{"id":"https://openalex.org/W2074909247","doi":"https://doi.org/10.1021/ci3000216","title":"Harvesting Classification Trees for Drug Discovery","display_name":"Harvesting Classification Trees for Drug Discovery","publication_year":2012,"publication_date":"2012-10-31","ids":{"openalex":"https://openalex.org/W2074909247","doi":"https://doi.org/10.1021/ci3000216","mag":"2074909247","pmid":"https://pubmed.ncbi.nlm.nih.gov/23110407"},"language":"en","primary_location":{"id":"doi:10.1021/ci3000216","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci3000216","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/A5066041865","display_name":"Yan Yuan","orcid":"https://orcid.org/0000-0002-2073-9924"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Yan Yuan","raw_affiliation_strings":["Department of Public\rHealth\rSciences, University of Alberta, Edmonton, Alberta T6G 1C9, Canada","Department of Public Health Sciences, University of Alberta, Edmonton, Alberta T6G 1C9, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Public\rHealth\rSciences, University of Alberta, Edmonton, Alberta T6G 1C9, Canada","institution_ids":["https://openalex.org/I154425047"]},{"raw_affiliation_string":"Department of Public Health Sciences, University of Alberta, Edmonton, Alberta T6G 1C9, Canada","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058092350","display_name":"Hugh Chipman","orcid":"https://orcid.org/0000-0002-3276-3622"},"institutions":[{"id":"https://openalex.org/I92688161","display_name":"Acadia University","ror":"https://ror.org/00839we02","country_code":"CA","type":"education","lineage":["https://openalex.org/I92688161"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hugh A. Chipman","raw_affiliation_strings":["Department of Mathematics and\rStatistics, Acadia University, Wolfville, Nova Scotia B4P 2R6, Canada","Department of Mathematics and#R#Statistics, Acadia University, Wolfville, Nova Scotia B4P 2R6, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and\rStatistics, Acadia University, Wolfville, Nova Scotia B4P 2R6, Canada","institution_ids":["https://openalex.org/I92688161"]},{"raw_affiliation_string":"Department of Mathematics and#R#Statistics, Acadia University, Wolfville, Nova Scotia B4P 2R6, Canada","institution_ids":["https://openalex.org/I92688161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043650697","display_name":"William J. Welch","orcid":"https://orcid.org/0000-0002-4575-3124"},"institutions":[{"id":"https://openalex.org/I141945490","display_name":"University of British Columbia","ror":"https://ror.org/03rmrcq20","country_code":"CA","type":"education","lineage":["https://openalex.org/I141945490"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"William J. Welch","raw_affiliation_strings":["Department of Statistics, University\rof British Columbia, Vancouver, BC V6T 1Z4, Canada","Department of Statistics, University#R#of British Columbia, Vancouver, BC V6T 1Z4, Canada"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, University\rof British Columbia, Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I141945490"]},{"raw_affiliation_string":"Department of Statistics, University#R#of British Columbia, Vancouver, BC V6T 1Z4, Canada","institution_ids":["https://openalex.org/I141945490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066041865"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.13540462,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"52","issue":"12","first_page":"3169","last_page":"3180"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.968500018119812,"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":0.968500018119812,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9366999864578247,"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"}},{"id":"https://openalex.org/T14351","display_name":"Statistical and Computational Modeling","score":0.9275000095367432,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.8076634407043457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.43121904134750366},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.40380698442459106},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.29832923412323},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.20536315441131592}],"concepts":[{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.8076634407043457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43121904134750366},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.40380698442459106},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.29832923412323},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.20536315441131592}],"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":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D004364","descriptor_name":"Pharmaceutical Preparations","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014481","descriptor_name":"United States","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D015497","descriptor_name":"HIV-1","qualifier_ui":"Q000187","qualifier_name":"drug effects","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D019380","descriptor_name":"Anti-HIV Agents","qualifier_ui":"Q000494","qualifier_name":"pharmacology","is_major_topic":false},{"descriptor_ui":"D054547","descriptor_name":"National Cancer Institute (U.S.)","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054547","descriptor_name":"National Cancer Institute (U.S.)","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054547","descriptor_name":"National Cancer Institute (U.S.)","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},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057166","descriptor_name":"High-Throughput Screening Assays","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D062313","descriptor_name":"Databases, Pharmaceutical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1021/ci3000216","is_oa":false,"landing_page_url":"https://doi.org/10.1021/ci3000216","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:23110407","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/23110407","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":[{"score":0.5600000023841858,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322675","display_name":"Mitacs","ror":"https://ror.org/00cjrc276"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1531520279","https://openalex.org/W1545231783","https://openalex.org/W1578148179","https://openalex.org/W1608932033","https://openalex.org/W1965098358","https://openalex.org/W2031441006","https://openalex.org/W2031498906","https://openalex.org/W2040389962","https://openalex.org/W2046588282","https://openalex.org/W2048231652","https://openalex.org/W2061660567","https://openalex.org/W2067885219","https://openalex.org/W2091731012","https://openalex.org/W2095534911","https://openalex.org/W2122320759","https://openalex.org/W2125055259","https://openalex.org/W2136316780","https://openalex.org/W2150084651","https://openalex.org/W2162099412","https://openalex.org/W2167960276","https://openalex.org/W2213612645","https://openalex.org/W2911964244","https://openalex.org/W4214489552","https://openalex.org/W4297957988"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2013003323","https://openalex.org/W1981076832","https://openalex.org/W2024773645","https://openalex.org/W2001717001","https://openalex.org/W2043147644"],"abstract_inverted_index":{"Millions":[0],"of":[1,40,47,61,68,108,127,138,145,149,179,207,235,242,249,275],"compounds":[2,21,49,54,118],"are":[3,91],"available":[4],"as":[5,121],"potential":[6],"drug":[7,17,124],"candidates.":[8],"High":[9],"throughput":[10],"screening":[11],"(HTS)":[12],"is":[13,30,81,100,103,107,130],"widely":[14],"used":[15,210],"in":[16,240],"discovery":[18],"to":[19,31,43,110,119,159,211,229,256],"assay":[20,41],"for":[22,55,123,278],"a":[23,33,37,84,128,155,213],"particular":[24],"biological":[25,79],"activity.":[26,279],"A":[27,97],"common":[28],"approach":[29],"build":[32,212],"classification":[34,214],"model":[35,99,141],"using":[36],"smaller":[38],"sample":[39],"data":[42,197],"predict":[44],"the":[45,59,62,66,72,78,88,116,135,139,143,150,166,177,199,208,233,236,243,247,250,258,263,276],"activity":[46,80,187,194],"unscreened":[48],"and":[50,142,147,186,188],"hence":[51],"select":[52],"further":[53],"assay.":[56],"This":[57,173],"improves":[58,246],"efficiency":[60],"search":[63],"by":[64,134],"increasing":[65],"proportion":[67],"hits":[69],"found":[70],"among":[71,115],"assayed":[73],"compounds.":[74],"In":[75],"many":[76,206],"assays,":[77],"dichotomized":[82],"into":[83,267],"binary":[85],"indicator":[86],"variable;":[87],"explanatory":[89],"variables":[90,146,225],"chemical":[92,113],"descriptors":[93],"capturing":[94],"compound":[95],"structure.":[96],"tree":[98,129,140,167,215,220,222,259],"interpretable,":[101],"which":[102],"key,":[104],"since":[105],"it":[106],"interest":[109],"identify":[111],"diverse":[112],"classes":[114],"active":[117],"serve":[120],"leads":[122],"optimization.":[125],"Interpretability":[126],"often":[131],"reduced,":[132],"however,":[133],"sheer":[136],"size":[137],"number":[144],"rules":[148,164,191,209,228],"terminal":[151,244],"nodes.":[152],"We":[153],"develop":[154],"\"tree":[156],"harvesting\"":[157],"algorithm":[158,253],"filter":[160],"out":[161],"redundant":[162],"\"junk\"":[163],"from":[165,198],"while":[168],"retaining":[169],"its":[170],"predictive":[171],"accuracy.":[172],"simplification":[174],"can":[175],"facilitate":[176],"process":[178],"uncovering":[180],"key":[181],"relations":[182],"between":[183],"molecular":[184],"structure":[185],"may":[189,216],"clarify":[190],"defining":[192],"multiple":[193],"mechanisms.":[195],"Using":[196],"National":[200],"Cancer":[201],"Institute,":[202],"we":[203],"illustrate":[204],"that":[205],"be":[217,230],"redundant.":[218],"Unlike":[219],"pruning,":[221],"harvesting":[223],"allows":[224],"with":[226,262],"junk":[227],"removed":[231],"near":[232],"top":[234],"tree.":[237],"The":[238,252],"reduction":[239],"complexity":[241],"nodes":[245,260],"interpretability":[248],"model.":[251],"also":[254],"aims":[255],"reorganize":[257],"associated":[261],"interesting":[264],"\"active\"":[265],"class":[266],"larger,":[268],"more":[269],"coherent":[270],"groups,":[271],"thus":[272],"facilitating":[273],"identification":[274],"mechanisms":[277]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
