{"id":"https://openalex.org/W2605274794","doi":"https://doi.org/10.1021/acs.jcim.7b00088","title":"Influence of Varying Training Set Composition and Size on Support Vector Machine-Based Prediction of Active Compounds","display_name":"Influence of Varying Training Set Composition and Size on Support Vector Machine-Based Prediction of Active Compounds","publication_year":2017,"publication_date":"2017-04-05","ids":{"openalex":"https://openalex.org/W2605274794","doi":"https://doi.org/10.1021/acs.jcim.7b00088","mag":"2605274794","pmid":"https://pubmed.ncbi.nlm.nih.gov/28376613"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.7b00088","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00088","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","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/A5038390721","display_name":"Raquel Rodr\u00edguez-P\u00e9rez","orcid":"https://orcid.org/0000-0002-2992-3402"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Raquel Rodr\u00edguez-P\u00e9rez","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016304883","display_name":"Martin Vogt","orcid":"https://orcid.org/0000-0002-3931-9516"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Vogt","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039926688","display_name":"J\u00fcrgen Bajorath","orcid":"https://orcid.org/0000-0002-0557-5714"},"institutions":[{"id":"https://openalex.org/I135140700","display_name":"University of Bonn","ror":"https://ror.org/041nas322","country_code":"DE","type":"education","lineage":["https://openalex.org/I135140700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"J\u00fcrgen Bajorath","raw_affiliation_strings":["Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany"],"affiliations":[{"raw_affiliation_string":"Department of Life Science Informatics, B-IT, LIMES Program Unit Chemical Biology and Medicinal Chemistry, Rheinische Friedrich-Wilhelms-Universit\u00e4t, Dahlmannstrasse 2, D-53113 Bonn, Germany","institution_ids":["https://openalex.org/I135140700"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038390721"],"corresponding_institution_ids":["https://openalex.org/I135140700"],"apc_list":null,"apc_paid":null,"fwci":4.0273,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.94603822,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"57","issue":"4","first_page":"710","last_page":"716"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":1.0,"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":1.0,"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9627000093460083,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.9581000208854675,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.847241222858429},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6750251054763794},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6631290912628174},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.6424342393875122},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6403040289878845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5644687414169312},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5643139481544495},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5322553515434265},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.5264891982078552},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.4744495153427124},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46212953329086304},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4303657114505768},{"id":"https://openalex.org/keywords/active-learning","display_name":"Active learning (machine learning)","score":0.4255896210670471},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32724300026893616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25259771943092346},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2070731520652771},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.10130444169044495},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.08026352524757385}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.847241222858429},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6750251054763794},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6631290912628174},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.6424342393875122},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6403040289878845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5644687414169312},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5643139481544495},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5322553515434265},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.5264891982078552},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.4744495153427124},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46212953329086304},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4303657114505768},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.4255896210670471},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32724300026893616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25259771943092346},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2070731520652771},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.10130444169044495},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.08026352524757385},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015195","descriptor_name":"Drug Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1021/acs.jcim.7b00088","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.7b00088","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":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Chemical Information and Modeling","raw_type":"journal-article"},{"id":"pmid:28376613","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/28376613","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:4268819","is_oa":false,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5417594","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W129457532","https://openalex.org/W1504663295","https://openalex.org/W1941659294","https://openalex.org/W1974166884","https://openalex.org/W1975875968","https://openalex.org/W1988037271","https://openalex.org/W2024224430","https://openalex.org/W2025580327","https://openalex.org/W2027482274","https://openalex.org/W2041406732","https://openalex.org/W2045673749","https://openalex.org/W2046842230","https://openalex.org/W2048489440","https://openalex.org/W2056881083","https://openalex.org/W2081301924","https://openalex.org/W2087347434","https://openalex.org/W2112081648","https://openalex.org/W2113846323","https://openalex.org/W2122629583","https://openalex.org/W2135445066","https://openalex.org/W2139212933","https://openalex.org/W2157963336","https://openalex.org/W2560674852","https://openalex.org/W4206641356","https://openalex.org/W4230674625"],"related_works":["https://openalex.org/W1573015311","https://openalex.org/W1570419641","https://openalex.org/W4386509167","https://openalex.org/W2889938001","https://openalex.org/W4293771607","https://openalex.org/W3165034028","https://openalex.org/W2296499206","https://openalex.org/W3210319767","https://openalex.org/W132037564","https://openalex.org/W4246770172"],"abstract_inverted_index":{"Support":[0],"vector":[1],"machine":[2,11],"(SVM)":[3],"modeling":[4],"is":[5,30],"one":[6],"of":[7,21,51,58,61,70,92,102,107,119,127,139,153,156,188],"the":[8,59,86,114,125,137],"most":[9],"popular":[10],"learning":[12,135],"approaches":[13],"in":[14,34,112],"chemoinformatics":[15],"and":[16,25,45,63,80,105,136,151,165,199],"drug":[17],"design.":[18],"The":[19],"influence":[20],"training":[22,65,72,94,121,157,170,193,206],"set":[23,158],"composition":[24,159],"size":[26],"on":[27],"predictions":[28],"currently":[29],"an":[31],"underinvestigated":[32],"issue":[33],"SVM":[35,43,74,134],"modeling.":[36],"In":[37,99],"this":[38,83],"study,":[39,147],"we":[40],"have":[41,130],"derived":[42],"classification":[44,75],"ranking":[46],"models":[47],"for":[48,116,133,184,204],"a":[49,89],"variety":[50],"compound":[52,144,154],"activity":[53],"classes":[54,145],"under":[55,146],"systematic":[56],"variation":[57],"number":[60],"positive":[62,93],"negative":[64,71,120,192],"examples.":[66,122],"With":[67],"increasing":[68,117,186],"numbers":[69,118,187],"compounds,":[73],"calculations":[76,115],"became":[77],"increasingly":[78],"accurate":[79],"stable.":[81],"However,":[82,174],"was":[84,96,160],"only":[85],"case":[87],"if":[88],"required":[90],"threshold":[91],"examples":[95,194],"also":[97],"reached.":[98],"addition,":[100],"consideration":[101],"class":[103],"weights":[104],"optimization":[106],"cost":[108],"factors":[109],"substantially":[110],"aided":[111],"balancing":[113],"Taken":[123],"together,":[124],"results":[126,203],"our":[128],"analysis":[129],"practical":[131],"implications":[132],"prediction":[138],"active":[140,164,180],"compounds.":[141],"For":[142],"all":[143],"top":[148],"recall":[149,155],"performance":[150,198],"independence":[152],"achieved":[161],"when":[162],"250-500":[163],"500-1000":[166,189],"randomly":[167,190],"selected":[168,191],"inactive":[169],"instances":[171],"were":[172,182],"used.":[173],"as":[175,177],"long":[176],"\u223c50":[178],"known":[179],"compounds":[181],"available":[183],"training,":[185],"significantly":[195],"improved":[196],"model":[197],"gave":[200],"very":[201],"similar":[202],"different":[205],"sets.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-22T08:09:32.410652","created_date":"2025-10-10T00:00:00"}