{"id":"https://openalex.org/W3036578548","doi":"https://doi.org/10.1021/acs.jcim.0c00403","title":"Data Augmentation and Pretraining for Template-Based Retrosynthetic Prediction in Computer-Aided Synthesis Planning","display_name":"Data Augmentation and Pretraining for Template-Based Retrosynthetic Prediction in Computer-Aided Synthesis Planning","publication_year":2020,"publication_date":"2020-06-22","ids":{"openalex":"https://openalex.org/W3036578548","doi":"https://doi.org/10.1021/acs.jcim.0c00403","mag":"3036578548","pmid":"https://pubmed.ncbi.nlm.nih.gov/32568548"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.0c00403","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00403","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":true,"oa_status":"green","oa_url":"https://hdl.handle.net/1721.1/134636","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066151949","display_name":"Michael Fortunato","orcid":"https://orcid.org/0000-0003-1344-5642"},"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":"Michael E. Fortunato","raw_affiliation_strings":["Department of Chemical Engineering, 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"]}]},{"author_position":"middle","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":false,"raw_author_name":"Connor W. Coley","raw_affiliation_strings":["Department of Chemical Engineering, 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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028204979","display_name":"Brian C. Barnes","orcid":"https://orcid.org/0000-0002-2756-3554"},"institutions":[{"id":"https://openalex.org/I166416128","display_name":"DEVCOM Army Research Laboratory","ror":"https://ror.org/011hc8f90","country_code":"US","type":"government","lineage":["https://openalex.org/I1304082316","https://openalex.org/I1330347796","https://openalex.org/I166416128","https://openalex.org/I2802705668","https://openalex.org/I4210154437"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian C. Barnes","raw_affiliation_strings":["Detonation Science and Modeling Branch, CCDC Army Research Laboratory, Aberdeen Proving Ground, Maryland 21005, United States"],"affiliations":[{"raw_affiliation_string":"Detonation Science and Modeling Branch, CCDC Army Research Laboratory, Aberdeen Proving Ground, Maryland 21005, United States","institution_ids":["https://openalex.org/I166416128"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071010920","display_name":"Klavs F. Jensen","orcid":"https://orcid.org/0000-0001-7192-580X"},"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":"Klavs F. Jensen","raw_affiliation_strings":["Department of Chemical Engineering, 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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066151949"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":3.9768,"has_fulltext":false,"cited_by_count":82,"citation_normalized_percentile":{"value":0.95058526,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"60","issue":"7","first_page":"3398","last_page":"3407"},"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":0.9979000091552734,"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":0.9348000288009644,"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/template","display_name":"Template","score":0.9053742289543152},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7816060781478882},{"id":"https://openalex.org/keywords/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.701850414276123},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6438932418823242},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6199931502342224},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.615250825881958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5319212675094604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5212802886962891},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.48865941166877747},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.48375701904296875},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4651193618774414},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4541151523590088},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3942629098892212},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14774003624916077}],"concepts":[{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.9053742289543152},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7816060781478882},{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.701850414276123},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6438932418823242},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6199931502342224},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.615250825881958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5319212675094604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5212802886962891},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.48865941166877747},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.48375701904296875},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4651193618774414},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4541151523590088},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3942629098892212},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14774003624916077},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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":"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":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":"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},{"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":4,"locations":[{"id":"doi:10.1021/acs.jcim.0c00403","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.0c00403","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:32568548","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32568548","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:1721.1/134636","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/134636","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Other repository","raw_type":"http://purl.org/eprint/type/JournalArticle"},{"id":"pmh:oai:figshare.com:article/12612363","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Data_Augmentation_and_Pretraining_for_Template-Based_Retrosynthetic_Prediction_in_Computer-Aided_Synthesis_Planning/12612363","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:dspace.mit.edu:1721.1/134636","is_oa":true,"landing_page_url":"https://hdl.handle.net/1721.1/134636","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-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Other repository","raw_type":"http://purl.org/eprint/type/JournalArticle"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2698530835","display_name":null,"funder_award_id":"W911NF19-2-0034","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"}],"funders":[{"id":"https://openalex.org/F4320332201","display_name":"Office of the Secretary of Defense","ror":"https://ror.org/00q4sx826"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W29374554","https://openalex.org/W325368666","https://openalex.org/W604459335","https://openalex.org/W1560865569","https://openalex.org/W1975147762","https://openalex.org/W1979651826","https://openalex.org/W2044834685","https://openalex.org/W2060586571","https://openalex.org/W2095705004","https://openalex.org/W2580919858","https://openalex.org/W2621742623","https://openalex.org/W2747592475","https://openalex.org/W2769756736","https://openalex.org/W2809598685","https://openalex.org/W2947722296","https://openalex.org/W2950079015","https://openalex.org/W2950377709","https://openalex.org/W2950955377","https://openalex.org/W2968071222","https://openalex.org/W2972608805","https://openalex.org/W2987091515","https://openalex.org/W2991279511","https://openalex.org/W2991310815","https://openalex.org/W3009202547","https://openalex.org/W3010111948","https://openalex.org/W3010145447","https://openalex.org/W3023658436","https://openalex.org/W3202507447","https://openalex.org/W4393502349"],"related_works":["https://openalex.org/W4387596259","https://openalex.org/W4296525969","https://openalex.org/W4221161859","https://openalex.org/W4200030022","https://openalex.org/W3036578548","https://openalex.org/W4233141470","https://openalex.org/W3095314085","https://openalex.org/W2786391746","https://openalex.org/W3210545473","https://openalex.org/W2991483587"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"efforts":[3],"to":[4,28,55,80,155],"augment":[5],"the":[6,30,46,56,60,86,124,132,143,171],"performance":[7],"of":[8,32,49,99,134,149,168],"data-driven":[9],"machine":[10,24,73],"learning":[11,25,74],"algorithms":[12],"for":[13,45,69,158,185,196],"reaction":[14,34,53,87],"template":[15,57,105,125],"recommendation":[16],"used":[17],"in":[18,52,71,85,123,131,178,181],"computer-aided":[19],"synthesis":[20],"planning":[21],"software.":[22],"Often,":[23],"models":[26,75],"designed":[27],"perform":[29],"task":[31],"prioritizing":[33],"templates":[35,65,150],"or":[36],"molecular":[37],"transformations":[38],"are":[39],"focused":[40],"on":[41,113,163],"reporting":[42],"high-accuracy":[43],"metrics":[44],"one-to-one":[47],"mapping":[48],"product":[50],"molecules":[51],"databases":[54,88],"extracted":[58],"from":[59],"recorded":[61],"reaction.":[62],"The":[63,137],"available":[64],"that":[66,82,151,189],"get":[67],"selected":[68],"inclusion":[70],"these":[72,190],"have":[76],"been":[77],"previously":[78],"limited":[79],"those":[81],"appear":[83],"frequently":[84],"and":[89,107,128,139,174],"exclude":[90],"potentially":[91],"useful":[92,195],"transformations.":[93],"By":[94],"augmenting":[95],"open-access":[96],"data":[97,117,166,172,198],"sets":[98],"organic":[100],"reactions":[101,157],"with":[102],"explicitly":[103],"calculated":[104],"applicability":[106,116,126],"pretraining":[108,140,175],"a":[109,159,164],"template-relevance":[110],"neural":[111,144],"network":[112,145],"this":[114],"augmented":[115],"set,":[118],"we":[119],"report":[120],"an":[121,129,146,179],"increase":[122,130,180],"recall":[127],"diversity":[133],"predicted":[135],"precursors.":[136],"augmentation":[138,173],"effectively":[141],"teaches":[142],"increased":[147],"set":[148,167],"could":[152],"theoretically":[153],"lead":[154],"successful":[156],"given":[160],"target.":[161],"Even":[162],"small":[165,197],"well-curated":[169],"reactions,":[170],"methods":[176],"resulted":[177],"top-1":[182],"accuracy,":[183],"especially":[184],"rare":[186],"templates,":[187],"indicating":[188],"strategies":[191],"can":[192],"be":[193],"very":[194],"sets.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":13},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}