{"id":"https://openalex.org/W2114933215","doi":"https://doi.org/10.1093/bioinformatics/bth499","title":"Missing value estimation for DNA microarray gene expression data: local least squares imputation","display_name":"Missing value estimation for DNA microarray gene expression data: local least squares imputation","publication_year":2004,"publication_date":"2004-08-27","ids":{"openalex":"https://openalex.org/W2114933215","doi":"https://doi.org/10.1093/bioinformatics/bth499","mag":"2114933215","pmid":"https://pubmed.ncbi.nlm.nih.gov/15333461"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth499","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth499","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/2/187/48962001/bioinformatics_21_2_187.pdf","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":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/21/2/187/48962001/bioinformatics_21_2_187.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100441148","display_name":"Hyunsoo Kim","orcid":"https://orcid.org/0000-0002-8441-3376"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyunsoo Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, 200 Union Street S.E., Minneapolis, MN 55455, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, 200 Union Street S.E., Minneapolis, MN 55455, USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110003399","display_name":"Gene H. Golub","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gene H. Golub","raw_affiliation_strings":["Computer Science Department, Stanford University Gates Building 2B #280, Stanford, CA 94305-9025, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, Stanford University Gates Building 2B #280, Stanford, CA 94305-9025, USA#TAB#","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101728710","display_name":"Haesun Park","orcid":"https://orcid.org/0000-0001-6259-7170"},"institutions":[{"id":"https://openalex.org/I130238516","display_name":"University of Minnesota","ror":"https://ror.org/017zqws13","country_code":"US","type":"education","lineage":["https://openalex.org/I130238516"]},{"id":"https://openalex.org/I4210101327","display_name":"Twin Cities Orthopedics","ror":"https://ror.org/01en4s460","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210101327"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haesun Park","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Minnesota Twin Cities, 200 Union Street S.E., Minneapolis, MN 55455, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Minnesota Twin Cities, 200 Union Street S.E., Minneapolis, MN 55455, USA","institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100441148"],"corresponding_institution_ids":["https://openalex.org/I130238516","https://openalex.org/I4210101327"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":6.5055,"has_fulltext":false,"cited_by_count":489,"citation_normalized_percentile":{"value":0.97732071,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"21","issue":"2","first_page":"187","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.8483999967575073,"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":0.8483999967575073,"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/T10136","display_name":"Statistical Methods and Inference","score":0.017100000753998756,"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/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.014399999752640724,"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/missing-data","display_name":"Missing data","score":0.8052065372467041},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.7090128064155579},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6188832521438599},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5111225247383118},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5001780986785889},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4514913558959961},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4351866841316223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3711894154548645}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8052065372467041},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.7090128064155579},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6188832521438599},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5111225247383118},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5001780986785889},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4514913558959961},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4351866841316223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3711894154548645}],"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":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016018","descriptor_name":"Least-Squares Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D018401","descriptor_name":"Sample Size","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":4,"locations":[{"id":"doi:10.1093/bioinformatics/bth499","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth499","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/2/187/48962001/bioinformatics_21_2_187.pdf","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:15333461","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/15333461","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":"Comparative Study"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.7824","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.7824","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://sci2s.ugr.es/keel/pdf/algorithm/articulo/2005-Kim-B.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.857.270","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.857.270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/content/early/2004/08/27/bioinformatics.bth499.full.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/bth499","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth499","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/21/2/187/48962001/bioinformatics_21_2_187.pdf","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309636","display_name":"University of Minnesota","ror":"https://ror.org/03grvy078"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2114933215.pdf"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981745143","https://openalex.org/W2018961890","https://openalex.org/W2022852240","https://openalex.org/W2064208261","https://openalex.org/W2096863518","https://openalex.org/W2097255042","https://openalex.org/W2103453943","https://openalex.org/W2109363337","https://openalex.org/W2111104102","https://openalex.org/W2128985829","https://openalex.org/W2129256542","https://openalex.org/W2137843728","https://openalex.org/W2148541040","https://openalex.org/W2156909104","https://openalex.org/W2162302435","https://openalex.org/W2162735386","https://openalex.org/W2171088586","https://openalex.org/W2171118759","https://openalex.org/W6685081291"],"related_works":["https://openalex.org/W2181530120","https://openalex.org/W4211215373","https://openalex.org/W2024529227","https://openalex.org/W2055961818","https://openalex.org/W1574575415","https://openalex.org/W3144172081","https://openalex.org/W3179858851","https://openalex.org/W3028371478","https://openalex.org/W2081476516","https://openalex.org/W2581984549"],"abstract_inverted_index":{"MOTIVATION:":[0],"Gene":[1],"expression":[2,7,21,52],"data":[3,22,61],"often":[4],"contain":[5],"missing":[6,10,47,84,115,146,155],"values.":[8,31],"Effective":[9],"value":[11,147],"estimation":[12,117,148],"methods":[13,36,144],"are":[14,43,96,121],"needed":[15],"since":[16],"many":[17],"algorithms":[18],"for":[19,145],"gene":[20,29,51,81],"analysis":[23],"require":[24],"a":[25,79,87],"complete":[26],"matrix":[27],"of":[28,90,110,119,154],"array":[30],"In":[32,129],"this":[33],"paper,":[34],"imputation":[35,75,143],"based":[37],"on":[38,149],"the":[39,50,60,132,158],"least":[40,65,73],"squares":[41,66,74],"formulation":[42],"proposed":[44,71,133],"to":[45],"estimate":[46],"values":[48,85,109,116,156],"in":[49,59,157],"data,":[53],"which":[54],"exploit":[55],"local":[56,72],"similarity":[57],"structures":[58],"as":[62,64,86],"well":[63],"optimization":[67],"process.":[68],"RESULTS:":[69],"The":[70,93,161],"method":[76,118,135],"(LLSimpute)":[77],"represents":[78],"target":[80],"that":[82,105],"has":[83],"linear":[88],"combination":[89],"similar":[91,94],"genes.":[92],"genes":[95,104],"chosen":[97],"by":[98,123],"k-nearest":[99],"neighbors":[100],"or":[101],"k":[102],"coherent":[103],"have":[106],"large":[107],"absolute":[108],"Pearson":[111],"correlation":[112],"coefficients.":[113],"Non-parametric":[114],"LLSimpute":[120,134],"designed":[122],"introducing":[124],"an":[125],"automatic":[126],"k-value":[127],"estimator.":[128],"our":[130],"experiments,":[131],"shows":[136],"competitive":[137],"results":[138],"when":[139],"compared":[140],"with":[141],"other":[142],"various":[150],"datasets":[151],"and":[152],"percentages":[153],"data.":[159],"AVAILABILITY:":[160],"software":[162],"is":[163],"available":[164],"at":[165],"http://www.cs.umn.edu/~hskim/tools.html":[166],"CONTACT:":[167],"hpark@cs.umn.edu":[168]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":18},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":27},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":25},{"year":2015,"cited_by_count":32},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":23},{"year":2012,"cited_by_count":25}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
