{"id":"https://openalex.org/W3140814277","doi":"https://doi.org/10.1093/bioinformatics/btab214","title":"EPS: automated feature selection in case\u2013control studies using extreme pseudo-sampling","display_name":"EPS: automated feature selection in case\u2013control studies using extreme pseudo-sampling","publication_year":2021,"publication_date":"2021-03-26","ids":{"openalex":"https://openalex.org/W3140814277","doi":"https://doi.org/10.1093/bioinformatics/btab214","mag":"3140814277","pmid":"https://pubmed.ncbi.nlm.nih.gov/33774671"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab214","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab214","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029563679","display_name":"Ruhollah Shemirani","orcid":"https://orcid.org/0000-0003-1065-7244"},"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":"Ruhollah Shemirani","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina del Rey , CA 90292, USA"],"raw_orcid":"https://orcid.org/0000-0003-1065-7244","affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina del Rey , CA 90292, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059943023","display_name":"St\u00e9phane Wenric","orcid":"https://orcid.org/0000-0001-5625-2133"},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephane Wenric","raw_affiliation_strings":["Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046822527","display_name":"Eimear E. Kenny","orcid":"https://orcid.org/0000-0001-9198-759X"},"institutions":[{"id":"https://openalex.org/I98704320","display_name":"Icahn School of Medicine at Mount Sinai","ror":"https://ror.org/04a9tmd77","country_code":"US","type":"education","lineage":["https://openalex.org/I1320796813","https://openalex.org/I98704320"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eimear Kenny","raw_affiliation_strings":["Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai , New York, NY 10029, USA","institution_ids":["https://openalex.org/I98704320"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033175043","display_name":"Jos\u00e9 Luis Ambite","orcid":"https://orcid.org/0000-0003-0087-080X"},"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":"Jos\u00e9 Luis Ambite","raw_affiliation_strings":["Information Sciences Institute, University of Southern California, Marina del Rey , CA 90292, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, University of Southern California, Marina del Rey , CA 90292, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029563679","https://openalex.org/A5033175043"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.2251,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54456341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"37","issue":"19","first_page":"3372","last_page":"3373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.37279999256134033,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.37279999256134033,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.14270000159740448,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.09000000357627869,"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/computer-science","display_name":"Computer science","score":0.7463448643684387},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.656633734703064},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5761081576347351},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5300008654594421},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.49363934993743896},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.47590765357017517},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4629472494125366},{"id":"https://openalex.org/keywords/regression","display_name":"Regression","score":0.421960711479187},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41648954153060913},{"id":"https://openalex.org/keywords/regression-analysis","display_name":"Regression analysis","score":0.4126337170600891},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37891125679016113},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.18754255771636963},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.163487046957016},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1004096269607544}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7463448643684387},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.656633734703064},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5761081576347351},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5300008654594421},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.49363934993743896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47590765357017517},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4629472494125366},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.421960711479187},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41648954153060913},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.4126337170600891},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37891125679016113},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.18754255771636963},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.163487046957016},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1004096269607544},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab214","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab214","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:33774671","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33774671","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}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2049295438","https://openalex.org/W2054021999","https://openalex.org/W2082704080","https://openalex.org/W2158485828","https://openalex.org/W2555803041","https://openalex.org/W2950016253","https://openalex.org/W3016461380","https://openalex.org/W6663052327","https://openalex.org/W6776182892"],"related_works":["https://openalex.org/W3210877509","https://openalex.org/W2785535669","https://openalex.org/W4225360065","https://openalex.org/W3044458868","https://openalex.org/W4212852473","https://openalex.org/W2891993883","https://openalex.org/W4293525103","https://openalex.org/W4285815787","https://openalex.org/W2592385986","https://openalex.org/W3174196512"],"abstract_inverted_index":{"SUMMARY:":[0],"Finding":[1],"informative":[2],"predictive":[3],"features":[4,124,139],"in":[5,74,93],"high-dimensional":[6],"biological":[7],"case-control":[8],"datasets":[9],"is":[10,107,161],"challenging.":[11],"The":[12,89,156],"Extreme":[13],"Pseudo-Sampling":[14],"(EPS)":[15],"algorithm":[16,105,120,146],"offers":[17],"a":[18,27,38,81,148],"solution":[19],"to":[20,109],"the":[21,47,52,69,75,86,104,118,137,142,145],"challenge":[22],"of":[23,29,55,103,144,151],"feature":[24],"selection":[25],"via":[26,59],"combination":[28],"deep":[30],"learning":[31],"and":[32,57,72,113,125,132],"linear":[33],"regression":[34,76,83,95],"models.":[35],"First,":[36],"using":[37],"variational":[39],"autoencoder,":[40],"it":[41,50,63,79],"generates":[42,64],"complex":[43],"latent":[44,53],"representations":[45,54],"for":[46,127,147,159],"samples.":[48],"Second,":[49],"classifies":[51],"cases":[56,71],"controls":[58,73],"logistic":[60],"regression.":[61],"Third,":[62],"new":[65,82,123,138],"samples":[66],"(pseudo-samples)":[67],"around":[68],"extreme":[70],"model.":[77],"Finally,":[78],"trains":[80],"model":[84,130],"over":[85],"upsampled":[87],"space.":[88],"most":[90],"significant":[91],"variables":[92],"this":[94],"are":[96,170],"selected.":[97],"We":[98,135],"present":[99],"an":[100],"open-source":[101],"implementation":[102],"that":[106],"easy":[108],"set":[110],"up,":[111],"use":[112],"customize.":[114],"Our":[115],"package":[116,158],"enhances":[117],"original":[119],"by":[121],"providing":[122],"customizability":[126],"data":[128,169],"preparation,":[129],"training":[131],"classification":[133],"functionalities.":[134],"believe":[136],"will":[140],"enable":[141],"adoption":[143],"diverse":[149],"range":[150],"datasets.":[152],"AVAILABILITY":[153],"AND":[154],"IMPLEMENTATION:":[155],"software":[157],"Python":[160],"available":[162,171],"online":[163],"at":[164,172],"https://github.com/roohy/eps.":[165],"SUPPLEMENTARY":[166],"INFORMATION:":[167],"Supplementary":[168],"Bioinformatics":[173],"online.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}