{"id":"https://openalex.org/W4416678103","doi":"https://doi.org/10.1186/s12859-025-06215-z","title":"Gradient boosting with knockoff filters: a biostatistical approach to variable selection","display_name":"Gradient boosting with knockoff filters: a biostatistical approach to variable selection","publication_year":2025,"publication_date":"2025-11-25","ids":{"openalex":"https://openalex.org/W4416678103","doi":"https://doi.org/10.1186/s12859-025-06215-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/41291416"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-025-06215-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06215-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-025-06215-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021329808","display_name":"Amr Mohamed","orcid":"https://orcid.org/0000-0002-1583-7503"},"institutions":[{"id":"https://openalex.org/I94658018","display_name":"University of Memphis","ror":"https://ror.org/01cq23130","country_code":"US","type":"education","lineage":["https://openalex.org/I94658018"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amr Mohamed","raw_affiliation_strings":["College of Health Sciences, The University of Memphis, 3720 Alumni Ave, Memphis, TN, 38152, USA. A.Mohamed@memphis.edu","College of Health Sciences, The University of Memphis, 3720 Alumni Ave, Memphis, TN, 38152, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Sciences, The University of Memphis, 3720 Alumni Ave, Memphis, TN, 38152, USA. A.Mohamed@memphis.edu","institution_ids":["https://openalex.org/I94658018"]},{"raw_affiliation_string":"College of Health Sciences, The University of Memphis, 3720 Alumni Ave, Memphis, TN, 38152, USA","institution_ids":["https://openalex.org/I94658018"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034713216","display_name":"Kevin H. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I141649380","display_name":"Western Michigan University","ror":"https://ror.org/04j198w64","country_code":"US","type":"education","lineage":["https://openalex.org/I141649380"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin H. Lee","raw_affiliation_strings":["Department of Statistics, Western Michigan University, 1903 W Michigan Ave, Kalamazoo, MI, 49008, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Western Michigan University, 1903 W Michigan Ave, Kalamazoo, MI, 49008, USA","institution_ids":["https://openalex.org/I141649380"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021329808"],"corresponding_institution_ids":["https://openalex.org/I94658018"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17247091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"27","issue":"1","first_page":"13","last_page":"13"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5117999911308289,"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"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.5117999911308289,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.12060000002384186,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.06840000301599503,"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/boosting","display_name":"Boosting (machine learning)","score":0.8274000287055969},{"id":"https://openalex.org/keywords/gradient-boosting","display_name":"Gradient boosting","score":0.7488999962806702},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.733299970626831},{"id":"https://openalex.org/keywords/false-discovery-rate","display_name":"False discovery rate","score":0.6809999942779541},{"id":"https://openalex.org/keywords/variable","display_name":"Variable (mathematics)","score":0.5572999715805054},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4966000020503998},{"id":"https://openalex.org/keywords/variables","display_name":"Variables","score":0.49630001187324524},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.37599998712539673}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.8274000287055969},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.7488999962806702},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.733299970626831},{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.6809999942779541},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6482999920845032},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6359999775886536},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6036999821662903},{"id":"https://openalex.org/C182365436","wikidata":"https://www.wikidata.org/wiki/Q50701","display_name":"Variable (mathematics)","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4966000020503998},{"id":"https://openalex.org/C27574286","wikidata":"https://www.wikidata.org/wiki/Q320723","display_name":"Variables","level":2,"score":0.49630001187324524},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.376800000667572},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.3504999876022339},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.34940001368522644},{"id":"https://openalex.org/C137002209","wikidata":"https://www.wikidata.org/wiki/Q898521","display_name":"Hidden variable theory","level":3,"score":0.3325999975204468},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.2883000075817108},{"id":"https://openalex.org/C162144332","wikidata":"https://www.wikidata.org/wiki/Q1665305","display_name":"Instrumental variable","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2982736386","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Statistical learning","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.25589999556541443}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056808","descriptor_name":"Biostatistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056808","descriptor_name":"Biostatistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D056808","descriptor_name":"Biostatistics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1186/s12859-025-06215-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06215-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41291416","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41291416","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:25fdd6a0ff24461f96f651b27c2685ae","is_oa":true,"landing_page_url":"https://doaj.org/article/25fdd6a0ff24461f96f651b27c2685ae","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1, Pp 1-20 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12801829","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12801829/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s12859-025-06215-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-025-06215-z","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2109177042","https://openalex.org/W2135046866","https://openalex.org/W2159400887","https://openalex.org/W2192203593","https://openalex.org/W2950389803","https://openalex.org/W2963371845"],"related_works":[],"abstract_inverted_index":{"As":[0],"data":[1],"complexity":[2],"and":[3,27,44,90,130,153,188],"volume":[4],"increase":[5],"rapidly,":[6],"efficient":[7],"statistical":[8,46,186],"methods":[9],"for":[10,71,123,181],"identifying":[11,120,182],"significant":[12],"variables":[13,57,122,184],"become":[14],"crucial.":[15],"Variable":[16],"selection":[17,161,170],"plays":[18],"a":[19,51,88,178],"vital":[20],"role":[21],"in":[22,33,171,185],"establishing":[23],"relationships":[24],"between":[25],"predictors":[26],"response":[28],"variables.":[29],"The":[30,48,145],"challenge":[31],"lies":[32],"achieving":[34],"this":[35,74],"goal":[36],"while":[37],"controlling":[38],"the":[39,60,64,78,104,157,166,172],"False":[40],"Discovery":[41],"Rate":[42],"(FDR)":[43],"maintaining":[45],"power.":[47],"knockoff":[49,56],"filter,":[50],"recent":[52],"approach,":[53,138],"generates":[54],"inexpensive":[55],"that":[58],"mimic":[59],"correlation":[61],"structure":[62],"of":[63,80,107,147,159,168,174],"original":[65],"variables,":[66],"serving":[67],"as":[68],"negative":[69],"controls":[70],"inference.":[72],"In":[73],"study,":[75],"we":[76],"extend":[77],"use":[79],"knockoffs":[81,148],"to":[82,102,156],"Light":[83],"Gradient":[84],"Boosting":[85],"Machine":[86],"(LightGBM),":[87],"fast":[89],"accurate":[91],"machine":[92,108,189],"learning":[93,190],"technique.":[94],"Shapely":[95],"Additive":[96],"Explanations":[97],"(SHAP)":[98],"values":[99],"are":[100],"employed":[101],"interpret":[103],"black-box":[105],"nature":[106],"learning.":[109],"Through":[110],"extensive":[111,140],"experimentation,":[112],"our":[113,137],"proposed":[114],"method":[115],"outperforms":[116],"traditional":[117],"approaches,":[118],"accurately":[119],"important":[121],"each":[124],"class.":[125],"It":[126],"offers":[127],"improved":[128],"speed":[129],"efficiency":[131],"across":[132],"multiple":[133],"datasets.":[134],"To":[135],"validate":[136],"an":[139],"simulation":[141],"study":[142],"is":[143],"conducted.":[144],"integration":[146],"into":[149],"LightGBM":[150],"enhances":[151],"performance":[152],"interpretability,":[154],"contributing":[155],"advancement":[158],"variable":[160,169],"methods.":[162],"Our":[163],"research":[164],"addresses":[165],"challenges":[167],"era":[173],"big":[175],"data,":[176],"providing":[177],"valuable":[179],"tool":[180],"relevant":[183],"modeling":[187],"applications.":[191]},"counts_by_year":[],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-11-25T00:00:00"}