{"id":"https://openalex.org/W2188662811","doi":null,"title":"Mining large-scale Genomic and Proteomic Data: Algorithms, Tools and Inference","display_name":"Mining large-scale Genomic and Proteomic Data: Algorithms, Tools and Inference","publication_year":2007,"publication_date":"2007-01-01","ids":{"openalex":"https://openalex.org/W2188662811","mag":"2188662811"},"language":"en","primary_location":{"id":"mag:2188662811","doi":null,"is_oa":false,"landing_page_url":"http://horn.tau.ac.il/publications/roy_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5090731305","display_name":"Roy Varshavsky","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Roy Varshavsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5090731305"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9984999895095825,"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":0.9984999895095825,"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":0.00039999998989515007,"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":9.999999747378752e-05,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unsupervised-feature-selection","display_name":"unsupervised feature selection","score":0.9089999794960022},{"id":"https://openalex.org/keywords/entropy-based-feature-selection","display_name":"entropy-based feature selection","score":0.6019999980926514},{"id":"https://openalex.org/keywords/forward-selection","display_name":"forward selection","score":0.7459999918937683},{"id":"https://openalex.org/keywords/backward-elimination","display_name":"backward elimination","score":0.9980000257492065},{"id":"https://openalex.org/keywords/feature-ranking","display_name":"feature ranking","score":0.6800000071525574},{"id":"https://openalex.org/keywords/gene-selection","display_name":"gene selection","score":0.5630000233650208},{"id":"https://openalex.org/keywords/gene-ontology-enrichment","display_name":"gene ontology enrichment","score":0.578000009059906},{"id":"https://openalex.org/keywords/genomic-data-mining","display_name":"genomic data mining","score":0.421999990940094}],"concepts":[{"id":"https://openalex.org/C203519979","wikidata":"https://www.wikidata.org/wiki/Q865360","display_name":"Jaccard index","level":3,"score":0.695855975151062},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.679067075252533},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.6557014584541321},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6521537899971008},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5854442119598389},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5506047606468201},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5347949862480164},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49840712547302246},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47274526953697205},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.468118816614151},{"id":"https://openalex.org/C22789450","wikidata":"https://www.wikidata.org/wiki/Q420904","display_name":"Singular value decomposition","level":2,"score":0.4515704810619354},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.4256828725337982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3889862895011902},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2188662811","doi":null,"is_oa":false,"landing_page_url":"http://horn.tau.ac.il/publications/roy_thesis.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":102,"referenced_works":["https://openalex.org/W184018770","https://openalex.org/W1489800245","https://openalex.org/W1492327544","https://openalex.org/W1493217831","https://openalex.org/W1532319248","https://openalex.org/W1564049492","https://openalex.org/W1570448133","https://openalex.org/W1587034566","https://openalex.org/W1587362683","https://openalex.org/W1595315260","https://openalex.org/W1651093245","https://openalex.org/W1727290854","https://openalex.org/W1769049279","https://openalex.org/W1774711529","https://openalex.org/W1836115926","https://openalex.org/W1851949912","https://openalex.org/W1966168239","https://openalex.org/W1968185051","https://openalex.org/W1971318281","https://openalex.org/W1971784203","https://openalex.org/W1975900269","https://openalex.org/W1982481323","https://openalex.org/W1991537543","https://openalex.org/W2000771269","https://openalex.org/W2005049999","https://openalex.org/W2006577689","https://openalex.org/W2010637767","https://openalex.org/W2010785223","https://openalex.org/W2023971898","https://openalex.org/W2042328724","https://openalex.org/W2043108205","https://openalex.org/W2043154233","https://openalex.org/W2044506145","https://openalex.org/W2047555270","https://openalex.org/W2050986127","https://openalex.org/W2053423550","https://openalex.org/W2055101717","https://openalex.org/W2086301041","https://openalex.org/W2087684630","https://openalex.org/W2090182432","https://openalex.org/W2092095117","https://openalex.org/W2095732971","https://openalex.org/W2096863518","https://openalex.org/W2097554668","https://openalex.org/W2099322651","https://openalex.org/W2099841076","https://openalex.org/W2103453943","https://openalex.org/W2106801905","https://openalex.org/W2107383984","https://openalex.org/W2108758729","https://openalex.org/W2109174028","https://openalex.org/W2109204369","https://openalex.org/W2109363337","https://openalex.org/W2109972881","https://openalex.org/W2110065044","https://openalex.org/W2115996640","https://openalex.org/W2116811581","https://openalex.org/W2117270410","https://openalex.org/W2117812871","https://openalex.org/W2119387367","https://openalex.org/W2119479037","https://openalex.org/W2120246066","https://openalex.org/W2124704116","https://openalex.org/W2132292391","https://openalex.org/W2133098435","https://openalex.org/W2135805255","https://openalex.org/W2138745909","https://openalex.org/W2140703956","https://openalex.org/W2140776132","https://openalex.org/W2141087758","https://openalex.org/W2142465702","https://openalex.org/W2142830469","https://openalex.org/W2144368255","https://openalex.org/W2144792853","https://openalex.org/W2147693880","https://openalex.org/W2148541040","https://openalex.org/W2150452501","https://openalex.org/W2150926065","https://openalex.org/W2152183901","https://openalex.org/W2152186880","https://openalex.org/W2152274187","https://openalex.org/W2152491277","https://openalex.org/W2153187042","https://openalex.org/W2158714788","https://openalex.org/W2158997610","https://openalex.org/W2159686118","https://openalex.org/W2160135234","https://openalex.org/W2161732286","https://openalex.org/W2165767110","https://openalex.org/W2165905264","https://openalex.org/W2166902257","https://openalex.org/W2166913844","https://openalex.org/W2168627286","https://openalex.org/W2170798597","https://openalex.org/W2394994061","https://openalex.org/W2477408078","https://openalex.org/W2480518476","https://openalex.org/W2611831635","https://openalex.org/W2799061466","https://openalex.org/W2885041036","https://openalex.org/W3015571647","https://openalex.org/W3138771162"],"related_works":["https://openalex.org/W7096730979","https://openalex.org/W7097209986","https://openalex.org/W2140703956","https://openalex.org/W7099313572","https://openalex.org/W1970833132","https://openalex.org/W1973958131","https://openalex.org/W3162614041","https://openalex.org/W7095809457","https://openalex.org/W7095976478","https://openalex.org/W2563489032"],"abstract_inverted_index":{"Motivation:":[0],"Many":[1],"methods":[2,18,118],"have":[3,207,218],"been":[4],"developed":[5],"for":[6,29,177],"selecting":[7,45],"small":[8,165],"informative":[9],"feature":[10,37,47,136,148,184],"subsets":[11],"in":[12,65,133,200,222],"large":[13],"noisy":[14],"data.":[15],"However,":[16],"unsupervised":[17],"are":[19,22,157],"scarce.":[20],"Examples":[21],"using":[23],"the":[24,33,36,39,53,94,97,102,112,127,131,134,151,160,171,182,196,201,210],"variance":[25,152],"of":[26,35,96,101,109,129,167,181,195,198,250],"data":[27,132],"collected":[28],"each":[30,123],"feature,":[31],"or":[32],"projection":[34],"on":[38,57,163],"first":[40],"principal":[41],"component.Weproposeanovel":[42],"unsupervisedcriterion,":[43],"basedonSVDentropy,":[44],"a":[46,58,164,192],"according":[48,70,80],"to":[49,52,71,81,119,144,189,217],"its":[50],"contribution":[51],"entropy":[54,86],"(CE)":[55],"calculated":[56],"leave-one-out":[59],"basis.":[60],"This":[61,186],"can":[62],"be":[63,190],"implemented":[64],"four":[66],"ways:":[67],"simple":[68],"ranking":[69],"CE":[72,99],"values":[73],"(SR);":[74],"forward":[75,88],"selection":[76,89],"by":[77,90,138],"accumulating":[78,91],"features":[79,92,110],"which":[82],"set":[83,166],"produces":[84],"highest":[85],"(FS1);":[87],"through":[93],"choice":[95],"best":[98,172],"out":[100,188,216],"remaining":[103],"ones":[104],"(FS2);":[105],"backward":[106],"elimination":[107],"(BE)":[108,246],"with":[111,142],"lowest":[113],"CE.":[114],"Results:We":[115],"apply":[116],"our":[117],"different":[120],"benchmarks.":[121],"In":[122],"case":[124],"we":[125,206],"evaluate":[126],"success":[128],"clustering":[130],"selected":[135,168,213],"spaces,":[137],"measuring":[139],"Jaccard":[140],"scores":[141],"respect":[143],"known":[145],"classifications.Wedemonstrate":[146],"that":[147,205],"filteringaccording":[149],"toCEoutperforms":[150],"method":[153],"and":[154],"gene-shaving.":[155],"There":[156],"cases":[158],"where":[159],"analysis,":[161],"based":[162],"features,":[169],"outperforms":[170],"score":[173],"reportedwhenall":[174],"informationwasused.Ourmethod":[175],"calls":[176],"an":[178],"optimal":[179],"size":[180],"relevant":[183,223],"set.":[185],"turns":[187],"just":[191],"few":[193],"percents":[194],"number":[197],"genes":[199,214],"two":[202],"Leukemia":[203],"datasets":[204],"analyzed.":[208],"Moreover,":[209],"most":[211],"favored":[212],"turn":[215],"significant":[219],"GO":[220],"enrichment":[221],"cellular":[224],"processes.":[225],"Abbreviations:":[226],"Singular":[227],"Value":[228],"Decomposition":[229],"(SVD),":[230],"Principal":[231],"Component":[232],"Analysis":[233],"(PCA),":[234],"Quantum":[235],"Clustering":[236],"(QC),":[237],"Gene":[238],"Shaving":[239],"(GS),":[240],"Variance":[241],"Selection":[242],"(VS),":[243],"Backward":[244],"Elimination":[245],"Contact:":[247],"royke@cs.huji.ac.il":[248],"Conflicts":[249],"Interest:":[251],"not":[252],"reported":[253]},"counts_by_year":[],"updated_date":"2026-07-14T23:32:53.992493","created_date":"2016-06-24T00:00:00"}