{"id":"https://openalex.org/W2141823231","doi":"https://doi.org/10.1093/bioinformatics/btg039","title":"Simultaneous gene clustering and subset selection for sample classification via MDL","display_name":"Simultaneous gene clustering and subset selection for sample classification via MDL","publication_year":2003,"publication_date":"2003-06-11","ids":{"openalex":"https://openalex.org/W2141823231","doi":"https://doi.org/10.1093/bioinformatics/btg039","mag":"2141823231","pmid":"https://pubmed.ncbi.nlm.nih.gov/12801870"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btg039","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg039","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/9/1100/48904206/bioinformatics_19_9_1100.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/19/9/1100/48904206/bioinformatics_19_9_1100.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050648584","display_name":"Rebecka J\u00f6rnsten","orcid":"https://orcid.org/0000-0002-2550-3494"},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]},{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Rebecka J\u00f6rnsten","raw_affiliation_strings":["Department of Statistics, Rutgers University, 501 Hill Center, Piscataway, NJ 08854, USA. rebecka@stat.rutgers.edu","Department of Statistics, Rutgers University, 501 Hill Center, Piscataway, NJ 08854, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, Rutgers University, 501 Hill Center, Piscataway, NJ 08854, USA. rebecka@stat.rutgers.edu","institution_ids":["https://openalex.org/I102322142","https://openalex.org/I4210096112"]},{"raw_affiliation_string":"Department of Statistics, Rutgers University, 501 Hill Center, Piscataway, NJ 08854, USA","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100646131","display_name":"Bin Yu","orcid":"https://orcid.org/0000-0002-2453-7852"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bin Yu","raw_affiliation_strings":["Department of Statistics, UC Berkeley, 367 Evans Hall, Berkeley, CA 94720, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, UC Berkeley, 367 Evans Hall, Berkeley, CA 94720, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":3.0786,"has_fulltext":true,"cited_by_count":81,"citation_normalized_percentile":{"value":0.92038239,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"9","first_page":"1100","last_page":"1109"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.968500018119812,"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":0.968500018119812,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.01600000075995922,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.003000000026077032,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8112847805023193},{"id":"https://openalex.org/keywords/centroid","display_name":"Centroid","score":0.659379243850708},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.6218022108078003},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5694397687911987},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5273500084877014},{"id":"https://openalex.org/keywords/gene-selection","display_name":"Gene selection","score":0.5185495018959045},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4424932301044464},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4298778474330902},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.4282483458518982},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41262632608413696},{"id":"https://openalex.org/keywords/affinity-propagation","display_name":"Affinity propagation","score":0.41032034158706665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40920767188072205},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36770811676979065},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.34278440475463867},{"id":"https://openalex.org/keywords/microarray-analysis-techniques","display_name":"Microarray analysis techniques","score":0.26623934507369995},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.25305676460266113},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.22562068700790405},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1948702037334442},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.19212603569030762},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17720043659210205},{"id":"https://openalex.org/keywords/gene-expression","display_name":"Gene expression","score":0.15341484546661377}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8112847805023193},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.659379243850708},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.6218022108078003},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5694397687911987},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5273500084877014},{"id":"https://openalex.org/C2984324147","wikidata":"https://www.wikidata.org/wiki/Q3080021","display_name":"Gene selection","level":5,"score":0.5185495018959045},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4424932301044464},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4298778474330902},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4282483458518982},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41262632608413696},{"id":"https://openalex.org/C109659709","wikidata":"https://www.wikidata.org/wiki/Q3407504","display_name":"Affinity propagation","level":5,"score":0.41032034158706665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40920767188072205},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36770811676979065},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.34278440475463867},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.26623934507369995},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25305676460266113},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.22562068700790405},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1948702037334442},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.19212603569030762},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17720043659210205},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.15341484546661377},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"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":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D003110","descriptor_name":"Colonic Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D007938","descriptor_name":"Leukemia","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"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":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009369","descriptor_name":"Neoplasms","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","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":"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":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D015972","descriptor_name":"Gene Expression Regulation, Neoplastic","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D025341","descriptor_name":"Principal Component Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D045744","descriptor_name":"Cell Line, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D045744","descriptor_name":"Cell Line, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D045744","descriptor_name":"Cell Line, Tumor","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btg039","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg039","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/9/1100/48904206/bioinformatics_19_9_1100.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:12801870","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/12801870","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":{"id":"doi:10.1093/bioinformatics/btg039","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btg039","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/19/9/1100/48904206/bioinformatics_19_9_1100.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":[{"id":"https://openalex.org/G8065475703","display_name":"Discriminant Analysis of Hyperspectral Data for Bio         Species Recognition","funder_award_id":"9803063","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2141823231.pdf","grobid_xml":"https://content.openalex.org/works/W2141823231.grobid-xml"},"referenced_works_count":13,"referenced_works":["https://openalex.org/W183258039","https://openalex.org/W1608932033","https://openalex.org/W1966701961","https://openalex.org/W1973217014","https://openalex.org/W1989076816","https://openalex.org/W2042328724","https://openalex.org/W2056392803","https://openalex.org/W2087684630","https://openalex.org/W2109363337","https://openalex.org/W2115996640","https://openalex.org/W2122759946","https://openalex.org/W4237937969","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W3049268462","https://openalex.org/W4200482842","https://openalex.org/W3208326136","https://openalex.org/W2045437074","https://openalex.org/W4301079385","https://openalex.org/W2953024232","https://openalex.org/W2970287821","https://openalex.org/W2992603957","https://openalex.org/W4298875530","https://openalex.org/W2017920586"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,16,39,65,157,341,354],"microarray":[2],"technology":[3],"allows":[4],"for":[5,13,84,106,118,146,185,192],"the":[6,52,85,99,107,137,161,176,180,220,231,249,252,261,264,281,288,292,322,329,338,351,360],"simultaneous":[7,108,186],"monitoring":[8],"of":[9,11,27,44,55,90,110,115,160,217,254,263,283,324],"thousands":[10],"genes":[12,111,178,289],"each":[14],"sample.":[15],"high-dimensional":[17],"gene":[18,28,37,49,63,66,116,187,242,306,330],"expression":[19,29],"data":[20,200,205],"can":[21],"be":[22,42],"used":[23],"to":[24,34,48,179,196,291,301],"study":[25],"similarities":[26],"profiles":[30],"across":[31,271],"different":[32,272],"samples":[33],"form":[35],"a":[36,77,123,165,257,325],"clustering.":[38],"clusters":[40,117,255,265,284],"may":[41,94],"indicative":[43],"genetic":[45],"pathways.":[46],"Parallel":[47],"clustering":[50,67,109,188],"is":[51,144,164,194,357],"important":[53],"application":[54],"sample":[56,69,119],"classification":[57,70,169,193,212,237,326],"based":[58,128,171,214,239,303],"on":[59,129,172,215,240,304,320],"all":[60,203],"or":[61,75,175],"selected":[62],"expressions.":[64],"and":[68,112,151,167,189,210,260],"are":[71,246,266,285,309],"often":[72],"undertaken":[73],"separately,":[74],"in":[76,98,248,337,344,350],"directional":[78],"manner":[79],"(one":[80],"as":[81,230,312,314],"an":[82,104,140],"aid":[83],"other).":[86],"However,":[87],"such":[88],"separation":[89],"these":[91,223],"two":[92],"tasks":[93],"occlude":[95],"informative":[96,335],"structure":[97,336],"data.":[100,339],"Here":[101],"we":[102,207,318],"present":[103],"algorithm":[105,163,184],"subset":[113,190],"selection":[114,126,191],"classification.":[120],"We":[121,276],"develop":[122],"new":[124],"model":[125],"criterion":[127,327],"Rissanen's":[130],"MDL":[131,141],"(minimum":[132],"description":[133],"length)":[134],"principle.":[135],"For":[136,202],"first":[138,361],"time,":[139,222],"code":[142,356],"length":[143],"given":[145],"both":[147],"explanatory":[148],"variables":[149,153],"(genes)":[150],"response":[152],"(sample":[154],"class":[155,334],"labels).":[156],"final":[158],"output":[159],"proposed":[162],"sparse":[166,209,311],"interpretable":[168,211],"rule":[170],"cluster":[173],"centroids":[174,216,262,282],"closest":[177,290],"centroids.":[181,293],"RESULTS:":[182],"Our":[183],"applied":[195],"three":[197,204],"publicly":[198],"available":[199,358],"sets.":[201],"sets,":[206],"obtain":[208],"models":[213,224,238,279,295,302],"clusters.":[218],"At":[219],"same":[221],"give":[225],"competitive":[226],"test":[227,298],"error":[228,299],"rates":[229,300],"best":[232],"reported":[233],"methods.":[234],"Compared":[235],"with":[236,287],"single":[241,305],"selections,":[243],"our":[244],"rules":[245],"stable":[247],"sense":[250],"that":[251],"number":[253],"has":[256],"small":[258],"variability":[259],"well":[267,313],"correlated":[268],"(or":[269],"consistent)":[270],"cross":[273],"validation":[274],"samples.":[275],"also":[277],"discuss":[278],"where":[280],"replaced":[286],"These":[294],"show":[296],"comparable":[297],"selection,":[307],"but":[308],"more":[310,315],"stable.":[316],"Moreover,":[317],"comment":[319],"how":[321],"inclusion":[323],"affects":[328],"clustering,":[331],"bringing":[332],"out":[333],"AVAILABILITY:":[340],"methods":[342],"presented":[343],"this":[345],"paper":[346],"have":[347],"been":[348],"implemented":[349],"R":[352],"language.":[353],"source":[355],"from":[359],"author.":[362]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}