{"id":"https://openalex.org/W574507516","doi":null,"title":"Learning from positive and unlabeled examples in biology","display_name":"Learning from positive and unlabeled examples in biology","publication_year":2010,"publication_date":"2010-12-15","ids":{"openalex":"https://openalex.org/W574507516","mag":"574507516"},"language":"en","primary_location":{"id":"pmh:hdl:10068/857587","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10068/857587","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/pastel-00566401v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5050871146","display_name":"Fantine Mordelet","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4387153074","display_name":"Cancer et g\u00e9nome: Bioinformatique, biostatistiques et \u00e9pid\u00e9miologie des syst\u00e8mes complexes","ror":"https://ror.org/0095dt357","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I190752583","https://openalex.org/I2746051580","https://openalex.org/I4387153074","https://openalex.org/I70768539","https://openalex.org/I80043"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Fantine Mordelet","raw_affiliation_strings":["Cancer et g\u00e9nome: Bioinformatique, biostatistiques et \u00e9pid\u00e9miologie d'un syst\u00e8me complexe"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cancer et g\u00e9nome: Bioinformatique, biostatistiques et \u00e9pid\u00e9miologie d'un syst\u00e8me complexe","institution_ids":["https://openalex.org/I4387153074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5050871146"],"corresponding_institution_ids":["https://openalex.org/I4387153074"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"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":0.20419999957084656,"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":0.20419999957084656,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.09390000253915787,"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/T10621","display_name":"Gene Regulatory Network Analysis","score":0.07890000194311142,"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/positive-unlabeled-learning","display_name":"positive-unlabeled learning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/gene-regulatory-network-inference","display_name":"gene regulatory network inference","score":0.6269999742507935},{"id":"https://openalex.org/keywords/disease-gene-discovery","display_name":"disease gene discovery","score":0.6899999976158142},{"id":"https://openalex.org/keywords/transcription-factors","display_name":"transcription factors","score":0.6129999756813049},{"id":"https://openalex.org/keywords/high-throughput-biological-data","display_name":"high-throughput biological data","score":0.7260000109672546},{"id":"https://openalex.org/keywords/gene-prioritization","display_name":"gene prioritization","score":0.5059999823570251},{"id":"https://openalex.org/keywords/gene-expression-data","display_name":"gene expression data","score":0.3109999895095825}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7537206411361694},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6562324166297913},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.5469213128089905},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5153805613517761},{"id":"https://openalex.org/C67339327","wikidata":"https://www.wikidata.org/wiki/Q1502576","display_name":"Gene regulatory network","level":4,"score":0.4688611626625061},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4682183265686035},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.46147724986076355},{"id":"https://openalex.org/C2777615720","wikidata":"https://www.wikidata.org/wiki/Q11888847","display_name":"Prioritization","level":2,"score":0.4541385769844055},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.450021356344223},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4373052716255188},{"id":"https://openalex.org/C28225019","wikidata":"https://www.wikidata.org/wiki/Q4915005","display_name":"Biological network","level":2,"score":0.41350674629211426},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.37298303842544556},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29079145193099976},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.24093693494796753},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.15346822142601013},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.12301579117774963},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10354173183441162},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.09083440899848938},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08842501044273376},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:hdl:10068/857587","doi":null,"is_oa":false,"landing_page_url":"http://hdl.handle.net/10068/857587","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},{"id":"pmh:oai:HAL:pastel-00566401v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/pastel-00566401v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics [q-bio.QM]. \u00c9cole Nationale Sup\u00e9rieure des Mines de Paris, 2010. English. ⟨NNT : 2010ENMP0058⟩","raw_type":"info:eu-repo/semantics/doctoralThesis"},{"id":"mag:574507516","doi":null,"is_oa":false,"landing_page_url":"https://pastel.archives-ouvertes.fr/pastel-00566401","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":{"id":"pmh:oai:HAL:pastel-00566401v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/pastel-00566401v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics [q-bio.QM]. \u00c9cole Nationale Sup\u00e9rieure des Mines de Paris, 2010. English. ⟨NNT : 2010ENMP0058⟩","raw_type":"info:eu-repo/semantics/doctoralThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":77,"referenced_works":["https://openalex.org/W22461475","https://openalex.org/W61101988","https://openalex.org/W795561076","https://openalex.org/W1479807131","https://openalex.org/W1537348014","https://openalex.org/W1538189649","https://openalex.org/W1542652324","https://openalex.org/W1560724230","https://openalex.org/W1570564798","https://openalex.org/W1581219065","https://openalex.org/W1605479404","https://openalex.org/W1873158149","https://openalex.org/W1986280275","https://openalex.org/W1995897489","https://openalex.org/W2020301095","https://openalex.org/W2022756254","https://openalex.org/W2031823405","https://openalex.org/W2038122249","https://openalex.org/W2048679005","https://openalex.org/W2055043387","https://openalex.org/W2059682917","https://openalex.org/W2070412833","https://openalex.org/W2070448217","https://openalex.org/W2070934708","https://openalex.org/W2076372398","https://openalex.org/W2078450879","https://openalex.org/W2087347434","https://openalex.org/W2091879895","https://openalex.org/W2096152098","https://openalex.org/W2097498614","https://openalex.org/W2099862356","https://openalex.org/W2100549317","https://openalex.org/W2100672820","https://openalex.org/W2104261859","https://openalex.org/W2105431236","https://openalex.org/W2105813018","https://openalex.org/W2107008379","https://openalex.org/W2108181223","https://openalex.org/W2109555487","https://openalex.org/W2115108153","https://openalex.org/W2119220491","https://openalex.org/W2119582780","https://openalex.org/W2121150592","https://openalex.org/W2123280311","https://openalex.org/W2123958887","https://openalex.org/W2128487019","https://openalex.org/W2128817214","https://openalex.org/W2130652100","https://openalex.org/W2132870739","https://openalex.org/W2133227149","https://openalex.org/W2134092975","https://openalex.org/W2135000328","https://openalex.org/W2137233422","https://openalex.org/W2137518425","https://openalex.org/W2139489886","https://openalex.org/W2141873373","https://openalex.org/W2142237411","https://openalex.org/W2142968125","https://openalex.org/W2144752499","https://openalex.org/W2146179241","https://openalex.org/W2148603752","https://openalex.org/W2153933562","https://openalex.org/W2154654747","https://openalex.org/W2156750171","https://openalex.org/W2159675211","https://openalex.org/W2161444669","https://openalex.org/W2163485494","https://openalex.org/W2164362099","https://openalex.org/W2170866859","https://openalex.org/W2294273376","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W2916288174","https://openalex.org/W2917375902","https://openalex.org/W3119651796","https://openalex.org/W3152020487","https://openalex.org/W4239510810"],"related_works":["https://openalex.org/W7151804070","https://openalex.org/W2403803761","https://openalex.org/W3106686059","https://openalex.org/W2404209711","https://openalex.org/W7150897066","https://openalex.org/W7147139489","https://openalex.org/W7144144085","https://openalex.org/W2001632023","https://openalex.org/W2990447207","https://openalex.org/W2625958347"],"abstract_inverted_index":{"Biology":[0],"is":[1,153,168,192,220,271,281,292,368,413,431,436,470,484,524,532],"a":[2,70,94,150,223,245,290,300,328,337,390,404,419,426,474,485,556],"field":[3,104,359],"where":[4],"an":[5,422,513],"enormous":[6],"amount":[7],"of":[8,61,82,88,105,117,146,171,195,214,226,299,309,341,360,365,371,410,418,425,458,465,480,506],"knowledge":[9],"remains":[10],"to":[11,37,40,58,68,101,112,125,216,221,231,284,287,336,378,414,448,462,472,492,540,549],"be":[12,232],"discovered.":[13],"There":[14],"are":[15,23,27,45,109,210,249,307,325,334],"many":[16,42],"problems":[17,147,241,252],"for":[18,79,97,137,148,235,253,314,317,393,477,495,515,534],"which":[19,149,254,318,430,489,523],"traditional":[20],"laboratory":[21],"techniques":[22],"overwhelmed.":[24],"Whether":[25],"they":[26,35,248,324,333],"time":[28],"consuming,":[29],"expensive,":[30],"error-prone":[31],"or":[32,228,263,331],"low":[33],"throughput,":[34],"struggle":[36],"bring":[38],"answers":[39],"these":[41,53,89],"questions":[43],"that":[44,140,289,432],"left":[46],"unanswered.":[47],"In":[48,205,381],"parallel,":[49],"biotechnologies":[50],"have":[51],"evolved":[52],"past":[54],"decades":[55],"giving":[56],"rise":[57],"mass":[59],"production":[60],"biological":[62,84,138,274,379],"data.":[63],"High-throughput":[64],"experiments":[65,122],"now":[66],"allow":[67],"characterize":[69],"cell":[71],"at":[72],"the":[73,80,103,115,169,186,193,218,296,303,358,369,382,387,411,433,449,463,499,504,527],"genome-scale,":[74],"raising":[75],"great":[76],"expectations":[77],"as":[78],"understanding":[81],"complex":[83],"phenomenons.":[85],"The":[86,239,339,363,407,467,530],"combination":[87],"two":[90,240],"facts":[91],"has":[92,352],"induced":[93],"growing":[95],"need":[96],"mathematicians":[98],"and":[99,161,181,279,345,375,396,401,460,538],"statisticians":[100],"enter":[102],"biology.":[106],"Not":[107],"only":[108],"bioinformaticians":[110],"required":[111],"analyze":[113],"efficiently":[114],"tons":[116],"data":[118,270,543],"coming":[119],"from":[120,343,526],"high-throughput":[121],"in":[123,134,258,295,355,357,456],"order":[124],"extract":[126],"reliable":[127],"information":[128],"but":[129,267],"their":[130,182,376],"work":[131],"also":[132,348],"consists":[133],"building":[135],"models":[136],"systems":[139],"result":[141],"into":[142],"useful":[143],"predictions.":[144],"Examples":[145],"such":[151],"expertise":[152],"needed":[154],"encompass":[155],"among":[156],"others":[157],"regulatory":[158,481],"network":[159,166,496],"inference":[160,167,479],"disease":[162,189,265,507,553],"gene":[163,183,190,291,330,508,536],"identification.":[164,509],"Regulatory":[165],"elucidation":[170],"transcriptional":[172],"regulation":[173],"interactions":[174,227,262],"between":[175],"regulator":[176,329],"genes":[177,197,215,229,316,554],"called":[178,349],"transcription":[179],"factors":[180],"targets.":[184],"On":[185,302],"other":[187,304],"hand,":[188,305],"identification":[191],"process":[194,298],"finding":[196],"whose":[198],"disruption":[199],"triggers":[200],"some":[201],"genetically":[202],"inherited":[203],"disease.":[204,301,338],"both":[206,250],"cases,":[207],"since":[208],"biologists":[209],"confronted":[211],"with":[212,327,438,503,520],"thousands":[213],"investigate,":[217],"challenge":[219],"output":[222],"prioritized":[224],"list":[225],"believed":[230],"good":[233,454],"candidates":[234],"further":[236],"experimental":[237],"study.":[238],"mentioned":[242],"above":[243],"share":[244],"common":[246],"feature:":[247],"prioritization":[251],"positive":[255,344,440],"examples":[256,312],"exists":[257],"small":[259],"amounts":[260],"(confirmed":[261],"identified":[264],"genes)":[266],"no":[268],"negative":[269],"available.":[272],"Indeed,":[273],"databases":[275],"seldom":[276],"report":[277],"non-interactions":[278],"it":[280],"difficult":[282],"not":[283,293,321],"say":[285],"impossible":[286],"determine":[288],"involved":[294],"developing":[297],"there":[306],"plenty":[308],"so-called":[310],"unlabeled":[311,346,434],"like":[313],"instance":[315],"we":[319,385,397],"do":[320],"know":[322],"whether":[323,332],"interacting":[326],"related":[335],"problem":[340,505],"learning":[342,373,428],"examples,":[347],"PU":[350,372,394,427,521],"learning,":[351,395,522],"been":[353],"studied":[354],"itself":[356],"machine":[361],"learning.":[362],"subject":[364],"this":[366],"thesis":[367],"study":[370],"methods":[374,494],"application":[377],"problems.":[380],"first":[383],"chapter":[384,469,501],"introduce":[386],"bagging":[388,443,528],"SVM,":[389],"new":[391,475],"algorithm":[392,412,488,514,531],"assess":[398],"its":[399,547],"performance":[400,447],"properties":[402,455],"on":[403,555],"benchmark":[405],"dataset.":[406,558],"main":[408],"idea":[409],"exploit":[415],"by":[416],"means":[417],"bagging-like":[420],"procedure,":[421],"intrinsic":[423],"feature":[424],"problem,":[429],"set":[435],"contaminated":[437],"hidden":[439],"examples.":[441,466],"Our":[442],"SVM":[444],"achieves":[445],"comparable":[446],"state-of-the-art":[450],"method":[451,476],"while":[452],"showing":[453],"terms":[457],"speed":[459],"scalability":[461],"number":[464],"second":[468],"dedicated":[471],"SIRENE,":[473],"supervised":[478],"network.":[482],"SIRENE":[483],"conceptually":[486],"simple":[487],"compares":[490],"favorably":[491],"existing":[493],"inference.":[497],"Finally,":[498],"third":[500],"deals":[502],"We":[510,545],"propose":[511],"ProDiGe,":[512],"Prioritization":[516],"Of":[517],"Disease":[518],"Genes":[519],"derived":[525],"SVM.":[529],"tailored":[533],"genome-wide":[535],"search":[537],"allows":[539],"integrate":[541],"several":[542],"sources.":[544],"illustrate":[546],"ability":[548],"correctly":[550],"retrieve":[551],"human":[552],"real":[557]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}