{"id":"https://openalex.org/W2910734083","doi":"https://doi.org/10.1021/acs.jcim.8b00801","title":"Enhancing Retrosynthetic Reaction Prediction with Deep Learning Using Multiscale Reaction Classification","display_name":"Enhancing Retrosynthetic Reaction Prediction with Deep Learning Using Multiscale Reaction Classification","publication_year":2019,"publication_date":"2019-01-14","ids":{"openalex":"https://openalex.org/W2910734083","doi":"https://doi.org/10.1021/acs.jcim.8b00801","mag":"2910734083","pmid":"https://pubmed.ncbi.nlm.nih.gov/30642173"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00801","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00801","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/A5026626873","display_name":"Javier L. Baylon","orcid":"https://orcid.org/0000-0003-1802-8450"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Javier L. Baylon","raw_affiliation_strings":["Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States"],"raw_orcid":"https://orcid.org/0000-0003-1802-8450","affiliations":[{"raw_affiliation_string":"Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","institution_ids":[]},{"raw_affiliation_string":"Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007229926","display_name":"Nicholas A. Cilfone","orcid":"https://orcid.org/0000-0002-6490-4418"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nicholas A. Cilfone","raw_affiliation_strings":["Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","institution_ids":[]},{"raw_affiliation_string":"Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108091007","display_name":"Jeffrey R. Gulcher","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I4210145812","display_name":"Cancer Genetics (United States)","ror":"https://ror.org/05feyya22","country_code":"US","type":"company","lineage":["https://openalex.org/I4210145812"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey R. Gulcher","raw_affiliation_strings":["Cancer Genetics Group, WuXi NextCODE, Cambridge, Massachusetts 02142, United States","Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cancer Genetics Group, WuXi NextCODE, Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I4210145812"]},{"raw_affiliation_string":"Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088313695","display_name":"Thomas W. Chittenden","orcid":"https://orcid.org/0000-0002-4414-0262"},"institutions":[{"id":"https://openalex.org/I1288882113","display_name":"Boston Children's Hospital","ror":"https://ror.org/00dvg7y05","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1288882113"]},{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Thomas W. Chittenden","raw_affiliation_strings":["Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE, Cambridge, Massachusetts 02142, United States","Division of Genetics and Genomics, Boston Children\u2019s Hospital, Harvard Medical School, Boston, Massachusetts 02215, United States","Division of Genetics and Genomics, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts 02215, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Complex Biological Systems Alliance, Medford, Massachusetts 02155, United States","institution_ids":[]},{"raw_affiliation_string":"Computational Statistics and Bioinformatics Group, Advanced Artificial Intelligence Research Laboratory, WuXi NextCODE, Cambridge, Massachusetts 02142, United States","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"Division of Genetics and Genomics, Boston Children\u2019s Hospital, Harvard Medical School, Boston, Massachusetts 02215, United States","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]},{"raw_affiliation_string":"Division of Genetics and Genomics, Boston Children's Hospital, Harvard Medical School, Boston, Massachusetts 02215, United States","institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I136199984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088313695"],"corresponding_institution_ids":["https://openalex.org/I1288882113","https://openalex.org/I1343180700","https://openalex.org/I136199984"],"apc_list":null,"apc_paid":null,"fwci":13.1111,"has_fulltext":false,"cited_by_count":117,"citation_normalized_percentile":{"value":0.9906997,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"59","issue":"2","first_page":"673","last_page":"688"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998999834060669,"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":0.9998999834060669,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9994000196456909,"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/T10911","display_name":"Chemical Synthesis and Analysis","score":0.9750999808311462,"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/retrosynthetic-analysis","display_name":"Retrosynthetic analysis","score":0.9940318465232849},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5704402327537537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5623400807380676},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5084737539291382},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4465482234954834},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4435674846172333},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.32122603058815}],"concepts":[{"id":"https://openalex.org/C42437451","wikidata":"https://www.wikidata.org/wiki/Q902227","display_name":"Retrosynthetic analysis","level":3,"score":0.9940318465232849},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5704402327537537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623400807380676},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5084737539291382},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4465482234954834},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4435674846172333},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.32122603058815},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C35753019","wikidata":"https://www.wikidata.org/wiki/Q644785","display_name":"Total synthesis","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D000080911","descriptor_name":"Cheminformatics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010330","descriptor_name":"Patents as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060326","descriptor_name":"Chemistry Techniques, Synthetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060326","descriptor_name":"Chemistry Techniques, Synthetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D060326","descriptor_name":"Chemistry Techniques, Synthetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.8b00801","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00801","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:30642173","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30642173","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":68,"referenced_works":["https://openalex.org/W1665214252","https://openalex.org/W1947322855","https://openalex.org/W1964326237","https://openalex.org/W1972052186","https://openalex.org/W1975147762","https://openalex.org/W1979641548","https://openalex.org/W1984994707","https://openalex.org/W1988037271","https://openalex.org/W1988080642","https://openalex.org/W1992858616","https://openalex.org/W1993953045","https://openalex.org/W1994811557","https://openalex.org/W1999881113","https://openalex.org/W2010703635","https://openalex.org/W2026265322","https://openalex.org/W2039840297","https://openalex.org/W2043995170","https://openalex.org/W2046344452","https://openalex.org/W2046747992","https://openalex.org/W2048983899","https://openalex.org/W2056701057","https://openalex.org/W2058290489","https://openalex.org/W2060586571","https://openalex.org/W2061903169","https://openalex.org/W2062601468","https://openalex.org/W2064000318","https://openalex.org/W2064535969","https://openalex.org/W2066412916","https://openalex.org/W2074515425","https://openalex.org/W2079571299","https://openalex.org/W2101807845","https://openalex.org/W2102521826","https://openalex.org/W2130244530","https://openalex.org/W2132842501","https://openalex.org/W2158835780","https://openalex.org/W2176412452","https://openalex.org/W2187089797","https://openalex.org/W2290847742","https://openalex.org/W2315058517","https://openalex.org/W2324964582","https://openalex.org/W2326892341","https://openalex.org/W2328708083","https://openalex.org/W2509639622","https://openalex.org/W2512660405","https://openalex.org/W2529996553","https://openalex.org/W2551217916","https://openalex.org/W2560467604","https://openalex.org/W2606363443","https://openalex.org/W2621742623","https://openalex.org/W2747592475","https://openalex.org/W2753921001","https://openalex.org/W2767891136","https://openalex.org/W2769756736","https://openalex.org/W2774977638","https://openalex.org/W2775684663","https://openalex.org/W2777416523","https://openalex.org/W2782636657","https://openalex.org/W2789615344","https://openalex.org/W2793371569","https://openalex.org/W2799620402","https://openalex.org/W2950621961","https://openalex.org/W2951427585","https://openalex.org/W2952525197","https://openalex.org/W3098269892","https://openalex.org/W3100157108","https://openalex.org/W3100545487","https://openalex.org/W3102693939","https://openalex.org/W4240234659"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W3046775127","https://openalex.org/W3107602296","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Chemical":[0],"synthesis":[1,36],"planning":[2],"is":[3,64],"a":[4,41,62,67,91,110,113,118,141,168,179,185,209,223,261,275],"key":[5],"aspect":[6],"in":[7,60,85,240,264,274],"many":[8],"fields":[9],"of":[10,17,71,98,101,124,188,212,218,236,277],"chemistry,":[11],"especially":[12],"drug":[13],"discovery.":[14],"Recent":[15],"implementations":[16],"machine":[18],"learning":[19],"and":[20,162,267],"artificial":[21,278],"intelligence":[22,279],"techniques":[23],"for":[24,35,45,154,272],"retrosynthetic":[25,46,81,151,195,265],"analysis":[26,47,266],"have":[27],"shown":[28],"great":[29],"potential":[30],"to":[31,94,108,133,139,230,249],"improve":[32],"computational":[33],"methods":[34],"planning.":[37],"Herein,":[38],"we":[39,89,147],"present":[40],"multiscale,":[42],"data-driven":[43],"approach":[44,183,229,246],"with":[48,167,227],"deep":[49],"highway":[50],"networks":[51],"(DHN).":[52],"We":[53,78],"automatically":[54],"extracted":[55],"reaction":[56,82,104,114,129,152,175,196,206,235],"rules":[57,176,207],"(i.e.,":[58],"ways":[59],"which":[61,96],"molecule":[63],"produced)":[65],"from":[66,75,194],"data":[68],"set":[69,217],"consisting":[70],"chemical":[72],"reactions":[73,99,125],"derived":[74],"U.S.":[76],"patents.":[77],"performed":[79],"the":[80,122,127,135,149,199,215,237],"prediction":[83],"task":[84],"two":[86],"steps:":[87],"first,":[88],"built":[90],"DHN":[92,119],"model":[93,161,170,201],"predict":[95,134],"group":[97,115],"(consisting":[100],"chemically":[102],"similar":[103],"rules)":[105],"was":[106,116,131,247],"employed":[107,132,177],"produce":[109,140],"molecule.":[111,142],"Once":[112],"identified,":[117],"trained":[120,171,202],"on":[121,172,203,214],"subset":[123],"within":[126],"identified":[128],"group,":[130],"transformation":[136],"rule":[137],"used":[138],"To":[143],"validate":[144],"our":[145,159,228,244],"approach,":[146],"predicted":[148],"first":[150,233],"step":[153],"40":[155,219],"approved":[156],"drugs":[157,239],"using":[158],"multiscale":[160,182,245,258],"compared":[163],"its":[164],"predictive":[165],"performance":[166],"conventional":[169],"all":[173,204],"machine-extracted":[174,205],"as":[178],"control.":[180],"Our":[181],"showed":[184],"success":[186,210],"rate":[187,211],"82.9%":[189],"at":[190],"generating":[191],"valid":[192],"reactants":[193],"predictions.":[197],"Comparatively,":[198],"control":[200],"yielded":[208],"58.5%":[213],"validation":[216],"pharmaceutical":[220],"molecules,":[221],"indicating":[222],"significant":[224],"statistical":[225],"improvement":[226],"match":[231],"known":[232],"synthetic":[234],"tested":[238],"this":[241],"study.":[242],"While":[243],"unable":[248],"outperform":[250],"state-of-the-art":[251],"rule-based":[252],"systems":[253],"curated":[254],"by":[255],"expert":[256],"chemists,":[257],"classification":[259],"represents":[260],"marked":[262],"enhancement":[263],"can":[268],"be":[269],"easily":[270],"adapted":[271],"use":[273],"range":[276],"strategies.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":17},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":16}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}