{"id":"https://openalex.org/W7225039716","doi":"https://doi.org/10.64898/2026.10.27.762202","title":"Batch Effect Correction to Enhance Utility of a Publicly Available ALS Proteomics Dataset","display_name":"Batch Effect Correction to Enhance Utility of a Publicly Available ALS Proteomics Dataset","publication_year":2026,"publication_date":"2026-11-01","ids":{"openalex":"https://openalex.org/W7225039716","doi":"https://doi.org/10.64898/2026.10.27.762202"},"language":"en","primary_location":{"id":"doi:10.64898/2026.10.27.762202","doi":"https://doi.org/10.64898/2026.10.27.762202","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762202","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.27.762202.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"erratum","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.27.762202.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5158867988","display_name":"Grace Cooper","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Grace Cooper","raw_affiliation_strings":["Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States","Washington University School of Medicine, 660 S. Euclid, St. Louis, MO 63110, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]},{"raw_affiliation_string":"Washington University School of Medicine, 660 S. Euclid, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006054736","display_name":"Inez Oh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Inez Oh","raw_affiliation_strings":["Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071367198","display_name":"Philip Payne","orcid":"https://orcid.org/0000-0002-9532-2998","observed_orcids":["https://orcid.org/0000-0002-9532-2998"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Payne","raw_affiliation_strings":["Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States"],"raw_orcid":"https://orcid.org/0000-0002-9532-2998","affiliations":[{"raw_affiliation_string":"Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011451107","display_name":"Zachary B. Abrams","orcid":"https://orcid.org/0000-0001-5219-9996","observed_orcids":["https://orcid.org/0000-0001-5219-9996"]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zachary Abrams","raw_affiliation_strings":["Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States"],"raw_orcid":"https://orcid.org/0000-0001-5219-9996","affiliations":[{"raw_affiliation_string":"Institute for Informatics, Data Science, and Biostatistics, Washington University, 660 S. Euclid Ave., 8067-0013-05, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139146423","display_name":"Timothy Miller","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Timothy Miller","raw_affiliation_strings":["Washington University School of Medicine, 660 S. Euclid, St. Louis, MO 63110, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University School of Medicine, 660 S. Euclid, St. Louis, MO 63110, United States","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5139146423"],"corresponding_institution_ids":["https://openalex.org/I204465549"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.4542999863624573,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.4542999863624573,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.09740000218153,"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":0.09740000218153,"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":0.8740000128746033},{"id":"https://openalex.org/keywords/amyotrophic-lateral-sclerosis","display_name":"amyotrophic lateral sclerosis","score":0.996999979019165},{"id":"https://openalex.org/keywords/proteomics","display_name":"proteomics","score":0.7770000100135803},{"id":"https://openalex.org/keywords/combat","display_name":"combat","score":0.9670000076293945},{"id":"https://openalex.org/keywords/neurodegenerative-diseases","display_name":"neurodegenerative diseases","score":0.6790000200271606},{"id":"https://openalex.org/keywords/data-reproducibility","display_name":"data reproducibility","score":0.5879999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6115999817848206},{"id":"https://openalex.org/C2780596555","wikidata":"https://www.wikidata.org/wiki/Q206901","display_name":"Amyotrophic lateral sclerosis","level":3,"score":0.5879999995231628},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5020999908447266},{"id":"https://openalex.org/C46111723","wikidata":"https://www.wikidata.org/wiki/Q471857","display_name":"Proteomics","level":3,"score":0.4603999853134155},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.39959999918937683},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C172658912","wikidata":"https://www.wikidata.org/wiki/Q661613","display_name":"Batch processing","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30869999527931213},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2517000138759613},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.25110000371932983},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.10.27.762202","doi":"https://doi.org/10.64898/2026.10.27.762202","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762202","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.27.762202.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.10.27.762202","doi":"https://doi.org/10.64898/2026.10.27.762202","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.10.27.762202","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/11/01/2026.10.27.762202.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8048999905586243,"id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225039716.pdf","grobid_xml":"https://content.openalex.org/works/W7225039716.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1585895556","https://openalex.org/W1971075885","https://openalex.org/W2026863482","https://openalex.org/W2096192437","https://openalex.org/W2106083582","https://openalex.org/W2107665951","https://openalex.org/W2115003883","https://openalex.org/W2128768698","https://openalex.org/W2153600047","https://openalex.org/W2155221045","https://openalex.org/W2169353806","https://openalex.org/W2276108155","https://openalex.org/W2415678243","https://openalex.org/W2474747771","https://openalex.org/W2477863367","https://openalex.org/W2498993352","https://openalex.org/W2603756957","https://openalex.org/W2790053519","https://openalex.org/W2899396140","https://openalex.org/W2953216035","https://openalex.org/W2966871345","https://openalex.org/W2983423530","https://openalex.org/W2985534093","https://openalex.org/W2991468917","https://openalex.org/W2995916473","https://openalex.org/W3002417351","https://openalex.org/W3040840440","https://openalex.org/W3088326085","https://openalex.org/W3088980954","https://openalex.org/W3107500297","https://openalex.org/W3118396931","https://openalex.org/W3152857445","https://openalex.org/W3167068736","https://openalex.org/W3175016977","https://openalex.org/W3182038423","https://openalex.org/W3185954544","https://openalex.org/W3196317695","https://openalex.org/W3213876751","https://openalex.org/W4200307349","https://openalex.org/W4210469056","https://openalex.org/W4212788428","https://openalex.org/W4214665053","https://openalex.org/W4281749328","https://openalex.org/W4283650099","https://openalex.org/W4290861579","https://openalex.org/W4296698991","https://openalex.org/W4304588918","https://openalex.org/W4318617212","https://openalex.org/W4319728675","https://openalex.org/W4379054235","https://openalex.org/W4388539829","https://openalex.org/W4393871147","https://openalex.org/W4399639388","https://openalex.org/W4399639685","https://openalex.org/W4400834464","https://openalex.org/W4402644867","https://openalex.org/W4402656091","https://openalex.org/W4403107764","https://openalex.org/W4404458588","https://openalex.org/W4404616293","https://openalex.org/W4413044474"],"related_works":["https://openalex.org/W7201840979","https://openalex.org/W4367852829","https://openalex.org/W7114899061","https://openalex.org/W4413044474","https://openalex.org/W7221342524","https://openalex.org/W4411494230","https://openalex.org/W4321498165","https://openalex.org/W6939700763","https://openalex.org/W6949257887","https://openalex.org/W1988110172"],"abstract_inverted_index":{"Abstract":[0],"Background":[1],"Large,":[2],"publicly":[3],"available":[4],"databases":[5],"of":[6,40,132,229,255,265,288,300],"patient":[7],"data":[8,42,321],"have":[9],"been":[10],"successful":[11],"in":[12,75,113,134,187],"identifying":[13,309],"associations":[14],"between":[15],"neurodegenerative":[16],"diseases":[17],"and":[18,63,87,100,128,145,166,171,203,281,296,310],"biological":[19,61],"features":[20],"that":[21,34,58,137,215,244,314],"might":[22],"otherwise":[23],"go":[24],"unnoticed.":[25],"The":[26,173],"Answer":[27,77,98,115,180,267],"ALS":[28,78,99,116,181,268],"Consortium":[29],"is":[30],"one":[31],"such":[32],"database":[33],"has":[35],"generated":[36],"a":[37,72,110,192,263,306],"rich":[38],"repository":[39],"multi-omic":[41],"from":[43,55,235],"people":[44],"with":[45,139,207,276],"amyotrophic":[46],"lateral":[47],"sclerosis":[48],"(ALS).":[49],"However,":[50],"large":[51,320],"studies":[52],"can":[53,315],"suffer":[54],"batch":[56,73,102,111,141,174,218,279,284,312],"effects":[57,313],"obscure":[59,124],"genuine":[60],"signal":[62],"prevent":[64],"experiment":[65],"reproducibility.":[66],"In":[67],"this":[68],"study,":[69],"we":[70,261],"identified":[71,109],"effect":[74,90,112,151,219,280],"the":[76,89,93,101,114,135,140,150,198,208,212,221,230,236,245,253,256,266,289,292,301],"1-2":[79,118],"proteomic":[80,119,269],"dataset":[81,120,136,199,247,270,290],"(508":[82],"samples":[83,186,272],"x":[84],"3,643":[85],"proteins)":[86,275],"corrected":[88,246],"using":[91],"both":[92,200],"internal":[94],"controls":[95,176],"provided":[96,178],"by":[97,179,273],"effect-correction":[103],"algorithm":[104],"(BECA)":[105],"ComBat.":[106],"Results":[107],"We":[108,303],"Dataset":[117],"that,":[121],"uncorrected,":[122],"may":[123],"biology.":[125],"Proteins":[126],"MOS":[127,144],"H4":[129,146],"were":[130,182],"outliers":[131],"expression":[133],"correlated":[138],"effect.":[142,285],"Removing":[143],"did":[147,154],"not":[148],"correct":[149,185],"fully":[152],"but":[153],"reveal":[155],"new":[156],"principal":[157],"component":[158],"(PC)":[159],"contributing":[160],"proteins":[161,234,299],"related":[162],"to":[163,184,197,318],"motor":[164],"neurons":[165],"potentially":[167],"ALS:":[168],"AINX,":[169],"NFL,":[170],"NFM.":[172],"differential":[175],"(BDCs)":[177],"used":[183],"their":[188],"respective":[189],"batches.":[190],"ComBat,":[191],"well-characterized":[193],"BECA,":[194],"was":[195,211],"applied":[196,317],"before":[201],"(ComBat-BDC)":[202],"after":[204],"(BDC-ComBat)":[205],"correction":[206],"BDCs.":[209],"BDC-ComBat":[210],"only":[213],"method":[214,225],"successfully":[216],"reduced":[217,278,283],"across":[220],"entire":[222],"dataset.":[223,258],"This":[224,286],"also":[226,304],"preserved":[227],"four":[228],"top":[231],"six":[232],"PC-contributing":[233],"original":[237,257],"dataset,":[238],"including":[239],"three":[240],"neuronal":[241,298],"proteins,":[242],"suggesting":[243],"recapitulates":[248,291],"biology":[249],"as":[250,252],"well":[251],"variability":[254,295],"Conclusion":[259],"Altogether,":[260],"produced":[262],"version":[264,287],"(354":[271],"3,641":[274],"globally":[277],"protein-level":[282],"individual":[293],"protein":[294],"important":[297],"original.":[302],"created":[305],"workflow":[307],"for":[308],"correcting":[311],"be":[316],"other":[319],"repositories.":[322]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-11-02T00:00:00"}
