{"id":"https://openalex.org/W3097652663","doi":"https://doi.org/10.1093/bioinformatics/btaa912","title":"KIMI: Knockoff Inference for Motif Identification from molecular sequences with controlled false discovery rate","display_name":"KIMI: Knockoff Inference for Motif Identification from molecular sequences with controlled false discovery rate","publication_year":2020,"publication_date":"2020-10-14","ids":{"openalex":"https://openalex.org/W3097652663","doi":"https://doi.org/10.1093/bioinformatics/btaa912","mag":"3097652663","pmid":"https://pubmed.ncbi.nlm.nih.gov/33119059"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa912","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa912","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599924","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101611189","display_name":"Xin Bai","orcid":"https://orcid.org/0000-0002-3755-0730"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Bai","raw_affiliation_strings":["Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA"],"raw_orcid":"https://orcid.org/0000-0002-3755-0730","affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100720540","display_name":"Jie Ren","orcid":"https://orcid.org/0000-0003-0464-9096"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jie Ren","raw_affiliation_strings":["Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029944120","display_name":"Yingying Fan","orcid":"https://orcid.org/0000-0003-1726-4654"},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yingying Fan","raw_affiliation_strings":["Data Sciences and Operations Department, Marshall School of Business, University of Southern California , Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Sciences and Operations Department, Marshall School of Business, University of Southern California , Los Angeles, CA 90089, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5022255550","display_name":"Fengzhu Sun","orcid":"https://orcid.org/0000-0002-8552-043X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fengzhu Sun","raw_affiliation_strings":["Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Quantitative and Computational Biology Program, Department of Biological Sciences , Los Angeles, CA 90089, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5022255550","https://openalex.org/A5029944120"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.3216,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.63711307,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"37","issue":"6","first_page":"759","last_page":"766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.532800018787384,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.532800018787384,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.28049999475479126,"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/T10120","display_name":"Bacterial Genetics and Biotechnology","score":0.06310000270605087,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/false-discovery-rate","display_name":"False discovery rate","score":0.9059117436408997},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.6818993091583252},{"id":"https://openalex.org/keywords/contig","display_name":"Contig","score":0.675366997718811},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.6568785905838013},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.530475914478302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4956923723220825},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49342408776283264},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.46592187881469727},{"id":"https://openalex.org/keywords/deep-sequencing","display_name":"Deep sequencing","score":0.44256851077079773},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4246543049812317},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.4223713278770447},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3372340202331543},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.24612310528755188},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.1294003427028656},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.12146267294883728}],"concepts":[{"id":"https://openalex.org/C193244246","wikidata":"https://www.wikidata.org/wiki/Q5432696","display_name":"False discovery rate","level":3,"score":0.9059117436408997},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.6818993091583252},{"id":"https://openalex.org/C59582021","wikidata":"https://www.wikidata.org/wiki/Q1128751","display_name":"Contig","level":4,"score":0.675366997718811},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6568785905838013},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.530475914478302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4956923723220825},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49342408776283264},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.46592187881469727},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.44256851077079773},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4246543049812317},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4223713278770447},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3372340202331543},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24612310528755188},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.1294003427028656},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.12146267294883728},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":"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":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa912","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa912","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33119059","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33119059","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:8599924","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599924","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:8599924","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8599924","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1186640831","display_name":null,"funder_award_id":"1R01GM131407","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G545056270","display_name":null,"funder_award_id":"R01 GM120624","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G5564570098","display_name":null,"funder_award_id":"R01GM120624","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6209734522","display_name":null,"funder_award_id":"R01 GM131407","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1594947347","https://openalex.org/W1600463518","https://openalex.org/W1964027278","https://openalex.org/W1972978214","https://openalex.org/W1974888957","https://openalex.org/W1982443365","https://openalex.org/W1998300401","https://openalex.org/W2005107631","https://openalex.org/W2009462809","https://openalex.org/W2019634045","https://openalex.org/W2023091911","https://openalex.org/W2024500224","https://openalex.org/W2025166640","https://openalex.org/W2029607409","https://openalex.org/W2041397659","https://openalex.org/W2048869777","https://openalex.org/W2053392780","https://openalex.org/W2054984882","https://openalex.org/W2085436536","https://openalex.org/W2087671769","https://openalex.org/W2105381419","https://openalex.org/W2110065044","https://openalex.org/W2119859604","https://openalex.org/W2124738224","https://openalex.org/W2125905177","https://openalex.org/W2130124027","https://openalex.org/W2132996374","https://openalex.org/W2156178399","https://openalex.org/W2159042875","https://openalex.org/W2166162901","https://openalex.org/W2167084464","https://openalex.org/W2204774351","https://openalex.org/W2328023807","https://openalex.org/W2625479840","https://openalex.org/W2732139758","https://openalex.org/W2762425175","https://openalex.org/W2949831026","https://openalex.org/W2963371845","https://openalex.org/W2964082794","https://openalex.org/W2968001089","https://openalex.org/W3003110834","https://openalex.org/W3043129934","https://openalex.org/W3102311896","https://openalex.org/W3103223646","https://openalex.org/W3150707515","https://openalex.org/W6754669518"],"related_works":["https://openalex.org/W2097029864","https://openalex.org/W3198631238","https://openalex.org/W4206661388","https://openalex.org/W2809598614","https://openalex.org/W2099006507","https://openalex.org/W1874977748","https://openalex.org/W4320169348","https://openalex.org/W2124201730","https://openalex.org/W3097652663","https://openalex.org/W2966369432"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1],"rapid":[2],"development":[3],"of":[4,15,39,42,91,108,186,210,220,245],"sequencing":[5,66],"technologies":[6],"has":[7],"enabled":[8],"us":[9],"to":[10,27,59,158],"generate":[11],"a":[12,120,206],"large":[13],"number":[14],"metagenomic":[16,65],"reads":[17,67],"from":[18],"genetic":[19,37],"materials":[20,38],"in":[21,161,188],"microbial":[22],"communities,":[23],"making":[24],"it":[25],"possible":[26],"gain":[28],"deep":[29],"insights":[30],"into":[31,68],"understanding":[32],"the":[33,36,77,88,129,170,176,184,194,218,231],"differences":[34],"between":[35],"different":[40,69,89,106],"groups":[41,90,107],"microorganisms,":[43],"such":[44,72,145],"as":[45,79,128,199],"bacteria,":[46],"viruses,":[47],"plasmids,":[48],"etc.":[49],"Computational":[50],"methods":[51,73],"based":[52,123],"on":[53,124,205,235],"k-mer":[54],"frequencies":[55],"have":[56],"been":[57],"shown":[58,154],"be":[60,149,159,227],"highly":[61],"effective":[62,160],"for":[63,81,87,104,133,136,179],"classifying":[64],"groups.":[70],"However,":[71],"usually":[74],"use":[75],"all":[76],"k-mers":[78,86,103,237],"features":[80],"prediction":[82,232],"without":[83],"selecting":[84],"relevant":[85,236],"sequences,":[92],"i.e.":[93],"unique":[94],"nucleotide":[95],"patterns":[96],"containing":[97],"biological":[98],"significance.":[99],"RESULTS:":[100],"To":[101,182],"select":[102],"distinguishing":[105],"sequences":[109],"with":[110,140],"guaranteed":[111],"false":[112],"discovery":[113,139,197],"rate":[114],"(FDR)":[115],"control,":[116,135],"we":[117,192],"develop":[118],"KIMI,":[119],"general":[121],"framework":[122],"model-X":[125],"Knockoffs":[126],"regarded":[127],"state-of-the-art":[130],"statistical":[131],"method":[132,178],"FDR":[134,143,164,180],"sequence":[137],"motif":[138,196],"arbitrary":[141],"target":[142],"level,":[144],"that":[146,217],"reproducibility":[147],"can":[148,226],"theoretically":[150],"guaranteed.":[151],"KIMI":[152,187,204,246],"is":[153,247],"through":[155],"simulation":[156],"studies":[157],"simultaneously":[162],"controlling":[163],"and":[165,175,202,212,223],"yielding":[166],"high":[167],"power,":[168],"outperforming":[169],"broadly":[171],"used":[172],"Benjamini-Hochberg":[173],"procedure":[174],"q-value":[177],"control.":[181],"illustrate":[183],"usefulness":[185],"analyzing":[189],"real":[190,207],"datasets,":[191],"take":[193],"viral":[195,211,222],"problem":[198],"an":[200],"example":[201],"implement":[203],"dataset":[208],"consisting":[209],"bacterial":[213,224],"contigs.":[214],"We":[215],"show":[216],"accuracy":[219],"predicting":[221],"contigs":[225],"increased":[228],"by":[229,239],"training":[230],"model":[233],"only":[234],"selected":[238],"KIMI.":[240],"AVAILABILITYAND":[241],"IMPLEMENTATION:":[242],"Our":[243],"implementation":[244],"available":[248,256],"at":[249,257],"https://github.com/xinbaiusc/KIMI.":[250],"SUPPLEMENTARY":[251],"INFORMATION:":[252],"Supplementary":[253],"data":[254],"are":[255],"Bioinformatics":[258],"online.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}
