{"id":"https://openalex.org/W138166317","doi":null,"title":"Avoiding data over fitting in scientific discovery: experiments in functional genomics","display_name":"Avoiding data over fitting in scientific discovery: experiments in functional genomics","publication_year":2004,"publication_date":"2004-08-22","ids":{"openalex":"https://openalex.org/W138166317","mag":"138166317"},"language":"en","primary_location":{"id":"mag:138166317","doi":null,"is_oa":false,"landing_page_url":"http://www.frontiersinai.com/ecai/ecai2004/ecai04/pdf/p0470.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418308","display_name":"European Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Artificial Intelligence","raw_type":null},"volume":null,"type":"conference-paper","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/A5087537644","display_name":"Dragan Gamberger","orcid":"https://orcid.org/0000-0002-9008-6156","observed_orcids":["https://orcid.org/0000-0002-9008-6156"]},"institutions":[{"id":"https://openalex.org/I4210123216","display_name":"Ru\u0111er Bo\u0161kovi\u0107 Institute","ror":"https://ror.org/02mw21745","country_code":"HR","type":"facility","lineage":["https://openalex.org/I4210123216"]}],"countries":["HR"],"is_corresponding":false,"raw_author_name":"Dragan Gamberger","raw_affiliation_strings":["Rudjer Bo\u0161kovi\u0107 Institute, Zagreb, Croatia#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-9008-6156","affiliations":[{"raw_affiliation_string":"Rudjer Bo\u0161kovi\u0107 Institute, Zagreb, Croatia#TAB#","institution_ids":["https://openalex.org/I4210123216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060174190","display_name":"Nada Lavra\u010d","orcid":"https://orcid.org/0000-0002-9995-7093","observed_orcids":["https://orcid.org/0000-0002-9995-7093"]},"institutions":[{"id":"https://openalex.org/I3006985408","display_name":"Jo\u017eef Stefan Institute","ror":"https://ror.org/05060sz93","country_code":"SI","type":"facility","lineage":["https://openalex.org/I3006985408"]},{"id":"https://openalex.org/I4210113529","display_name":"Jo\u017eef Stefan International Postgraduate School","ror":"https://ror.org/01hdkb925","country_code":"SI","type":"education","lineage":["https://openalex.org/I4210113529"]}],"countries":["SI"],"is_corresponding":false,"raw_author_name":"Nada Lavra\u010d","raw_affiliation_strings":["Jo\u017eef Stefan Institute, Ljubljana, Slovenia and Politehnika Nova Gorica, Nova Gorica, Slovenia#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-9995-7093","affiliations":[{"raw_affiliation_string":"Jo\u017eef Stefan Institute, Ljubljana, Slovenia and Politehnika Nova Gorica, Nova Gorica, Slovenia#TAB#","institution_ids":["https://openalex.org/I3006985408","https://openalex.org/I4210113529"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9564,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79406208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"470","last_page":"474"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.6054999828338623,"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":0.6054999828338623,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.357699990272522,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.0032999999821186066,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/functional-genomics","display_name":"functional genomics","score":0.9160000085830688},{"id":"https://openalex.org/keywords/subgroup-discovery","display_name":"subgroup discovery","score":0.9610000252723694},{"id":"https://openalex.org/keywords/rule-learning","display_name":"rule induction","score":0.8920000195503235},{"id":"https://openalex.org/keywords/feature-relevance","display_name":"feature relevance","score":0.5450000166893005},{"id":"https://openalex.org/keywords/cancer-classification","display_name":"cancer classification","score":0.7319999933242798},{"id":"https://openalex.org/keywords/gene-expression","display_name":"gene expression","score":0.8510000109672546}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9603351950645447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.67091304063797},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6252133250236511},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5938114523887634},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.587883710861206},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5801462531089783},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5296342968940735},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5094166398048401},{"id":"https://openalex.org/C161078062","wikidata":"https://www.wikidata.org/wiki/Q1068690","display_name":"Functional genomics","level":5,"score":0.49424102902412415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36867982149124146},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.16709387302398682},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.16532421112060547},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14075130224227905},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13573241233825684},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.11311644315719604},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:138166317","doi":null,"is_oa":false,"landing_page_url":"http://www.frontiersinai.com/ecai/ecai2004/ecai04/pdf/p0470.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306418308","display_name":"European Conference on Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Conference on Artificial Intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W184639320","https://openalex.org/W1671614046","https://openalex.org/W1761022139","https://openalex.org/W1798570018","https://openalex.org/W1966701961","https://openalex.org/W1971138308","https://openalex.org/W1995023359","https://openalex.org/W2065004085","https://openalex.org/W2109363337","https://openalex.org/W2137476312","https://openalex.org/W2139837606","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W2335379403","https://openalex.org/W2323708302","https://openalex.org/W1998261914","https://openalex.org/W7095389860","https://openalex.org/W2166716616","https://openalex.org/W37780701","https://openalex.org/W2647615591","https://openalex.org/W2584011462","https://openalex.org/W7100798536","https://openalex.org/W1566665095"],"abstract_inverted_index":{"Functional":[0],"genomics":[1,103],"is":[2,29,61,118],"a":[3,10],"typical":[4],"scientific":[5],"discovery":[6,66],"domain":[7],"characterized":[8],"by":[9,71,79],"very":[11],"large":[12],"number":[13,20],"of":[14,21,26,50,73,83,105],"attributes":[15],"(genes)":[16],"relative":[17],"to":[18,120],"the":[19,64,75,81,87,98,122],"examples":[22],"(observations).":[23],"The":[24,59],"danger":[25],"data":[27,44],"overfitting":[28,45],"crucial":[30],"in":[31,42,46],"such":[32],"domains.":[33],"This":[34],"work":[35],"presents":[36],"an":[37],"approach":[38,60],"which":[39],"can":[40],"help":[41],"avoiding":[43],"supervised":[47],"inductive":[48],"learning":[49,68],"short":[51],"rules":[52],"that":[53,85,96],"are":[54],"appropriate":[55],"for":[56],"human":[57],"interpretation.":[58],"based":[62,110],"on":[63,111],"subgroup":[65],"rule":[67,88],"framework,":[69],"enhanced":[70],"methods":[72],"restricting":[74],"hypothesis":[76],"search":[77],"space":[78],"exploiting":[80],"relevancy":[82],"features":[84],"enter":[86],"construction":[89],"process":[90],"as":[91,93],"well":[92],"their":[94],"combinations":[95],"form":[97],"rules.":[99],"A":[100],"multi-class":[101],"functional":[102],"problem":[104],"classifying":[106],"fourteen":[107],"cancer":[108],"types":[109],"more":[112],"than":[113],"16000":[114],"gene":[115],"expression":[116],"values":[117],"used":[119],"illustrate":[121],"methodology.":[123]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2016-06-24T00:00:00"}