{"id":"https://openalex.org/W148116772","doi":null,"title":"A COMPARATIVE STUDY OF DIFFERENT STRATEGIES OF BATCH EFFECT REMOVAL IN MICROARRAY DATA: A CASE STUDY OF THREE DATASETS","display_name":"A COMPARATIVE STUDY OF DIFFERENT STRATEGIES OF BATCH EFFECT REMOVAL IN MICROARRAY DATA: A CASE STUDY OF THREE DATASETS","publication_year":2013,"publication_date":"2013-09-27","ids":{"openalex":"https://openalex.org/W148116772","mag":"148116772"},"language":"en","primary_location":{"id":"pmh:oai:d-scholarship.pitt.edu:18962","doi":null,"is_oa":true,"landing_page_url":"https://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","pdf_url":"http://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","source":{"id":"https://openalex.org/S4306402372","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fei Ding","orcid":"https://orcid.org/0000-0002-8935-8169","observed_orcids":["https://orcid.org/0000-0002-8935-8169"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fei Ding","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8935-8169","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.00960391,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"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":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":1.0,"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"}},{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","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"}},{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","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-effect-correction","display_name":"batch effect correction","score":0.9789999723434448},{"id":"https://openalex.org/keywords/microarray-data","display_name":"microarray data","score":0.9729999899864197},{"id":"https://openalex.org/keywords/differential-expression-analysis","display_name":"differential expression analysis","score":0.9229999780654907},{"id":"https://openalex.org/keywords/mean-centering","display_name":"mean centering","score":0.8579999804496765},{"id":"https://openalex.org/keywords/combat","display_name":"combat","score":0.9900000095367432},{"id":"https://openalex.org/keywords/surrogate-variable-analysis","display_name":"surrogate variable analysis","score":0.7260000109672546},{"id":"https://openalex.org/keywords/biomarker-discovery","display_name":"biomarker discovery","score":0.8230000138282776},{"id":"https://openalex.org/keywords/method-comparison","display_name":"method comparison","score":0.5019999742507935}],"concepts":[{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6227282285690308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.608211874961853},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.523875892162323},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.4879447817802429},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.4474654793739319},{"id":"https://openalex.org/C8415881","wikidata":"https://www.wikidata.org/wiki/Q6839217","display_name":"Microarray analysis techniques","level":4,"score":0.43095940351486206},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24202939867973328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16871902346611023},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06768986582756042},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:d-scholarship.pitt.edu:18962","doi":null,"is_oa":true,"landing_page_url":"https://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","pdf_url":"http://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","source":{"id":"https://openalex.org/S4306402372","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},{"id":"mag:148116772","doi":null,"is_oa":false,"landing_page_url":"http://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","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:d-scholarship.pitt.edu:18962","doi":null,"is_oa":true,"landing_page_url":"https://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","pdf_url":"http://d-scholarship.pitt.edu/18962/1/Ding_Fei_finalETD_2013.pdf","source":{"id":"https://openalex.org/S4306402372","display_name":"D-Scholarship@Pitt (University of Pittsburgh)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I170201317","host_organization_name":"University of Pittsburgh","host_organization_lineage":["https://openalex.org/I170201317"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W148116772.pdf","grobid_xml":"https://content.openalex.org/works/W148116772.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W1533179050","https://openalex.org/W1986849266","https://openalex.org/W2021560851","https://openalex.org/W2038437697","https://openalex.org/W2049446938","https://openalex.org/W2099079147","https://openalex.org/W2107665951","https://openalex.org/W2137499573","https://openalex.org/W2139345901","https://openalex.org/W2140345723","https://openalex.org/W2150542002","https://openalex.org/W3148930403"],"related_works":["https://openalex.org/W1986849266","https://openalex.org/W2049446938","https://openalex.org/W7097009009","https://openalex.org/W2070095707","https://openalex.org/W6989471421","https://openalex.org/W2107665951","https://openalex.org/W2115003883","https://openalex.org/W2110583317","https://openalex.org/W2808082201","https://openalex.org/W3015567273"],"abstract_inverted_index":{"Batch":[0],"effects":[1,56,128],"refer":[2],"to":[3,243],"the":[4,33,83,100,109,149,167,196,210,214,217],"systematic":[5],"non-biological":[6],"variability":[7],"that":[8,95,148,212],"is":[9,21,73,154,213],"introduced":[10],"by":[11],"experimental":[12,138],"design":[13],"and":[14,28,58,122,130,182,208,241],"sample":[15],"processing":[16],"in":[17,25,162,234],"microarray":[18,26,71,235],"experiments.":[19],"It":[20],"a":[22,189,202],"common":[23,66],"issue":[24],"data":[27,72,236],"could":[29,176],"introduce":[30],"bias":[31],"into":[32],"analysis,":[34,77,91],"if":[35,219],"ignored.":[36],"Many":[37],"batch":[38,55,114,127,144,205,232],"effect":[39,115,233],"removal":[40,57,116,206],"methods":[41,87,153,207],"have":[42],"been":[43,49],"developed.":[44],"Previous":[45],"comparative":[46],"work":[47],"has":[48,81,223],"focused":[50],"on":[51,60,88,126,133],"their":[52,131],"effectiveness":[53],"of":[54,68,85,102,111,143,151,231],"impact":[59,84,132],"downstream":[61,89],"classification":[62],"analysis.":[63],"The":[64],"most":[65],"type":[67],"analysis":[69,135],"for":[70,179,216],"differential":[74],"expression":[75],"(DE)":[76],"yet":[78],"no":[79],"study":[80,222],"examined":[82],"these":[86,152],"DE":[90,134],"which":[92],"identifies":[93],"markers":[94],"are":[96],"significantly":[97],"associated":[98],"with":[99,140,186],"outcome":[101],"interest.":[103],"In":[104],"this":[105],"project,":[106],"we":[107,192],"investigated":[108],"performance":[110,150,175],"five":[112],"popular":[113],"methods,":[117,125],"mean-centering,":[118],"ComBat_p,":[119],"ComBat_n,":[120],"SVA,":[121],"ratio":[123],"based":[124],"reduction":[129],"using":[136,195],"three":[137,164],"datasets":[139],"different":[141,204],"sources":[142],"effects.":[145],"We":[146],"found":[147],"data-dependent:":[155],"simple":[156],"mean-centering":[157,197],"method":[158,198],"performed":[159],"reasonably":[160],"well":[161],"all":[163],"datasets,":[165],"but":[166],"more":[168],"complicated":[169],"algorithms":[170],"such":[171],"as":[172],"ComBat":[173],"method\u2019s":[174],"be":[177,184],"unstable":[178],"certain":[180],"dataset":[181],"should":[183],"applied":[185],"caution.":[187],"Given":[188],"new":[190],"dataset,":[191],"recommend":[193],"either":[194],"or":[199],"carefully":[200],"investigating":[201],"few":[203],"choosing":[209],"one":[211],"best":[215],"data,":[218],"possible.":[220],"This":[221],"important":[224],"public":[225],"health":[226],"significance":[227],"because":[228],"better":[229],"handling":[230],"can":[237],"reduce":[238],"biased":[239],"results":[240],"lead":[242],"improved":[244],"biomarker":[245],"identification.":[246]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2016-06-24T00:00:00"}