{"id":"https://openalex.org/W2807111212","doi":"https://doi.org/10.1186/s13040-018-0167-7","title":"Improving machine learning reproducibility in genetic association studies with proportional instance cross validation (PICV)","display_name":"Improving machine learning reproducibility in genetic association studies with proportional instance cross validation (PICV)","publication_year":2018,"publication_date":"2018-04-19","ids":{"openalex":"https://openalex.org/W2807111212","doi":"https://doi.org/10.1186/s13040-018-0167-7","mag":"2807111212","pmid":"https://pubmed.ncbi.nlm.nih.gov/29713384"},"language":"en","primary_location":{"id":"doi:10.1186/s13040-018-0167-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-018-0167-7","pdf_url":"https://biodatamining.biomedcentral.com/track/pdf/10.1186/s13040-018-0167-7","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://biodatamining.biomedcentral.com/track/pdf/10.1186/s13040-018-0167-7","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087021381","display_name":"Elizabeth R. Piette","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Elizabeth R. Piette","raw_affiliation_strings":["1Graduate Group in Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA","Graduate Group in Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"1Graduate Group in Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA","institution_ids":[]},{"raw_affiliation_string":"Graduate Group in Genomics and Computational Biology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032971510","display_name":"Jason H. Moore","orcid":"https://orcid.org/0000-0002-5015-1099"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason H. Moore","raw_affiliation_strings":["2Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA","Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"2Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA USA","institution_ids":[]},{"raw_affiliation_string":"Institute for Biomedical Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032971510"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":1.0867,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.80338184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"11","issue":"1","first_page":"6","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10885","display_name":"Gene expression and cancer classification","score":0.9901000261306763,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9861000180244446,"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/reproducibility","display_name":"Reproducibility","score":0.6641374826431274},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57845139503479},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.5623009204864502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3689868450164795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3262142241001129},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.27546727657318115},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16337230801582336},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.13896390795707703}],"concepts":[{"id":"https://openalex.org/C9893847","wikidata":"https://www.wikidata.org/wiki/Q1425625","display_name":"Reproducibility","level":2,"score":0.6641374826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57845139503479},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.5623009204864502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3689868450164795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3262142241001129},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.27546727657318115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16337230801582336},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.13896390795707703},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1186/s13040-018-0167-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-018-0167-7","pdf_url":"https://biodatamining.biomedcentral.com/track/pdf/10.1186/s13040-018-0167-7","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},{"id":"pmid:29713384","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29713384","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":"BioData mining","raw_type":null},{"id":"pmh:oai:doaj.org/article:8d30603385a449c2b2f090852bb70f31","is_oa":true,"landing_page_url":"https://doaj.org/article/8d30603385a449c2b2f090852bb70f31","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Mining, Vol 11, Iss 1, Pp 1-11 (2018)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:4848133","is_oa":true,"landing_page_url":"http://europepmc.org/pmc/articles/PMC5907739","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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":"","raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:5907739","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/5907739","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BioData Min","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13040-018-0167-7","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13040-018-0167-7","pdf_url":"https://biodatamining.biomedcentral.com/track/pdf/10.1186/s13040-018-0167-7","source":{"id":"https://openalex.org/S84409260","display_name":"BioData Mining","issn_l":"1756-0381","issn":["1756-0381"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BioData Mining","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1318844706","display_name":null,"funder_award_id":"ES013508","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G5087828963","display_name":null,"funder_award_id":"DK112217","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6634558516","display_name":null,"funder_award_id":"AI116794","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G6682602594","display_name":null,"funder_award_id":"LM010098","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2807111212.pdf","grobid_xml":"https://content.openalex.org/works/W2807111212.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W327991062","https://openalex.org/W1505191356","https://openalex.org/W1533942137","https://openalex.org/W1542772707","https://openalex.org/W1966360257","https://openalex.org/W1980175560","https://openalex.org/W1980991473","https://openalex.org/W1981552604","https://openalex.org/W1993196280","https://openalex.org/W2007669896","https://openalex.org/W2023639956","https://openalex.org/W2034368206","https://openalex.org/W2070865170","https://openalex.org/W2076011171","https://openalex.org/W2084150578","https://openalex.org/W2090037139","https://openalex.org/W2096095753","https://openalex.org/W2098740506","https://openalex.org/W2099454382","https://openalex.org/W2103851188","https://openalex.org/W2104167780","https://openalex.org/W2110808585","https://openalex.org/W2118978333","https://openalex.org/W2119168155","https://openalex.org/W2126964466","https://openalex.org/W2134469465","https://openalex.org/W2152905639","https://openalex.org/W2154706222","https://openalex.org/W2162651021","https://openalex.org/W2163924952","https://openalex.org/W2164330572","https://openalex.org/W2296335794","https://openalex.org/W2408121173","https://openalex.org/W2472803348","https://openalex.org/W2520667824","https://openalex.org/W2597357676","https://openalex.org/W2747311934","https://openalex.org/W3104887532","https://openalex.org/W4206713405","https://openalex.org/W6807200106"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W3046775127","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474"],"abstract_inverted_index":{"Application":[0],"of":[1,17,32,37],"traditional":[2],"machine":[3],"learning":[4],"procedures":[5],"to":[6,12,62],"biomedical":[7],"data":[8],"may":[9,59],"require":[10],"modifications":[11],"better":[13],"suit":[14],"intrinsic":[15],"characteristics":[16],"the":[18,22,30],"data,":[19],"such":[20,53],"as":[21,54],"potential":[23],"for":[24],"highly":[25],"imbalanced":[26,69],"genotype":[27],"distributions":[28,71],"in":[29,49,64,67],"case":[31],"epistasis":[33],"detection.":[34],"The":[35],"reproducibility":[36],"genetic":[38],"interaction":[39],"findings":[40],"can":[41],"be":[42,60],"improved":[43],"by":[44],"considering":[45],"this":[46],"variable":[47,70],"imbalance":[48],"cross":[50],"validation":[51],"implementation,":[52],"with":[55],"PICV.":[56],"This":[57],"approach":[58],"extended":[61],"problems":[63],"other":[65],"domains":[66],"which":[68],"are":[72],"a":[73],"concern.":[74]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}