{"id":"https://openalex.org/W2201106676","doi":"https://doi.org/10.1021/ci0497511","title":"Determining the Validity of a QSAR Model \u2212 A Classification Approach","display_name":"Determining the Validity of a QSAR Model \u2212 A Classification Approach","publication_year":2004,"publication_date":"2004-11-24","ids":{"openalex":"https://openalex.org/W2201106676","doi":"https://doi.org/10.1021/ci0497511","mag":"2201106676","pmid":"https://pubmed.ncbi.nlm.nih.gov/15667130"},"language":"en","primary_location":{"id":"doi:10.1021/ci0497511","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0497511","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/A5069062997","display_name":"Rajarshi Guha","orcid":"https://orcid.org/0000-0001-7403-8819"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rajarshi Guha","raw_affiliation_strings":["Chemistry Department, 104 Chemistry Building, Penn State University, University Park, Pennsylvania 16802"],"affiliations":[{"raw_affiliation_string":"Chemistry Department, 104 Chemistry Building, Penn State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109171233","display_name":"Peter C. Jurs","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter C. Jurs","raw_affiliation_strings":["Chemistry Department, 104 Chemistry Building, Penn State University, University Park, Pennsylvania 16802"],"affiliations":[{"raw_affiliation_string":"Chemistry Department, 104 Chemistry Building, Penn State University, University Park, Pennsylvania 16802","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5069062997"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":7.3325,"has_fulltext":false,"cited_by_count":92,"citation_normalized_percentile":{"value":0.97651738,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"45","issue":"1","first_page":"65","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9993000030517578,"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":0.9993000030517578,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.9853000044822693,"subfield":{"id":"https://openalex.org/subfields/1602","display_name":"Analytical 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/T11948","display_name":"Machine Learning in Materials Science","score":0.9172999858856201,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.8671935796737671},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6307504177093506},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5818164348602295},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5524592995643616},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5401983857154846},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.47503095865249634},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.44970014691352844},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44528406858444214},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.41946911811828613},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.41692161560058594},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3989361822605133},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3399885594844818},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.219711035490036},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12544497847557068}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.8671935796737671},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6307504177093506},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5818164348602295},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5524592995643616},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5401983857154846},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.47503095865249634},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.44970014691352844},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44528406858444214},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.41946911811828613},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.41692161560058594},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3989361822605133},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3399885594844818},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.219711035490036},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12544497847557068}],"mesh":[{"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":"D002965","descriptor_name":"Classification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D002965","descriptor_name":"Classification","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"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":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012044","descriptor_name":"Regression Analysis","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":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci0497511","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci0497511","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:15667130","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15667130","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W355734042","https://openalex.org/W421463624","https://openalex.org/W604621907","https://openalex.org/W1980019773","https://openalex.org/W1980956598","https://openalex.org/W2021748110","https://openalex.org/W2036102095","https://openalex.org/W2051802332","https://openalex.org/W2056760934","https://openalex.org/W2059889666","https://openalex.org/W2068116546","https://openalex.org/W2079179972","https://openalex.org/W2091823093","https://openalex.org/W2117812871","https://openalex.org/W2136241053"],"related_works":["https://openalex.org/W2551736466","https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2358152617","https://openalex.org/W2411778156","https://openalex.org/W31220157","https://openalex.org/W2288557197","https://openalex.org/W2067177470"],"abstract_inverted_index":{"The":[0,119,149,166,188],"determination":[1],"of":[2,5,21,35,83,129,140,143,185],"the":[3,19,71,127,130,138,158,179,216],"validity":[4],"a":[6,39,47,55,91,99,104,113,133,141,161,197],"QSAR":[7,22,58],"model":[8,102],"when":[9],"applied":[10,31,79],"to":[11,32,80,125,213],"new":[12,48,134,198],"compounds":[13],"is":[14,73,88,122],"an":[15],"important":[16],"concern":[17],"in":[18],"field":[20],"and":[23,75,107,110,147,160,173,176],"QSPR":[24],"modeling.":[25],"Various":[26],"scoring":[27],"techniques":[28],"can":[29,44,194],"be":[30,51,78,201],"specific":[33],"types":[34,82],"models.":[36,85],"We":[37,136],"present":[38],"technique":[40,72,87,150,193],"with":[41,181,206],"which":[42],"we":[43,63],"state":[45],"whether":[46,196],"compound":[49,199],"will":[50,200],"well":[52,202],"predicted":[53,205],"by":[54],"previously":[56,100],"built":[57,163],"model.":[59],"In":[60],"this":[61,117,192],"study":[62],"focus":[64],"on":[65,90,116,153],"linear":[66,146],"regression":[67,96,183],"models":[68,184],"only,":[69],"though":[70],"general":[74],"could":[76],"also":[77,177],"other":[81],"quantitative":[84,182],"Our":[86],"based":[89,115],"classification":[92],"method":[93],"that":[94,191],"divides":[95],"residuals":[97],"from":[98,157,211],"generated":[101],"into":[103],"good":[105],"class":[106,109,128],"bad":[108],"then":[111,123],"builds":[112],"classifier":[114,121],"division.":[118],"trained":[120],"used":[124],"determine":[126,195],"residual":[131],"for":[132,215],"compound.":[135],"investigated":[137],"performance":[139],"variety":[142],"classifiers,":[144],"both":[145,171],"nonlinear.":[148],"was":[151],"tested":[152],"two":[154],"data":[155,164,167],"sets":[156,168],"literature":[159],"hand":[162],"set.":[165],"selected":[169],"covered":[170],"physical":[172],"biological":[174],"properties":[175],"presented":[178],"methodology":[180],"varying":[186],"quality.":[187],"results":[189],"indicate":[190],"or":[203],"poorly":[204],"weighted":[207],"success":[208],"rates":[209],"ranging":[210],"73%":[212],"94%":[214],"best":[217],"classifier.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-03-24T08:02:53.985720","created_date":"2025-10-10T00:00:00"}