{"id":"https://openalex.org/W2475326882","doi":"https://doi.org/10.1093/bioinformatics/btw650","title":"Improving cross-study prediction through addon batch effect adjustment or addon normalization","display_name":"Improving cross-study prediction through addon batch effect adjustment or addon normalization","publication_year":2016,"publication_date":"2016-10-11","ids":{"openalex":"https://openalex.org/W2475326882","doi":"https://doi.org/10.1093/bioinformatics/btw650","mag":"2475326882","pmid":"https://pubmed.ncbi.nlm.nih.gov/27797760"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btw650","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw650","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/3/397/25145919/btw650.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/33/3/397/25145919/btw650.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048970390","display_name":"Roman Hornung","orcid":"https://orcid.org/0000-0002-6036-1495"},"institutions":[{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Roman Hornung","raw_affiliation_strings":["Department of Medical Informatics, Biometry and Epidemiology, University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Biometry and Epidemiology, University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210099379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043223217","display_name":"David Causeur","orcid":"https://orcid.org/0000-0001-6910-9440"},"institutions":[{"id":"https://openalex.org/I2800285241","display_name":"Institut Agro Rennes-Angers","ror":"https://ror.org/01s3fs709","country_code":"FR","type":"education","lineage":["https://openalex.org/I2800285241","https://openalex.org/I4210117091","https://openalex.org/I4399657933"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"David Causeur","raw_affiliation_strings":["Applied Mathematics Department, Agrocampus Ouest, Rennes, France","AGROCAMPUS OUEST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Applied Mathematics Department, Agrocampus Ouest, Rennes, France","institution_ids":["https://openalex.org/I2800285241"]},{"raw_affiliation_string":"AGROCAMPUS OUEST","institution_ids":["https://openalex.org/I2800285241"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091432937","display_name":"Christoph Bernau","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163716","display_name":"Leibniz Supercomputing Centre","ror":"https://ror.org/05558nw16","country_code":"DE","type":"facility","lineage":["https://openalex.org/I109144446","https://openalex.org/I4210163716"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Bernau","raw_affiliation_strings":["Leibniz Supercomputing Center, Garching, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz Supercomputing Center, Garching, Germany","institution_ids":["https://openalex.org/I4210163716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015152016","display_name":"Anne\u2010Laure Boulesteix","orcid":"https://orcid.org/0000-0002-2729-0947"},"institutions":[{"id":"https://openalex.org/I4210099379","display_name":"Zimmer Biomet (Germany)","ror":"https://ror.org/016731f38","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210099379","https://openalex.org/I4210115238"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Anne-Laure Boulesteix","raw_affiliation_strings":["Department of Medical Informatics, Biometry and Epidemiology, University of Munich, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Informatics, Biometry and Epidemiology, University of Munich, Munich, Germany","institution_ids":["https://openalex.org/I4210099379"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048970390"],"corresponding_institution_ids":["https://openalex.org/I4210099379"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.0251,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.78227109,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"33","issue":"3","first_page":"397","last_page":"404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.9503999948501587,"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":0.9503999948501587,"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/T10136","display_name":"Statistical Methods and Inference","score":0.004900000058114529,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.00430000014603138,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.8911102414131165},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7481728196144104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6385914087295532},{"id":"https://openalex.org/keywords/predictive-modelling","display_name":"Predictive modelling","score":0.5035886168479919},{"id":"https://openalex.org/keywords/database-normalization","display_name":"Database normalization","score":0.48262032866477966},{"id":"https://openalex.org/keywords/mean-squared-prediction-error","display_name":"Mean squared prediction error","score":0.45035985112190247},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44851991534233093},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4368416368961334},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.383547306060791},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3438224792480469},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.19576188921928406}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8911102414131165},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7481728196144104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6385914087295532},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.5035886168479919},{"id":"https://openalex.org/C162984825","wikidata":"https://www.wikidata.org/wiki/Q339072","display_name":"Database normalization","level":3,"score":0.48262032866477966},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.45035985112190247},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44851991534233093},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4368416368961334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.383547306060791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3438224792480469},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.19576188921928406},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D011237","descriptor_name":"Predictive Value of Tests","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012107","descriptor_name":"Research Design","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017423","descriptor_name":"Sequence Analysis, RNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020411","descriptor_name":"Oligonucleotide Array Sequence Analysis","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020869","descriptor_name":"Gene Expression Profiling","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D066264","descriptor_name":"Datasets as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btw650","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw650","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/3/397/25145919/btw650.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:27797760","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/27797760","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:HAL:hal-01518454v1","is_oa":false,"landing_page_url":"https://hal.science/hal-01518454","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics, 2017, 33 (3), pp.397-404. &#x27E8;10.1093/bioinformatics/btw650&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btw650","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btw650","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/33/3/397/25145919/btw650.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3597637701","display_name":"Centre de Math\u00e9matiques Henri Lebesgue : fondements, interactions, applications et Formation","funder_award_id":"ANR-11-LABX-0020","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2475326882.pdf","grobid_xml":"https://content.openalex.org/works/W2475326882.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W247104752","https://openalex.org/W1772250503","https://openalex.org/W1964904043","https://openalex.org/W1998096683","https://openalex.org/W2005852722","https://openalex.org/W2007615926","https://openalex.org/W2011682793","https://openalex.org/W2014216843","https://openalex.org/W2017008479","https://openalex.org/W2049446938","https://openalex.org/W2070270390","https://openalex.org/W2081093887","https://openalex.org/W2095556201","https://openalex.org/W2096561439","https://openalex.org/W2097180277","https://openalex.org/W2102307317","https://openalex.org/W2107618129","https://openalex.org/W2107665951","https://openalex.org/W2108420460","https://openalex.org/W2110925561","https://openalex.org/W2113273267","https://openalex.org/W2113878188","https://openalex.org/W2116044718","https://openalex.org/W2116166762","https://openalex.org/W2120153268","https://openalex.org/W2120865735","https://openalex.org/W2137499573","https://openalex.org/W2156631105","https://openalex.org/W2159543062","https://openalex.org/W2161036742","https://openalex.org/W2170219300","https://openalex.org/W2170989872","https://openalex.org/W2171528238","https://openalex.org/W2230139108","https://openalex.org/W2506717766","https://openalex.org/W3099723433","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W4241705247","https://openalex.org/W2145362441","https://openalex.org/W2101622345","https://openalex.org/W3134304369","https://openalex.org/W2582603276","https://openalex.org/W2175373041","https://openalex.org/W4386281023","https://openalex.org/W4312138714","https://openalex.org/W2012771827","https://openalex.org/W2113286112"],"abstract_inverted_index":{"Motivation:":[0],"To":[1],"date":[2],"most":[3],"medical":[4],"tests":[5],"derived":[6],"by":[7],"applying":[8,30],"classification":[9],"methods":[10,95,128],"to":[11,32,64,78],"high-dimensional":[12],"molecular":[13],"data":[14,34,70,141],"are":[15,129,142],"hardly":[16],"used":[17],"in":[18,61,131],"clinical":[19],"practice.":[20],"This":[21],"is":[22,35],"partly":[23],"because":[24],"the":[25,50,72,76,85],"prediction":[26,80,98,120],"error":[27,41],"resulting":[28],"when":[29],"them":[31],"external":[33,69],"usually":[36],"much":[37],"higher":[38],"than":[39],"internal":[40],"as":[42],"evaluated":[43],"through":[44],"within-study":[45],"validation":[46],"procedures.":[47],"We":[48,83],"suggest":[49],"use":[51],"of":[52,87,108,116],"addon":[53,56,88,127],"normalization":[54,89],"and":[55,71,90,123],"batch":[57,92],"effect":[58,93],"removal":[59,94],"techniques":[60,118],"this":[62],"context":[63],"reduce":[65,119],"systematic":[66],"differences":[67],"between":[68],"original":[73],"dataset":[74],"with":[75],"aim":[77],"improve":[79],"performance.":[81],"Results:":[82],"evaluate":[84],"impact":[86],"seven":[91],"on":[96],"cross-study":[97],"performance":[99],"for":[100],"several":[101],"common":[102],"classifiers":[103],"using":[104],"a":[105],"large":[106],"collection":[107],"microarray":[109],"gene":[110],"expression":[111],"datasets,":[112],"showing":[113],"that":[114],"some":[115],"these":[117],"error.":[121],"Availability":[122],"Implementation:":[124],"All":[125],"investigated":[126],"implemented":[130],"our":[132],"R":[133],"package":[134],"bapred.":[135],"Contact:":[136],"hornung@ibe.med.uni-muenchen.de.":[137],"Supplementary":[138,140],"information:":[139],"available":[143],"at":[144],"Bioinformatics":[145],"online.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}
