{"id":"https://openalex.org/W2078669100","doi":"https://doi.org/10.1145/1014052.1014099","title":"A rank sum test method for informative gene discovery","display_name":"A rank sum test method for informative gene discovery","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W2078669100","doi":"https://doi.org/10.1145/1014052.1014099","mag":"2078669100"},"language":"en","primary_location":{"id":"doi:10.1145/1014052.1014099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5110259343","display_name":"Lin Deng","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lin Deng","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]},{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["CA","US"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["State University of New York at Buffalo, NY and Simon Fraser University, Canada"],"affiliations":[{"raw_affiliation_string":"State University of New York at Buffalo, NY and Simon Fraser University, Canada","institution_ids":["https://openalex.org/I63190737","https://openalex.org/I18014758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108638166","display_name":"Jinwen Ma","orcid":"https://orcid.org/0009-0006-5861-1957"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinwen Ma","raw_affiliation_strings":["Peking University, Beijing, China","Peking University, Beijing, China#TAB#"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University, Beijing, China#TAB#","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036572194","display_name":"Dik Lun Lee","orcid":"https://orcid.org/0000-0002-2413-3882"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Dik Lun Lee","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5110259343"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.6029,"has_fulltext":false,"cited_by_count":68,"citation_normalized_percentile":{"value":0.65342134,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"410","last_page":"419"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9879999756813049,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9485999941825867,"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/discriminative-model","display_name":"Discriminative model","score":0.6390763521194458},{"id":"https://openalex.org/keywords/statistic","display_name":"Statistic","score":0.5937569737434387},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.5650817155838013},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5491290092468262},{"id":"https://openalex.org/keywords/test-statistic","display_name":"Test statistic","score":0.5314998030662537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5249438285827637},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5189016461372375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5118524432182312},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5104936361312866},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4480823874473572},{"id":"https://openalex.org/keywords/test-data","display_name":"Test data","score":0.4306098222732544},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41718778014183044},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4096718430519104},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3965553045272827}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6390763521194458},{"id":"https://openalex.org/C89128539","wikidata":"https://www.wikidata.org/wiki/Q1949963","display_name":"Statistic","level":2,"score":0.5937569737434387},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.5650817155838013},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5491290092468262},{"id":"https://openalex.org/C169857963","wikidata":"https://www.wikidata.org/wiki/Q1461038","display_name":"Test statistic","level":3,"score":0.5314998030662537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5249438285827637},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5189016461372375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5118524432182312},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5104936361312866},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4480823874473572},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4306098222732544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41718778014183044},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4096718430519104},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3965553045272827},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1014052.1014099","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1014052.1014099","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.420.7468","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.420.7468","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sfu.ca/~jpei/publications/ranksum-vldb04.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.85.6063","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.85.6063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.sfu.ca/~jpei/publications/ranksum-kdd04.pdf","raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-9944","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-9944","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W131436534","https://openalex.org/W238668910","https://openalex.org/W1490760466","https://openalex.org/W1576520375","https://openalex.org/W1607350267","https://openalex.org/W1966701961","https://openalex.org/W1995471966","https://openalex.org/W2033903399","https://openalex.org/W2059495650","https://openalex.org/W2087684630","https://openalex.org/W2108728387","https://openalex.org/W2109363337","https://openalex.org/W2122599407","https://openalex.org/W2128036349","https://openalex.org/W2143426320","https://openalex.org/W2145683967","https://openalex.org/W2797177778","https://openalex.org/W3020976948","https://openalex.org/W4230946174","https://openalex.org/W4252684946","https://openalex.org/W4300973687","https://openalex.org/W6629451354","https://openalex.org/W6634442568","https://openalex.org/W7011828667"],"related_works":["https://openalex.org/W3015822731","https://openalex.org/W2957280400","https://openalex.org/W2075332338","https://openalex.org/W1970221037","https://openalex.org/W4386776152","https://openalex.org/W1826709224","https://openalex.org/W2135903028","https://openalex.org/W2488034322","https://openalex.org/W2913739054","https://openalex.org/W4385820860"],"abstract_inverted_index":{"Finding":[0],"informative":[1,105,131,195],"genes":[2,35,196],"from":[3,231],"microarray":[4],"data":[5,66,85,201,205,217],"is":[6,162,247],"an":[7,253],"important":[8],"research":[9,13],"problem":[10],"in":[11,83,94,147,172],"bioinformatics":[12],"and":[14,28,44,165,206,218],"applications.":[15],"Most":[16],"of":[17,33,53,60,90,127,130,177],"the":[18,57,65,76,88,91,115,122,128,134,144,151,158,169,175,178,193,215,221,232],"existing":[19],"methods":[20,54],"rank":[21,100,159,179],"features":[22],"according":[23,72],"to":[24,73,155,188],"their":[25],"discriminative":[26,34],"capability":[27],"then":[29],"find":[30],"a":[31,68,99,111,141],"subset":[32],"(usually":[36],"top":[37],"k":[38],"genes).":[39],"In":[40],"particular,":[41],"t-statistic":[42,170],"criterion":[43],"its":[45],"variants":[46],"have":[47],"been":[48],"adopted":[49],"extensively.":[50],"This":[51],"kind":[52],"rely":[55],"on":[56,192,197,214,220],"statistics":[58],"principle":[59],"t-test,":[61],"which":[62],"requires":[63],"that":[64,157,242],"follows":[67],"normal":[69],"distribution.":[70],"However,":[71],"our":[74],"investigation,":[75],"normality":[77,92],"condition":[78],"often":[79],"cannot":[80],"be":[81],"met":[82],"real":[84],"sets.To":[86],"avoid":[87],"assumption":[89],"condition,":[93],"this":[95],"paper,":[96],"we":[97,119,182,239],"propose":[98,120],"sum":[101,160,180],"test":[102],"method":[103,109,161,171],"for":[104],"gene":[106],"discovery.":[107],"The":[108,136,209,224],"uses":[110],"rank-sum":[112],"statistic":[113],"as":[114,133,140],"ranking":[116,235],"criterion.":[117],"Moreover,":[118],"using":[121,243],"significance":[123,137,244],"level":[124,138,245],"threshold,":[125],"instead":[126],"number":[129],"genes,":[132],"parameter.":[135],"threshold":[139,246],"parameter":[142],"carries":[143],"quality":[145],"specification":[146],"statistics.":[148],"We":[149],"follow":[150],"Pitman":[152],"efficiency":[153],"theory":[154],"show":[156],"more":[163,166,248],"accurate":[164],"robust":[167],"than":[168,229,250],"theory.To":[173],"verify":[174,241],"effectiveness":[176],"method,":[181],"use":[183],"support":[184],"vector":[185],"machine":[186],"(SVM)":[187],"construct":[189],"classifiers":[190],"based":[191],"identified":[194],"two":[198],"well":[199],"known":[200],"sets,":[202],"namely":[203],"colon":[204,216],"leukemia":[207,222],"data.":[208,223],"prediction":[210],"accuracy":[211],"reaches":[212],"96.2%":[213],"100%":[219],"results":[225],"are":[226],"clearly":[227],"better":[228],"those":[230],"previous":[233],"feature":[234],"methods.":[236],"By":[237],"experiments,":[238],"also":[240],"effective":[249],"directly":[251],"specifying":[252],"arbitrary":[254],"k.":[255]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}