{"id":"https://openalex.org/W2010400359","doi":"https://doi.org/10.1515/1544-6115.1766","title":"The practical effect of batch on genomic prediction","display_name":"The practical effect of batch on genomic prediction","publication_year":2012,"publication_date":"2012-04-16","ids":{"openalex":"https://openalex.org/W2010400359","doi":"https://doi.org/10.1515/1544-6115.1766","mag":"2010400359","pmid":"https://pubmed.ncbi.nlm.nih.gov/22611599","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/3760371"},"language":"en","primary_location":{"id":"doi:10.1515/1544-6115.1766","doi":"https://doi.org/10.1515/1544-6115.1766","is_oa":false,"landing_page_url":"https://doi.org/10.1515/1544-6115.1766","pdf_url":null,"source":{"id":"https://openalex.org/S77188613","display_name":"Statistical Applications in Genetics and Molecular Biology","issn_l":"1544-6115","issn":["1544-6115","2194-6302"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","jufo-1","medline","norway-1","poland-40","russia-white-list-3"],"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Applications in Genetics and Molecular Biology","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3760371","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012605359","display_name":"Hilary S. Parker","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hilary S. Parker","raw_affiliation_strings":["Johns Hopkins Bloomberg School of Public Health","#N#            \u2020\u2020Johns Hopkins Bloomberg School of Public Health, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins Bloomberg School of Public Health","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"#N#            \u2020\u2020Johns Hopkins Bloomberg School of Public Health, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020868614","display_name":"Jeffrey T. Leek","orcid":"https://orcid.org/0000-0002-2873-2671","observed_orcids":["https://orcid.org/0000-0002-2873-2671"]},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey T. Leek","raw_affiliation_strings":["Johns Hopkins Bloomberg School of Public Health"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins Bloomberg School of Public Health","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I145311948"],"apc_list":{"value":2400,"currency":"EUR","value_usd":2712},"apc_paid":null,"fwci":1.1549,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.75102939,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"11","issue":"3","first_page":"Article 10","last_page":"Article 10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":0.0,"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/batch-effects","display_name":"batch effects","score":0.9900000095367432},{"id":"https://openalex.org/keywords/genomic-prediction","display_name":"genomic prediction","score":0.9950000047683716},{"id":"https://openalex.org/keywords/gene-expression-microarrays","display_name":"gene expression microarrays","score":0.9079999923706055},{"id":"https://openalex.org/keywords/probe-selection","display_name":"probe selection","score":0.3619999885559082},{"id":"https://openalex.org/keywords/training-set-construction","display_name":"training set construction","score":0.7120000123977661},{"id":"https://openalex.org/keywords/prediction-accuracy","display_name":"prediction accuracy","score":0.6949999928474426}],"concepts":[{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5957711935043335},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5501127243041992},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5386723279953003},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.5177327990531921},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.5155227184295654},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4160494804382324},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37480926513671875},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.36912497878074646},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24818527698516846},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008957","descriptor_name":"Models, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1515/1544-6115.1766","doi":"https://doi.org/10.1515/1544-6115.1766","is_oa":false,"landing_page_url":"https://doi.org/10.1515/1544-6115.1766","pdf_url":null,"source":{"id":"https://openalex.org/S77188613","display_name":"Statistical Applications in Genetics and Molecular Biology","issn_l":"1544-6115","issn":["1544-6115","2194-6302"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","dongbi-c","jufo-1","medline","norway-1","poland-40","russia-white-list-3"],"host_organization":"https://openalex.org/P4310313990","host_organization_name":"De Gruyter","host_organization_lineage":["https://openalex.org/P4310313990"],"host_organization_lineage_names":["De Gruyter"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistical Applications in Genetics and Molecular Biology","raw_type":"journal-article"},{"id":"pmid:22611599","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/22611599","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,"listed_in":[],"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":"Statistical applications in genetics and molecular biology","raw_type":"Journal Article"},{"id":"pmh:oai:europepmc.org:2754310","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3760371","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,"listed_in":[],"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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:3760371","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3760371","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Stat Appl Genet Mol Biol","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:europepmc.org:2754310","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3760371","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,"listed_in":[],"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":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1192883043","display_name":"Software for the statistical analysis of microarray probe level data","funder_award_id":"R01RR021967","funder_id":"https://openalex.org/F4320337375","funder_display_name":"National Center for Research Resources"},{"id":"https://openalex.org/G3101153843","display_name":"Preprocessing and Analysis Tools for High-Throughput Technologies","funder_award_id":"R01GM083084","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G7104840627","display_name":"Software for the statistical analysis of microarray probe level data","funder_award_id":"R01GM103552","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"},{"id":"https://openalex.org/F4320337375","display_name":"National Center for Research Resources","ror":"https://ror.org/04pw6fb54"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1973614663","https://openalex.org/W2007615926","https://openalex.org/W2020541351","https://openalex.org/W2021129827","https://openalex.org/W2029276959","https://openalex.org/W2049446938","https://openalex.org/W2063978378","https://openalex.org/W2082833890","https://openalex.org/W2096192437","https://openalex.org/W2107665951","https://openalex.org/W2108671185","https://openalex.org/W2109972881","https://openalex.org/W2113878188","https://openalex.org/W2113985797","https://openalex.org/W2114256688","https://openalex.org/W2135046866","https://openalex.org/W2137499573","https://openalex.org/W2138550913","https://openalex.org/W2141222206","https://openalex.org/W2146889962","https://openalex.org/W2150926065","https://openalex.org/W2163563958","https://openalex.org/W2169318796"],"related_works":["https://openalex.org/W2161036742","https://openalex.org/W2049446938","https://openalex.org/W2916026870","https://openalex.org/W7166742594","https://openalex.org/W2750588340","https://openalex.org/W2883544453","https://openalex.org/W1986849266","https://openalex.org/W2808082201","https://openalex.org/W1993952059","https://openalex.org/W3062377804"],"abstract_inverted_index":{"Measurements":[0],"from":[1,47],"microarrays":[2],"and":[3,30,64,88,94,128,130,151],"other":[4],"high-throughput":[5,34],"technologies":[6],"are":[7],"susceptible":[8],"to":[9,123,140],"non-biological":[10],"artifacts":[11],"like":[12],"batch":[13,19,42,52,78,89,102],"effects.":[14],"It":[15],"is":[16],"known":[17,62],"that":[18,116],"effects":[20,43,79],"can":[21],"alter":[22],"or":[23],"obscure":[24],"the":[25,39,75,84,91,108],"set":[26],"of":[27,41,77,110],"significant":[28],"results":[29,114,143],"biological":[31],"conclusions":[32],"in":[33,90],"studies.":[35],"Here":[36],"we":[37,54,72],"examine":[38],"impact":[40,76],"on":[44,80,83],"predictors":[45,105],"built":[46],"genomic":[48],"technologies.":[49],"To":[50],"investigate":[51],"effects,":[53],"collected":[55],"publicly":[56],"available":[57],"gene":[58],"expression":[59,97],"measurements":[60,98],"with":[61,146],"outcomes,":[63],"estimated":[65],"batches":[66,127,150],"using":[67],"date.":[68],"Using":[69],"these":[70],"data":[71],"show":[73],"(1)":[74,117],"prediction":[81,142],"depends":[82],"correlation":[85,125,148],"between":[86,126,149],"outcome":[87],"training":[92,118],"data,":[93],"(2)":[95,131],"removing":[96],"most":[99],"affected":[100],"by":[101],"before":[103],"building":[104],"may":[106],"improve":[107,141],"accuracy":[109],"those":[111],"predictors.":[112],"These":[113],"suggest":[115],"sets":[119],"should":[120,137],"be":[121,138],"designed":[122],"minimize":[124],"outcome,":[129],"methods":[132],"for":[133,144],"identifying":[134],"batch-affected":[135],"probes":[136],"developed":[139],"studies":[145],"high":[147],"outcome.":[152]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2016-06-24T00:00:00"}