786","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},{"id":"pmh:oai:dspace.mit.edu:1721.1/138894.2","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/138894.2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400425","display_name":"DSpace@MIT (Massachusetts Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I63966007","host_organization_name":"Massachusetts Institute of Technology","host_organization_lineage":["https://openalex.org/I63966007"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACS","raw_type":"Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8757433","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8757433","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Chem Inf Model","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1021/acs.jcim.1c01192","is_oa":true,"landing_page_url":"https://doi.org/10.1021/acs.jcim.1c01192","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G1514665075","display_name":null,"funder_award_id":"J-4415","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"}],"funders":[{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1990600049","https://openalex.org/W2011018037","https://openalex.org/W2038702914","https://openalex.org/W2044834685","https://openalex.org/W2060586571","https://openalex.org/W2101451020","https://openalex.org/W2128148743","https://openalex.org/W2325811289","https://openalex.org/W2405035126","https://openalex.org/W2409645877","https://openalex.org/W2580919858","https://openalex.org/W2606363443","https://openalex.org/W2621742623","https://openalex.org/W2622979832","https://openalex.org/W2769423117","https://openalex.org/W2769756736","https://openalex.org/W2903262661","https://openalex.org/W2944975820","https://openalex.org/W2945996271","https://openalex.org/W2947722296","https://openalex.org/W2950955377","https://openalex.org/W2951311167","https://openalex.org/W2963675331","https://openalex.org/W2963969340","https://openalex.org/W2966357564","https://openalex.org/W2972608805","https://openalex.org/W2987091515","https://openalex.org/W2991279511","https://openalex.org/W2991310815","https://openalex.org/W2994678679","https://openalex.org/W3009202547","https://openalex.org/W3036578548","https://openalex.org/W3088265803","https://openalex.org/W3094771832","https://openalex.org/W3101155908","https://openalex.org/W3111883182","https://openalex.org/W3181403764","https://openalex.org/W4285670373","https://openalex.org/W6600882715","https://openalex.org/W6605656274","https://openalex.org/W6609581451"],"related_works":["https://openalex.org/W4387596259","https://openalex.org/W4296525969","https://openalex.org/W4221161859","https://openalex.org/W3036578548","https://openalex.org/W4200030022","https://openalex.org/W4233141470","https://openalex.org/W3095314085","https://openalex.org/W3210545473","https://openalex.org/W4200259295","https://openalex.org/W4229893050"],"abstract_inverted_index":{"Heuristic":[0],"and":[1,21,32,45,49,66,85,99,125,145,151,164,179],"machine":[2,165],"learning":[3,166],"models":[4],"for":[5,13,58,161],"rank-ordering":[6],"reaction":[7,44],"templates":[8,103,132],"comprise":[9],"an":[10],"important":[11],"basis":[12],"computer-aided":[14],"organic":[15],"synthesis":[16],"regarding":[17],"both":[18,118,162],"product":[19],"prediction":[20],"retrosynthetic":[22,174],"pathway":[23],"planning.":[24],"Their":[25],"viability":[26],"relies":[27],"heavily":[28],"on":[29,87,110],"the":[30,35,40,51,68,79,88,106,119,122,126,129,136],"quality":[31,69],"characteristics":[33],"of":[34,42,53,70,81,90,115,121,128,139],"underlying":[36],"template":[37,46,54,71,82,92,167],"database.":[38],"With":[39],"advent":[41],"automated":[43],"extraction":[47],"software":[48],"consequently":[50],"creation":[52],"databases":[55],"too":[56],"large":[57],"manual":[59],"curation,":[60],"a":[61,143,156],"data-driven":[62],"approach":[63],"to":[64,149],"assess":[65],"improve":[67],"sets":[72,114],"is":[73,182],"needed.":[74],"We":[75,95],"therefore":[76],"systematically":[77],"studied":[78],"influence":[80],"generality,":[83],"canonicalization,":[84],"exclusivity":[86],"performance":[89,158],"different":[91],"ranking":[93,123,168],"models.":[94,176],"find":[96],"that":[97],"duplicate":[98],"nonexclusive":[100],"templates,":[101],"i.e.,":[102],"which":[104],"describe":[105],"same":[107],"chemical":[108],"transformation":[109],"identical":[111],"or":[112],"overlapping":[113],"molecules,":[116],"decrease":[117],"accuracy":[120],"algorithm":[124],"applicability":[127],"respective":[130],"top-ranked":[131],"significantly.":[133],"To":[134],"remedy":[135],"negative":[137],"effects":[138],"nonexclusivity,":[140],"we":[141],"developed":[142],"general":[144],"computationally":[146],"efficient":[147],"framework":[148],"deduplicate":[150],"hierarchically":[152],"correct":[153],"templates.":[154],"As":[155],"result,":[157],"improved":[159],"considerably":[160],"heuristic":[163],"models,":[169],"as":[170,172],"well":[171],"multistep":[173],"planning":[175],"The":[177],"canonicalization":[178],"correction":[180],"code":[181],"made":[183],"freely":[184],"available.":[185]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
