{"id":"https://openalex.org/W1973166400","doi":"https://doi.org/10.1021/ci200207y","title":"Learning to Predict Chemical Reactions","display_name":"Learning to Predict Chemical Reactions","publication_year":2011,"publication_date":"2011-08-07","ids":{"openalex":"https://openalex.org/W1973166400","doi":"https://doi.org/10.1021/ci200207y","mag":"1973166400","pmid":"https://pubmed.ncbi.nlm.nih.gov/21819139"},"language":"en","primary_location":{"id":"doi:10.1021/ci200207y","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200207y","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/A5027582939","display_name":"Matthew A. Kayala","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew A. Kayala","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114376683","display_name":"Chlo\u00e9\u2010Agathe Azencott","orcid":"https://orcid.org/0000-0003-1003-301X"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chlo\u00e9-Agathe Azencott","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046725885","display_name":"Jonathan H. Chen","orcid":"https://orcid.org/0000-0002-4387-8740"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan H. Chen","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088813478","display_name":"Pierre Baldi","orcid":"https://orcid.org/0000-0001-8752-4664"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pierre Baldi","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California, Irvine, California, United States","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088813478"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":4.7861,"has_fulltext":false,"cited_by_count":211,"citation_normalized_percentile":{"value":0.95206462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"51","issue":"9","first_page":"2209","last_page":"2222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9700999855995178,"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"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9700999855995178,"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/T12327","display_name":"Various Chemistry Research Topics","score":0.944599986076355,"subfield":{"id":"https://openalex.org/subfields/1606","display_name":"Physical and Theoretical Chemistry"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14470","display_name":"Advanced Data Processing Techniques","score":0.9444000124931335,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.38508468866348267},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.37728163599967957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.38508468866348267},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.37728163599967957}],"mesh":[{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002625","descriptor_name":"Chemistry, Organic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002625","descriptor_name":"Chemistry, Organic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002625","descriptor_name":"Chemistry, Organic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D002625","descriptor_name":"Chemistry, Organic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014584","descriptor_name":"User-Computer Interface","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci200207y","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci200207y","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:21819139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21819139","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:europepmc.org:2449774","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3193800","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1019976798","display_name":null,"funder_award_id":"R01 LM010235","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G2909942553","display_name":null,"funder_award_id":"LM010235","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G573371824","display_name":null,"funder_award_id":"T15 LM07443","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"},{"id":"https://openalex.org/G6622250571","display_name":null,"funder_award_id":"T15 LM007443","funder_id":"https://openalex.org/F4320337372","funder_display_name":"U.S. National Library of Medicine"}],"funders":[{"id":"https://openalex.org/F4320337372","display_name":"U.S. National Library of Medicine","ror":"https://ror.org/0060t0j89"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W10340167","https://openalex.org/W1492040047","https://openalex.org/W1502429606","https://openalex.org/W1508113248","https://openalex.org/W1527894967","https://openalex.org/W1548551133","https://openalex.org/W1563124950","https://openalex.org/W1584535387","https://openalex.org/W1680392829","https://openalex.org/W1966376777","https://openalex.org/W1977485766","https://openalex.org/W1980397420","https://openalex.org/W1987470703","https://openalex.org/W2008517160","https://openalex.org/W2034321566","https://openalex.org/W2035031507","https://openalex.org/W2040010296","https://openalex.org/W2044300739","https://openalex.org/W2046747992","https://openalex.org/W2047221353","https://openalex.org/W2058475745","https://openalex.org/W2067087023","https://openalex.org/W2069870183","https://openalex.org/W2085276885","https://openalex.org/W2089777445","https://openalex.org/W2091620265","https://openalex.org/W2093205000","https://openalex.org/W2105966118","https://openalex.org/W2109455667","https://openalex.org/W2115902930","https://openalex.org/W2122427541","https://openalex.org/W2127437840","https://openalex.org/W2138689719","https://openalex.org/W2142170650","https://openalex.org/W2143331230","https://openalex.org/W2156332942","https://openalex.org/W2162546656","https://openalex.org/W2167277498","https://openalex.org/W2176720124","https://openalex.org/W2200810672","https://openalex.org/W2317130155","https://openalex.org/W2326374312","https://openalex.org/W2330433584","https://openalex.org/W2500833725","https://openalex.org/W2608239929","https://openalex.org/W2951479592","https://openalex.org/W2952769273","https://openalex.org/W2988119488","https://openalex.org/W4205530682","https://openalex.org/W4236355931","https://openalex.org/W4251903194","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W2948807893","https://openalex.org/W2778153218","https://openalex.org/W2748952813","https://openalex.org/W1531601525","https://openalex.org/W4391375266","https://openalex.org/W2078814861","https://openalex.org/W2527526854","https://openalex.org/W1976181487","https://openalex.org/W1986764834"],"abstract_inverted_index":{"Being":[0],"able":[1],"to":[2,12,21,67,75,212,236,271,304],"predict":[3],"the":[4,13,22,187,192,250,256,260,264,268,274,277,283,295,305,321],"course":[5],"of":[6,17,98,125,169,174,215,228,233,252,267,273],"arbitrary":[7],"chemical":[8],"reactions":[9,92,129,217],"is":[10,285,312],"essential":[11],"theory":[14],"and":[15,41,61,65,102,105,135,143,171,292],"applications":[16],"organic":[18],"chemistry.":[19],"Approaches":[20],"reaction":[23,76,310],"prediction":[24,77],"problems":[25],"can":[26],"be":[27,68],"organized":[28],"around":[29],"three":[30],"poles":[31],"corresponding":[32],"to:":[33],"(1)":[34],"physical":[35],"laws;":[36],"(2)":[37],"rule-based":[38,113,296],"expert":[39,297],"systems;":[40],"(3)":[42],"inductive":[43],"machine":[44,151,196,306],"learning.":[45],"Previous":[46],"approaches":[47],"at":[48,263],"these":[49],"poles,":[50],"respectively,":[51],"are":[52,56,280],"not":[53,57,299],"high":[54],"throughput,":[55],"generalizable":[58],"or":[59],"scalable,":[60],"lack":[62],"sufficient":[63],"data":[64,122],"structure":[66],"implemented.":[69],"We":[70],"propose":[71],"a":[72,84,119,160,167,172,177,200,219,238,246],"new":[73],"approach":[74],"utilizing":[78],"elements":[79],"from":[80,150],"each":[81],"pole.":[82],"Using":[83,110],"physically":[85],"inspired":[86],"conceptualization,":[87],"we":[88,117,153,205,224],"describe":[89],"single":[90],"mechanistic":[91,141,147,157,189,243,309],"as":[93,108,159],"interactions":[94,184],"between":[95],"coarse":[96],"approximations":[97],"molecular":[99],"orbitals":[100],"(MOs)":[101],"use":[103,251],"topological":[104],"physicochemical":[106],"attributes":[107],"descriptors.":[109],"an":[111,226],"existing":[112],"system":[114,284],"(Reaction":[115],"Explorer),":[116],"derive":[118],"restricted":[120],"chemistry":[121],"set":[123,168],"consisting":[124],"1630":[126],"full":[127],"multistep":[128],"with":[130,138,218],"2358":[131],"distinct":[132],"starting":[133],"materials":[134],"intermediates,":[136],"associated":[137],"2989":[139],"productive":[140,156,261],"steps":[142,158,190,244],"6.14":[144],"million":[145],"unproductive":[146],"steps.":[148],"And":[149],"learning,":[152],"pose":[154],"identifying":[155],"statistical":[161],"ranking,":[162],"information":[163],"retrieval":[164],"problem:":[165],"given":[166,247],"reactants":[170,291],"description":[173],"conditions,":[175],"learn":[176,237],"ranking":[178,229],"model":[179],"over":[180,242,290],"potential":[181],"filled-to-unfilled":[182],"MO":[183],"such":[185],"that":[186],"top-ranked":[188],"yield":[191],"major":[193],"products.":[194],"The":[195],"learning":[197,307],"implementation":[198],"follows":[199],"two-stage":[201],"approach,":[202],"in":[203,245],"which":[204,294],"first":[206],"train":[207,225],"atom":[208],"level":[209],"reactivity":[210],"filters":[211],"prune":[213],"94.00%":[214],"nonproductive":[216],"0.01%":[220],"error":[221],"rate.":[222],"Then,":[223],"ensemble":[227,257],"models":[230],"on":[231],"pairs":[232],"interacting":[234],"MOs":[235],"relative":[239],"productivity":[240],"function":[241],"system.":[248],"Without":[249],"explicit":[253],"transformation":[254],"patterns,":[255],"perfectly":[258],"ranks":[259],"mechanism":[262],"top":[265,278],"89.05%":[266],"time,":[269],"rising":[270],"99.86%":[272],"time":[275],"when":[276],"four":[279],"considered.":[281],"Furthermore,":[282],"generalizable,":[286],"making":[287],"reasonable":[288],"predictions":[289],"conditions":[293],"does":[298],"handle.":[300],"A":[301],"web":[302],"interface":[303],"based":[308],"predictor":[311],"accessible":[313],"through":[314],"our":[315],"chemoinformatics":[316],"portal":[317],"(":[318],"http://cdb.ics.uci.edu)":[319],"under":[320],"Toolkits":[322],"section.":[323]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":38},{"year":2020,"cited_by_count":31},{"year":2019,"cited_by_count":17},{"year":2018,"cited_by_count":24},{"year":2017,"cited_by_count":19},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-23T06:36:01.041984","created_date":"2025-10-10T00:00:00"}
