{"id":"https://openalex.org/W3198253291","doi":"https://doi.org/10.1109/tcbb.2021.3110989","title":"Unsupervised Feature Selection Using an Integrated Strategy of Hierarchical Clustering With Singular Value Decomposition: An Integrative Biomarker Discovery Method With Application to Acute Myeloid Leukemia","display_name":"Unsupervised Feature Selection Using an Integrated Strategy of Hierarchical Clustering With Singular Value Decomposition: An Integrative Biomarker Discovery Method With Application to Acute Myeloid Leukemia","publication_year":2021,"publication_date":"2021-09-08","ids":{"openalex":"https://openalex.org/W3198253291","doi":"https://doi.org/10.1109/tcbb.2021.3110989","mag":"3198253291","pmid":"https://pubmed.ncbi.nlm.nih.gov/34495838"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2021.3110989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3110989","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","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/A5025631339","display_name":"Tapas Bhadra","orcid":"https://orcid.org/0000-0001-8421-1072"},"institutions":[{"id":"https://openalex.org/I180765649","display_name":"Aliah University","ror":"https://ror.org/03rfycd69","country_code":"IN","type":"education","lineage":["https://openalex.org/I180765649"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Tapas Bhadra","raw_affiliation_strings":["Department of Computer Science and Engineering, Aliah University, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aliah University, Kolkata, India","institution_ids":["https://openalex.org/I180765649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033317672","display_name":"Saurav Mallik","orcid":"https://orcid.org/0000-0003-4107-6784"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saurav Mallik","raw_affiliation_strings":["Center for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0000-0003-4107-6784","affiliations":[{"raw_affiliation_string":"Center for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002225639","display_name":"Amir Sohel","orcid":"https://orcid.org/0000-0001-7810-502X"},"institutions":[{"id":"https://openalex.org/I180765649","display_name":"Aliah University","ror":"https://ror.org/03rfycd69","country_code":"IN","type":"education","lineage":["https://openalex.org/I180765649"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Amir Sohel","raw_affiliation_strings":["Department of Computer Science and Engineering, Aliah University, Kolkata, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Aliah University, Kolkata, India","institution_ids":["https://openalex.org/I180765649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006688612","display_name":"Zhongming Zhao","orcid":"https://orcid.org/0000-0002-3477-0914"},"institutions":[{"id":"https://openalex.org/I919571938","display_name":"The University of Texas Health Science Center at Houston","ror":"https://ror.org/03gds6c39","country_code":"US","type":"education","lineage":["https://openalex.org/I919571938"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhongming Zhao","raw_affiliation_strings":["Center of Precision Health, School of Biomedical Informatices and Human Genetics Center, School of Public Health, MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, The University of Texas Health Science Center at Houston, Houston, TX, USA"],"raw_orcid":"https://orcid.org/0000-0002-3477-0914","affiliations":[{"raw_affiliation_string":"Center of Precision Health, School of Biomedical Informatices and Human Genetics Center, School of Public Health, MD Anderson Cancer Center UTHealth Graduate School of Biomedical Sciences, The University of Texas Health Science Center at Houston, Houston, TX, USA","institution_ids":["https://openalex.org/I919571938"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025631339"],"corresponding_institution_ids":["https://openalex.org/I180765649"],"apc_list":null,"apc_paid":null,"fwci":0.5699,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.64845375,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"19","issue":"3","first_page":"1354","last_page":"1364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9983999729156494,"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/T10062","display_name":"MicroRNA in disease regulation","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1306","display_name":"Cancer Research"},"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9936000108718872,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.7106606364250183},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6166707277297974},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5881313681602478},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5175070762634277},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49773862957954407},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4846854507923126},{"id":"https://openalex.org/keywords/biomarker-discovery","display_name":"Biomarker discovery","score":0.47599542140960693},{"id":"https://openalex.org/keywords/k-nearest-neighbors-algorithm","display_name":"k-nearest neighbors algorithm","score":0.45657089352607727},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.45008981227874756},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.44648998975753784},{"id":"https://openalex.org/keywords/singular-value-decomposition","display_name":"Singular value decomposition","score":0.4141649305820465},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.15741124749183655},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.1343669593334198},{"id":"https://openalex.org/keywords/proteomics","display_name":"Proteomics","score":0.1055682897567749},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.0859835147857666}],"concepts":[{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.7106606364250183},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6166707277297974},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5881313681602478},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5175070762634277},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49773862957954407},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4846854507923126},{"id":"https://openalex.org/C124535831","wikidata":"https://www.wikidata.org/wiki/Q4915074","display_name":"Biomarker discovery","level":4,"score":0.47599542140960693},{"id":"https://openalex.org/C113238511","wikidata":"https://www.wikidata.org/wiki/Q1071612","display_name":"k-nearest neighbors algorithm","level":2,"score":0.45657089352607727},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.45008981227874756},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.44648998975753784},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.4141649305820465},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.15741124749183655},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.1343669593334198},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.1055682897567749},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0859835147857666},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D015470","descriptor_name":"Leukemia, Myeloid, Acute","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D015470","descriptor_name":"Leukemia, Myeloid, Acute","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D015470","descriptor_name":"Leukemia, Myeloid, Acute","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2021.3110989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2021.3110989","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34495838","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34495838","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2673124498","display_name":null,"funder_award_id":"CPRIT RP170668","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"},{"id":"https://openalex.org/G431924609","display_name":null,"funder_award_id":"RP180734","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"},{"id":"https://openalex.org/G8100577519","display_name":null,"funder_award_id":"RP210045","funder_id":"https://openalex.org/F4320308129","funder_display_name":"Cancer Prevention and Research Institute of Texas"}],"funders":[{"id":"https://openalex.org/F4320308129","display_name":"Cancer Prevention and Research Institute of Texas","ror":"https://ror.org/0003xa228"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1808644423","https://openalex.org/W1988592429","https://openalex.org/W2000124990","https://openalex.org/W2017337590","https://openalex.org/W2048178552","https://openalex.org/W2060542593","https://openalex.org/W2077118844","https://openalex.org/W2080420136","https://openalex.org/W2081060988","https://openalex.org/W2081098333","https://openalex.org/W2082749834","https://openalex.org/W2099111195","https://openalex.org/W2099322651","https://openalex.org/W2128873747","https://openalex.org/W2133462743","https://openalex.org/W2133990480","https://openalex.org/W2140703956","https://openalex.org/W2149772057","https://openalex.org/W2154053567","https://openalex.org/W2154297838","https://openalex.org/W2156483112","https://openalex.org/W2158933803","https://openalex.org/W2395576310","https://openalex.org/W2586426327","https://openalex.org/W2766924555","https://openalex.org/W2890222565","https://openalex.org/W2948909630","https://openalex.org/W2949421741","https://openalex.org/W3028304854","https://openalex.org/W3039177529","https://openalex.org/W3112502911","https://openalex.org/W3131008709","https://openalex.org/W3132891126","https://openalex.org/W4299823361","https://openalex.org/W6674952872","https://openalex.org/W6681822384","https://openalex.org/W6712069013"],"related_works":["https://openalex.org/W3121932492","https://openalex.org/W4232638561","https://openalex.org/W1997544008","https://openalex.org/W1607100495","https://openalex.org/W3004137470","https://openalex.org/W131378092","https://openalex.org/W1598328844","https://openalex.org/W2943300910","https://openalex.org/W4240956634","https://openalex.org/W3028106195"],"abstract_inverted_index":{"In":[0],"this":[1],"article,":[2],"we":[3],"propose":[4],"a":[5,192],"novel":[6],"unsupervised":[7],"feature":[8,14,27,36,46,52,61,67,115,132],"selection":[9,62,133],"method":[10,63,219],"by":[11,29,206],"combining":[12],"hierarchical":[13,32],"clustering":[15,33],"with":[16,198],"singular":[17],"value":[18],"decomposition":[19],"(SVD).":[20],"The":[21,59,117,149,184,218],"proposed":[22,60,123,153],"algorithm":[23,124,154],"first":[24],"generates":[25],"several":[26,128],"clusters":[28,47],"adopting":[30],"the":[31,35,51,57,73,77,83,87,101,106,113,122,152,216,229],"on":[34],"space":[37],"and":[38,146,177,212,220],"then":[39],"applies":[40],"SVD":[41],"to":[42,48,56,96],"each":[43],"of":[44,86,100,112,131,136,151,159,168,231],"these":[45],"find":[49],"out":[50],"that":[53,69,121,166],"contributes":[54,105],"most":[55],"SVD-entropy.":[58],"selects":[64],"an":[65,199],"optimal":[66],"subset":[68],"not":[70],"only":[71],"minimizes":[72],"mutual":[74,84],"dependency":[75,85],"among":[76,109],"selected":[78,88,102],"features":[79,89,95,103,111],"but":[80],"also":[81,104],"maximizes":[82],"against":[90,127],"their":[91],"nearest":[92],"neighbor":[93],"non-selected":[94],"some":[97],"extent.":[98],"Each":[99],"maximum":[107],"SVD-entropy":[108],"all":[110],"same":[114],"cluster.":[116],"experimental":[118],"results":[119,221],"demonstrate":[120],"performs":[125],"well":[126],"state-of-the-art":[129],"methods":[130],"in":[134,215,228,232],"terms":[135],"various":[137],"evaluation":[138],"criteria":[139],"such":[140],"as":[141],"classification":[142],"accuracy,":[143],"redundancy":[144],"rate,":[145],"representation":[147],"entropy.":[148],"superiority":[150],"is":[155,204],"demonstrated":[156],"through":[157],"analysis":[158,190],"Acute":[160],"Myeloid":[161],"Leukemia":[162],"(AML)":[163],"multi-omics":[164],"data":[165],"consist":[167],"five":[169],"datasets:":[170],"gene":[171],"expression,":[172,174],"exon":[173],"methylation,":[175],"microRNA,":[176],"pathway":[178],"activity":[179],"dataset":[180],"(paradigm":[181],"IPLs)":[182],"from":[183],"Cancer":[185],"Genome":[186],"Atlas":[187],"(TCGA).":[188],"Our":[189],"pinpoints":[191],"candidate":[193],"gene-marker,":[194],"EREG":[195,203],"for":[196,225],"AML":[197],"integrative":[200],"omics":[201],"evidence.":[202],"targeted":[205],"two":[207],"top":[208],"ranked":[209],"microRNAs,":[210],"hsa-miR-1286":[211],"hsa-miR-1976,":[213],"here":[214],"datasets.":[217],"will":[222],"be":[223],"useful":[224],"biomarker":[226],"discovery":[227],"era":[230],"precision":[233],"medicine.":[234]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-19T08:33:51.333923","created_date":"2025-10-10T00:00:00"}