{"id":"https://openalex.org/W4311069000","doi":"https://doi.org/10.1371/journal.pone.0278570","title":"Hi-LASSO: High-performance python and apache spark packages for feature selection with high-dimensional data","display_name":"Hi-LASSO: High-performance python and apache spark packages for feature selection with high-dimensional data","publication_year":2022,"publication_date":"2022-12-01","ids":{"openalex":"https://openalex.org/W4311069000","doi":"https://doi.org/10.1371/journal.pone.0278570","pmid":"https://pubmed.ncbi.nlm.nih.gov/36455001","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/9714948"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pone.0278570","doi":"https://doi.org/10.1371/journal.pone.0278570","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0278570","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS ONE","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1371/journal.pone.0278570","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032794520","display_name":"Jongkwon Jo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongkwon Jo","raw_affiliation_strings":["Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea","institution_ids":["https://openalex.org/I189442560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070436511","display_name":"Seungha Jung","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungha Jung","raw_affiliation_strings":["Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea","institution_ids":["https://openalex.org/I189442560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083550355","display_name":"Joong-Yang Park","orcid":"https://orcid.org/0000-0002-6815-9996","observed_orcids":["https://orcid.org/0000-0002-6815-9996"]},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joongyang Park","raw_affiliation_strings":["Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea","institution_ids":["https://openalex.org/I189442560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024662417","display_name":"Young Soon Kim","orcid":"https://orcid.org/0000-0001-8549-5951","observed_orcids":["https://orcid.org/0000-0001-8549-5951"]},"institutions":[{"id":"https://openalex.org/I189442560","display_name":"Gyeongsang National University","ror":"https://ror.org/00saywf64","country_code":"KR","type":"education","lineage":["https://openalex.org/I189442560"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Youngsoon Kim","raw_affiliation_strings":["Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information and Statistics, Gyeongsang National University, Jinju-si, South Korea","institution_ids":["https://openalex.org/I189442560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058010272","display_name":"Mingon Kang","orcid":"https://orcid.org/0000-0002-9565-9523","observed_orcids":["https://orcid.org/0000-0002-9565-9523"]},"institutions":[{"id":"https://openalex.org/I133999245","display_name":"University of Nevada, Las Vegas","ror":"https://ror.org/0406gha72","country_code":"US","type":"education","lineage":["https://openalex.org/I133999245"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Mingon Kang","raw_affiliation_strings":["Department of Computer Science, University of Nevada, Las Vegas, Nevada, USA","Department of Computer Science, University of Nevada, Las Vegas, Nevada, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9565-9523","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Nevada, Las Vegas, Nevada, USA","institution_ids":["https://openalex.org/I133999245"]},{"raw_affiliation_string":"Department of Computer Science, University of Nevada, Las Vegas, Nevada, United States of America","institution_ids":["https://openalex.org/I133999245"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024662417","https://openalex.org/A5058010272"],"corresponding_institution_ids":["https://openalex.org/I133999245","https://openalex.org/I189442560"],"apc_list":{"value":1805,"currency":"USD","value_usd":1805},"apc_paid":{"value":1805,"currency":"USD","value_usd":1805},"fwci":1.0942,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.76885308,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":"17","issue":"12","first_page":"e0278570","last_page":"e0278570"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9994999766349792,"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":0.9994999766349792,"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/T13141","display_name":"Statistical Methods and Applications","score":0.0,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.0,"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/feature-selection","display_name":"feature selection","score":0.7590000033378601},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.968999981880188},{"id":"https://openalex.org/keywords/lasso","display_name":"LASSO","score":0.9520000219345093},{"id":"https://openalex.org/keywords/bootstrap-method","display_name":"bootstrapping","score":0.7039999961853027},{"id":"https://openalex.org/keywords/apache-spark","display_name":"Apache Spark","score":0.5950000286102295},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"parallel computing","score":0.7910000085830688},{"id":"https://openalex.org/keywords/python-library","display_name":"Python library","score":0.6150000095367432},{"id":"https://openalex.org/keywords/tcga-cancer-datasets","display_name":"TCGA cancer datasets","score":0.7570000290870667},{"id":"https://openalex.org/keywords/open-source-software","display_name":"open source software","score":0.722000002861023}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8887747526168823},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6986706852912903},{"id":"https://openalex.org/C37616216","wikidata":"https://www.wikidata.org/wiki/Q3218363","display_name":"Lasso (programming language)","level":2,"score":0.5957635641098022},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5389604568481445},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3382384777069092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27550172805786133},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21487605571746826},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.20952799916267395}],"mesh":[{"descriptor_ui":"D004349","descriptor_name":"Drug Packaging","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D007990","descriptor_name":"Libraries","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015723","descriptor_name":"Gene Library","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018806","descriptor_name":"APACHE","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":7,"locations":[{"id":"doi:10.1371/journal.pone.0278570","doi":"https://doi.org/10.1371/journal.pone.0278570","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0278570","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS ONE","raw_type":"journal-article"},{"id":"doi:10.1101/2022.04.22.489133","doi":"https://doi.org/10.1101/2022.04.22.489133","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2022.04.22.489133","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2022/04/22/2022.04.22.489133.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"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":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:36455001","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36455001","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,"listed_in":[],"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":"PloS one","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:9714948","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC9714948/","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,"listed_in":[],"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":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLoS One","raw_type":"Text"},{"id":"pmh:oai:RePEc:plo:pone00:0278570","doi":null,"is_oa":false,"landing_page_url":"https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0278570","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:doaj.org/article:34d3f9c0549a4fe9928aef64bdd39460","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/34d3f9c0549a4fe9928aef64bdd39460","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,"listed_in":[],"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":"PLoS ONE, Vol 17, Iss 12 (2022)","raw_type":"article"},{"id":"pmh:oai:doaj.org/article:d35e51c8f545484bb4b384f7ef822e8b","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/d35e51c8f545484bb4b384f7ef822e8b","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,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS ONE, Vol 17, Iss 12, p e0278570 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1371/journal.pone.0278570","doi":"https://doi.org/10.1371/journal.pone.0278570","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pone.0278570","pdf_url":null,"source":{"id":"https://openalex.org/S202381698","display_name":"PLoS ONE","issn_l":"1932-6203","issn":["1932-6203"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","doyens","erih-plus","jufo-1","ki-jl-1","medline","norway-1","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS ONE","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G734371350","display_name":null,"funder_award_id":"NRF-2021R1I1A3048029","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4311069000.pdf","grobid_xml":"https://content.openalex.org/works/W4311069000.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W124018459","https://openalex.org/W2020925091","https://openalex.org/W2122825543","https://openalex.org/W2163567911","https://openalex.org/W2889270078","https://openalex.org/W2910575305","https://openalex.org/W2938115382","https://openalex.org/W2948009788","https://openalex.org/W3037000643","https://openalex.org/W3149775087","https://openalex.org/W4200067075","https://openalex.org/W4229873072"],"related_works":["https://openalex.org/W2938115382","https://openalex.org/W7123439284","https://openalex.org/W3189704902","https://openalex.org/W3132426513","https://openalex.org/W7099160581","https://openalex.org/W211773742","https://openalex.org/W7097996100","https://openalex.org/W3126285036","https://openalex.org/W2368411078","https://openalex.org/W3126122061"],"abstract_inverted_index":{"High-dimensional":[0],"LASSO":[1,22],"(Hi-LASSO)":[2],"is":[3,139],"a":[4,36,65,99],"powerful":[5],"feature":[6,41,85,114],"selection":[7,42,86],"tool":[8],"for":[9,35,40,48,68,84,113],"high-dimensional":[10,88],"data.":[11,89],"Our":[12],"previous":[13],"study":[14],"showed":[15],"that":[16],"Hi-LASSO":[17,47,102,116],"outperformed":[18],"the":[19,25,31,54,77,80,111,124],"other":[20],"state-of-the-art":[21],"methods.":[23],"However,":[24],"substantial":[26],"cost":[27],"of":[28,33,79],"bootstrapping":[29],"and":[30,57,106,136,143],"lack":[32],"experiments":[34,97],"parametric":[37,81],"statistical":[38,82],"test":[39],"have":[43],"impeded":[44],"to":[45],"apply":[46],"practical":[49,100],"applications.":[50],"In":[51],"this":[52],"paper,":[53],"Python":[55,134],"package":[56],"its":[58],"Spark":[59],"library":[60],"are":[61,118],"efficiently":[62,105],"designed":[63],"in":[64,98],"parallel":[66],"manner":[67],"practice":[69],"with":[70,94],"real-world":[71],"problems,":[72],"as":[73,75],"well":[74],"providing":[76],"capability":[78],"tests":[83],"on":[87],"We":[90],"demonstrate":[91],"Hi-LASSO\u2019s":[92],"outperformance":[93],"various":[95],"intensive":[96],"manner.":[101],"will":[103],"be":[104,130],"easily":[107,131],"performed":[108],"by":[109,133],"using":[110],"packages":[112,117,128],"selection.":[115],"publicly":[119],"available":[120,140],"at":[121,141],"https://github.com/datax-lab/Hi-LASSO":[122],"under":[123],"MIT":[125],"license.":[126],"The":[127],"can":[129],"installed":[132],"PIP,":[135],"additional":[137],"documentation":[138],"https://pypi.org/project/hi-lasso":[142],"https://pypi.org/project/Hi-LASSO-spark":[144],".":[145]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2022-12-23T00:00:00"}