{"id":"https://openalex.org/W2060586571","doi":"https://doi.org/10.1021/ci5006614","title":"Development of a Novel Fingerprint for Chemical Reactions and Its Application to Large-Scale Reaction Classification and Similarity","display_name":"Development of a Novel Fingerprint for Chemical Reactions and Its Application to Large-Scale Reaction Classification and Similarity","publication_year":2014,"publication_date":"2014-12-26","ids":{"openalex":"https://openalex.org/W2060586571","doi":"https://doi.org/10.1021/ci5006614","mag":"2060586571","pmid":"https://pubmed.ncbi.nlm.nih.gov/25541888"},"language":"en","primary_location":{"id":"doi:10.1021/ci5006614","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci5006614","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/A5031496441","display_name":"Nadine Schneider","orcid":"https://orcid.org/0000-0001-5824-2764"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]},{"id":"https://openalex.org/I4400600974","display_name":"Novartis Institutes for BioMedical Research","ror":"https://ror.org/053gv2m95","country_code":null,"type":"funder","lineage":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Nadine Schneider","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021129795","display_name":"Daniel M. Lowe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel M. Lowe","raw_affiliation_strings":["NextMove Software, Ltd., Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge CB4 0EY, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NextMove Software, Ltd., Innovation Centre, Unit 23, Science Park, Milton Road, Cambridge CB4 0EY, United Kingdom","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064515321","display_name":"Roger A. Sayle","orcid":"https://orcid.org/0000-0003-0188-471X"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]},{"id":"https://openalex.org/I4400600974","display_name":"Novartis Institutes for BioMedical Research","ror":"https://ror.org/053gv2m95","country_code":null,"type":"funder","lineage":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Roger A. Sayle","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056808182","display_name":"Gregory A. Landrum","orcid":"https://orcid.org/0000-0001-6279-4481"},"institutions":[{"id":"https://openalex.org/I1283582996","display_name":"Novartis (Switzerland)","ror":"https://ror.org/02f9zrr09","country_code":"CH","type":"company","lineage":["https://openalex.org/I1283582996"]},{"id":"https://openalex.org/I4400600974","display_name":"Novartis Institutes for BioMedical Research","ror":"https://ror.org/053gv2m95","country_code":null,"type":"funder","lineage":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Gregory A. Landrum","raw_affiliation_strings":["Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Novartis Institutes for BioMedical Research, Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"]},{"raw_affiliation_string":"Novartis Institutes for BioMedical Research , Novartis Campus, 4002 Basel, Switzerland","institution_ids":["https://openalex.org/I1283582996"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056808182"],"corresponding_institution_ids":["https://openalex.org/I1283582996","https://openalex.org/I4400600974"],"apc_list":null,"apc_paid":null,"fwci":5.7176,"has_fulltext":false,"cited_by_count":216,"citation_normalized_percentile":{"value":0.9640515,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"55","issue":"1","first_page":"39","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9721999764442444,"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/python","display_name":"Python (programming language)","score":0.686896800994873},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6847774386405945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6142071485519409},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6118388772010803},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5773254632949829},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5569549798965454},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.486054927110672},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.48561254143714905},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4777635633945465},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4682377874851227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4152929186820984}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.686896800994873},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6847774386405945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6142071485519409},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6118388772010803},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5773254632949829},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5569549798965454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.486054927110672},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.48561254143714905},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4777635633945465},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4682377874851227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4152929186820984},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"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":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008956","descriptor_name":"Models, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055601","descriptor_name":"Organic Chemistry Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055601","descriptor_name":"Organic Chemistry Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D055601","descriptor_name":"Organic Chemistry Phenomena","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D062126","descriptor_name":"Databases, Chemical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/ci5006614","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci5006614","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:25541888","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/25541888","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:oak.novartis.com:24659","is_oa":false,"landing_page_url":"https://oak.novartis.com/24659/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400709","display_name":"The Novartis Repository (Novartis)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1283582996","host_organization_name":"Novartis (Switzerland)","host_organization_lineage":["https://openalex.org/I1283582996"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320307778","display_name":"Novartis","ror":"https://ror.org/02f9zrr09"},{"id":"https://openalex.org/F4320333796","display_name":"Novartis Institutes for BioMedical Research","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1483235123","https://openalex.org/W1547880691","https://openalex.org/W1966041739","https://openalex.org/W1969487950","https://openalex.org/W1975147762","https://openalex.org/W1984994707","https://openalex.org/W1987869189","https://openalex.org/W1988037271","https://openalex.org/W1999241626","https://openalex.org/W2002727413","https://openalex.org/W2008420299","https://openalex.org/W2016979469","https://openalex.org/W2020996919","https://openalex.org/W2021748110","https://openalex.org/W2026086065","https://openalex.org/W2040103915","https://openalex.org/W2044300739","https://openalex.org/W2056701057","https://openalex.org/W2096541451","https://openalex.org/W2101234009","https://openalex.org/W2116342920","https://openalex.org/W2126363023","https://openalex.org/W2130244530","https://openalex.org/W2277855841","https://openalex.org/W2911964244","https://openalex.org/W4210483668","https://openalex.org/W4301824020"],"related_works":["https://openalex.org/W3023169329","https://openalex.org/W4389470870","https://openalex.org/W2782165897","https://openalex.org/W1582950852","https://openalex.org/W4300438041","https://openalex.org/W2054104202","https://openalex.org/W2139703748","https://openalex.org/W2761254753","https://openalex.org/W1024825291","https://openalex.org/W2188981919"],"abstract_inverted_index":{"Fingerprint":[0],"methods":[1],"applied":[2,98],"to":[3,7,16,101,131,190],"molecules":[4],"have":[5,89],"proven":[6],"be":[8],"useful":[9],"for":[10,28,107,145,171,178],"similarity":[11,41,148],"determination":[12],"and":[13,31,39,57,59,180],"as":[14,48,183,185],"inputs":[15],"machine-learning":[17,37],"models.":[18],"Here,":[19],"we":[20],"present":[21],"the":[22,49,52,68,84,115,129,142,162,172,192,197],"development":[23],"of":[24,51,55,75,114,141,159,161,169],"a":[25,71,93,103,152,166],"new":[26],"fingerprint":[27,45,144],"chemical":[29],"reactions":[30,76,116,132],"validate":[32],"its":[33],"usefulness":[34],"in":[35,40,117,196],"building":[36],"models":[38],"assessment.":[42],"Our":[43],"final":[44],"is":[46],"constructed":[47],"difference":[50],"atom-pair":[53],"fingerprints":[54,69],"products":[56],"reactants":[58],"includes":[60],"agents":[61],"via":[62],"calculated":[63],"physicochemical":[64],"properties.":[65],"We":[66,97],"validated":[67],"on":[70],"large":[72],"data":[73,175],"set":[74],"text-mined":[77],"from":[78,83,133],"granted":[79],"United":[80],"States":[81],"patents":[82],"last":[85],"40":[86],"years":[87],"that":[88,110,155],"been":[90],"classified":[91],"using":[92],"substructure-based":[94],"expert":[95],"system.":[96],"machine":[99],"learning":[100],"build":[102],"50-class":[104],"predictive":[105],"model":[106],"reaction-type":[108],"classification":[109],"correctly":[111],"predicts":[112],"97%":[113],"an":[118,134],"external":[119],"test":[120],"set.":[121],"Impressive":[122],"accuracies":[123],"were":[124],"also":[125],"observed":[126],"when":[127],"applying":[128],"classifier":[130],"in-house":[135],"electronic":[136],"laboratory":[137],"notebook.":[138],"The":[139,174],"performance":[140],"novel":[143],"assessing":[146],"reaction":[147,163],"was":[149],"evaluated":[150],"by":[151],"cluster":[153],"analysis":[154,193],"recovered":[156],"48":[157],"out":[158],"50":[160],"classes":[164],"with":[165],"median":[167],"F-score":[168],"0.63":[170],"clusters.":[173],"sets":[176],"used":[177],"training":[179],"primary":[181],"validation":[182],"well":[184],"all":[186],"python":[187],"scripts":[188],"required":[189],"reproduce":[191],"are":[194],"provided":[195],"Supporting":[198],"Information.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":22},{"year":2024,"cited_by_count":39},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":26},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":29},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-11T18:08:03.149640","created_date":"2025-10-10T00:00:00"}
