{"id":"https://openalex.org/W1965395794","doi":"https://doi.org/10.1021/ci060064e","title":"Local Lazy Regression:\u2009 Making Use of the Neighborhood to Improve QSAR Predictions","display_name":"Local Lazy Regression:\u2009 Making Use of the Neighborhood to Improve QSAR Predictions","publication_year":2006,"publication_date":"2006-05-19","ids":{"openalex":"https://openalex.org/W1965395794","doi":"https://doi.org/10.1021/ci060064e","mag":"1965395794","pmid":"https://pubmed.ncbi.nlm.nih.gov/16859315"},"language":"en","primary_location":{"id":"doi:10.1021/ci060064e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci060064e","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/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Rajarshi Guha","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113845539","display_name":"Debojyoti Dutta","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Debojyoti Dutta","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109171233","display_name":"Peter C. Jurs","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100443173","display_name":"Ting Chen","orcid":"https://orcid.org/0000-0001-8414-6346"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]},{"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":"Ting Chen","raw_affiliation_strings":["Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Chemistry, Pennsylvania State University, University Park, Pennsylvania 16802, and Department of Computational Biology, University of Southern California, Los Angeles, California 90089","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3219,"has_fulltext":false,"cited_by_count":64,"citation_normalized_percentile":{"value":0.96889069,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":98},"biblio":{"volume":"46","issue":"4","first_page":"1836","last_page":"1847"},"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/T10908","display_name":"Analytical Chemistry and Chromatography","score":0.9926000237464905,"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/T10640","display_name":"Spectroscopy and Chemometric Analyses","score":0.972599983215332,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.729546308517456},{"id":"https://openalex.org/keywords/quantitative-structure\u2013activity-relationship","display_name":"Quantitative structure\u2013activity relationship","score":0.6900071501731873},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6295977830886841},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.613151490688324},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.5432792901992798},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.5383492708206177},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4896555542945862},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4411827325820923},{"id":"https://openalex.org/keywords/linear-regression","display_name":"Linear regression","score":0.43343406915664673},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4170604944229126},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35995298624038696},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3482634425163269},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15900099277496338}],"concepts":[{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.729546308517456},{"id":"https://openalex.org/C164126121","wikidata":"https://www.wikidata.org/wiki/Q766383","display_name":"Quantitative structure\u2013activity relationship","level":2,"score":0.6900071501731873},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6295977830886841},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.613151490688324},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.5432792901992798},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5383492708206177},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4896555542945862},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4411827325820923},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.43343406915664673},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4170604944229126},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35995298624038696},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3482634425163269},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15900099277496338},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[{"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":"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/ci060064e","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci060064e","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:16859315","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16859315","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":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1480376833","https://openalex.org/W1493454437","https://openalex.org/W1502930520","https://openalex.org/W1558248317","https://openalex.org/W1585772109","https://openalex.org/W1689445748","https://openalex.org/W1990906298","https://openalex.org/W2001597746","https://openalex.org/W2007077540","https://openalex.org/W2012540065","https://openalex.org/W2043122083","https://openalex.org/W2050870337","https://openalex.org/W2061959470","https://openalex.org/W2066273100","https://openalex.org/W2069270088","https://openalex.org/W2077980976","https://openalex.org/W2079179972","https://openalex.org/W2103913570","https://openalex.org/W2105738427","https://openalex.org/W2109355959","https://openalex.org/W2116342920","https://openalex.org/W2128703518","https://openalex.org/W2135731109","https://openalex.org/W2143022286","https://openalex.org/W2147169507","https://openalex.org/W2156077095","https://openalex.org/W2204819850","https://openalex.org/W2208720202","https://openalex.org/W2492794003","https://openalex.org/W2496675188","https://openalex.org/W2999729612","https://openalex.org/W3142152711"],"related_works":["https://openalex.org/W2382340815","https://openalex.org/W1972650408","https://openalex.org/W2551736466","https://openalex.org/W1997566113","https://openalex.org/W3189652131","https://openalex.org/W2908740012","https://openalex.org/W1967793880","https://openalex.org/W2792066564","https://openalex.org/W2575795810","https://openalex.org/W3121237257"],"abstract_inverted_index":{"Traditional":[0,54],"quantitative":[1],"structure-activity":[2,10,52],"relationship":[3],"(QSAR)":[4],"models":[5,56],"aim":[6],"to":[7,35,48,117,151,192,226,234,250],"capture":[8],"global":[9,145,172,219,236],"trends":[11],"present":[12,239],"in":[13,183,186],"a":[14,28,41,50,77,80,107,153,184,227],"data":[15,92,103,120,177],"set.":[16,93,200],"In":[17,63,122,201,221],"many":[18],"situations,":[19],"there":[20],"may":[21,57],"be":[22,46,111],"groups":[23],"of":[24,31,43,70,156,209,242],"molecules":[25,158],"which":[26,33,75],"exhibit":[27],"specific":[29,154],"set":[30,134],"features":[32,44],"relate":[34],"their":[36],"activity":[37],"or":[38],"inactivity.":[39],"Such":[40],"group":[42,155],"can":[45],"said":[47],"represent":[49],"local":[51,61,71,85,252],"relationship.":[53],"QSAR":[55],"not":[58],"recognize":[59],"such":[60],"relationships.":[62],"this":[64,244],"work,":[65],"we":[66,205],"investigate":[67],"the":[68,90,115,123,126,144,171,175,179,197,202,218,235,251],"use":[69],"lazy":[72],"regression":[73,253],"(LLR),":[74],"obtains":[76],"prediction":[78,133,199],"for":[79,100,130,143,170,196,217],"query":[81],"molecule":[82],"using":[83],"its":[84],"neighborhood,":[86],"rather":[87],"than":[88],"considering":[89],"whole":[91],"This":[94],"modeling":[95],"approach":[96],"is":[97],"especially":[98],"useful":[99],"very":[101],"large":[102],"sets":[104],"because":[105],"no":[106],"priori":[108],"model":[109],"need":[110],"built.":[112],"We":[113,238],"applied":[114],"technique":[116,181],"three":[118],"biological":[119],"sets.":[121],"first":[124],"case,":[125,204],"root-mean-square":[127],"error":[128],"(RMSE)":[129],"an":[131,207,240],"external":[132,198],"was":[135,149,245],"0.94":[136],"log":[137,141,164,168,190,194,211,215],"units":[138,142,165,169,191,195,212,216],"versus":[139,166,213],"0.92":[140],"model.":[146,220,237],"However,":[147],"LLR":[148,180,224],"able":[150],"characterize":[152],"anomalous":[157],"with":[159],"much":[160],"better":[161],"accuracy":[162],"(0.64":[163],"0.70":[167],"model).":[173],"For":[174],"second":[176],"set,":[178],"resulted":[182],"decrease":[185],"RMSE":[187,208],"from":[188],"0.36":[189],"0.31":[193],"third":[203],"obtained":[206],"2.01":[210],"2.16":[214],"all":[222],"cases,":[223],"led":[225],"few":[228],"observations":[229],"being":[230],"poorly":[231],"predicted":[232],"compared":[233],"analysis":[241],"why":[243],"observed":[246],"and":[247],"possible":[248],"improvements":[249],"approach.":[254]},"counts_by_year":[{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}