{"id":"https://openalex.org/W2892349988","doi":"https://doi.org/10.1021/acs.jcim.8b00313","title":"Regression Modelability Index: A New Index for Prediction of the Modelability of Data Sets in the Development of QSAR Regression Models","display_name":"Regression Modelability Index: A New Index for Prediction of the Modelability of Data Sets in the Development of QSAR Regression Models","publication_year":2018,"publication_date":"2018-09-11","ids":{"openalex":"https://openalex.org/W2892349988","doi":"https://doi.org/10.1021/acs.jcim.8b00313","mag":"2892349988","pmid":"https://pubmed.ncbi.nlm.nih.gov/30205684"},"language":"en","primary_location":{"id":"doi:10.1021/acs.jcim.8b00313","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00313","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/A5041078977","display_name":"Irene Luque Ruiz","orcid":"https://orcid.org/0000-0003-2996-7429"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Irene Luque Ruiz","raw_affiliation_strings":["Department of Computing and Numerical Analysis, University of C\u00f3rdoba, Campus de Rabanales, Albert Einstein Building, E-14071 C\u00f3rdoba, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2996-7429","affiliations":[{"raw_affiliation_string":"Department of Computing and Numerical Analysis, University of C\u00f3rdoba, Campus de Rabanales, Albert Einstein Building, E-14071 C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060638298","display_name":"Miguel \u00c1ngel G\u00f3mez\u2010Nieto","orcid":"https://orcid.org/0000-0002-1946-5495"},"institutions":[{"id":"https://openalex.org/I53110688","display_name":"University of C\u00f3rdoba","ror":"https://ror.org/05yc77b46","country_code":"ES","type":"education","lineage":["https://openalex.org/I53110688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miguel \u00c1ngel G\u00f3mez-Nieto","raw_affiliation_strings":["Department of Computing and Numerical Analysis, University of C\u00f3rdoba, Campus de Rabanales, Albert Einstein Building, E-14071 C\u00f3rdoba, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1946-5495","affiliations":[{"raw_affiliation_string":"Department of Computing and Numerical Analysis, University of C\u00f3rdoba, Campus de Rabanales, Albert Einstein Building, E-14071 C\u00f3rdoba, Spain","institution_ids":["https://openalex.org/I53110688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5041078977"],"corresponding_institution_ids":["https://openalex.org/I53110688"],"apc_list":null,"apc_paid":null,"fwci":0.8598,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.77015766,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"58","issue":"10","first_page":"2069","last_page":"2084"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9997000098228455,"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":0.9997000098228455,"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/T10836","display_name":"Metabolomics and Mass Spectrometry Studies","score":0.9857000112533569,"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/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.7157186269760132},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.6850872039794922},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.6547753214836121},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.6007663011550903},{"id":"https://openalex.org/keywords/factor-regression-model","display_name":"Factor regression model","score":0.46566203236579895},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.4392469525337219},{"id":"https://openalex.org/keywords/regression-diagnostic","display_name":"Regression diagnostic","score":0.4210865795612335},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3867718279361725},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3700164258480072},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.32635653018951416},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29771095514297485},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23941656947135925},{"id":"https://openalex.org/keywords/polynomial-regression","display_name":"Polynomial regression","score":0.17015084624290466},{"id":"https://openalex.org/keywords/proper-linear-model","display_name":"Proper linear model","score":0.15866664052009583}],"concepts":[{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.7157186269760132},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.6850872039794922},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.6547753214836121},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.6007663011550903},{"id":"https://openalex.org/C93698799","wikidata":"https://www.wikidata.org/wiki/Q5428730","display_name":"Factor regression model","level":5,"score":0.46566203236579895},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4392469525337219},{"id":"https://openalex.org/C57381214","wikidata":"https://www.wikidata.org/wiki/Q55631393","display_name":"Regression diagnostic","level":4,"score":0.4210865795612335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3867718279361725},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3700164258480072},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32635653018951416},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29771095514297485},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23941656947135925},{"id":"https://openalex.org/C120068334","wikidata":"https://www.wikidata.org/wiki/Q45343","display_name":"Polynomial regression","level":3,"score":0.17015084624290466},{"id":"https://openalex.org/C32224588","wikidata":"https://www.wikidata.org/wiki/Q7250175","display_name":"Proper linear model","level":4,"score":0.15866664052009583},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"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":"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":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015394","descriptor_name":"Molecular Structure","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":false},{"descriptor_ui":"D021281","descriptor_name":"Quantitative Structure-Activity Relationship","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":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D055808","descriptor_name":"Drug Discovery","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/acs.jcim.8b00313","is_oa":false,"landing_page_url":"https://doi.org/10.1021/acs.jcim.8b00313","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:30205684","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30205684","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":26,"referenced_works":["https://openalex.org/W128607844","https://openalex.org/W330953206","https://openalex.org/W1570912112","https://openalex.org/W1977843597","https://openalex.org/W2002503643","https://openalex.org/W2007344527","https://openalex.org/W2010933199","https://openalex.org/W2025556769","https://openalex.org/W2033757486","https://openalex.org/W2039609876","https://openalex.org/W2051810242","https://openalex.org/W2072582769","https://openalex.org/W2076018148","https://openalex.org/W2076592938","https://openalex.org/W2078877418","https://openalex.org/W2087300213","https://openalex.org/W2128245586","https://openalex.org/W2159887157","https://openalex.org/W2330317998","https://openalex.org/W2340543616","https://openalex.org/W2410846838","https://openalex.org/W2473238561","https://openalex.org/W2791494189","https://openalex.org/W2889157215","https://openalex.org/W4233620411","https://openalex.org/W4405190226"],"related_works":["https://openalex.org/W267133670","https://openalex.org/W3148095850","https://openalex.org/W2165410129","https://openalex.org/W2374894797","https://openalex.org/W2033531685","https://openalex.org/W2091740012","https://openalex.org/W4309298396","https://openalex.org/W4253065990","https://openalex.org/W2018714386","https://openalex.org/W2111748225"],"abstract_inverted_index":{"Prediction":[0],"of":[1,4,18,46,56,75,99,110,113,116,142,168,176,197,200],"the":[2,16,39,43,47,57,73,80,93,96,100,103,111,117,140,149,153,159,174,181,185,194,198],"capability":[3,112],"a":[5,12,67,125],"data":[6,48,104,118,133,190],"set":[7,49,119,191],"to":[8,32,41,52,120,179],"be":[9,121],"modeled":[10],"by":[11,124,184],"statistical":[13],"algorithm":[14],"in":[15,50,102,162,193],"development":[17],"quantitative":[19],"structure\u2013activity":[20],"relationship":[21],"(QSAR)":[22],"regression":[23,81,126,155,186,202],"models":[24],"is":[25,90],"an":[26,54],"important":[27],"issue":[28],"that":[29,70],"allows":[30,108],"researchers":[31],"avoid":[33],"unnecessary":[34],"tasks,":[35],"wasted":[36],"time,":[37],"and/or":[38],"need":[40],"depurate":[42],"molecule":[44,115],"composition":[45],"order":[51],"achieve":[53],"improvement":[55],"model\u2019s":[58],"accuracy.":[59],"In":[60,128,170],"this":[61,129,177],"paper,":[62],"we":[63,147,172],"propose":[64],"and":[65,89,144,158],"formulate":[66],"new":[68],"index":[69,157,178],"correlates":[71],"with":[72,135],"performance":[74],"QSAR":[76,201],"models.":[77,203],"This":[78,106],"index,":[79,83],"modelability":[82,156],"requires":[84],"very":[85,136],"low":[86],"computational":[87],"cost":[88],"based":[91],"on":[92],"rivality":[94,107],"between":[95,152],"nearest":[97],"neighbors":[98],"molecules":[101,143],"set.":[105],"measurement":[109],"each":[114],"correctly":[122],"predicted":[123],"algorithm.":[127],"study,":[130],"using":[131],"40":[132],"sets":[134],"different":[137],"characteristics":[138],"regarding":[139],"number":[141],"activity":[145],"values,":[146],"prove":[148],"high":[150],"correlation":[151,160],"proposed":[154],"coefficient":[161],"cross-validation":[163],"(Q2),":[164],"reaching":[165],"r2":[166],"values":[167],"0.8.":[169],"addition,":[171],"describe":[173],"ability":[175],"discover":[180],"outliers":[182],"detected":[183],"algorithms,":[187],"allowing":[188],"easy":[189],"depuration":[192],"first":[195],"stages":[196],"construction":[199]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-16T08:24:45.110214","created_date":"2025-10-10T00:00:00"}