{"status":"OK","data":{"id":64833,"identifier":"DVN/ZVHDGA","persistentUrl":"https://doi.org/10.7910/DVN/ZVHDGA","protocol":"doi","authority":"10.7910","separator":"/","publisher":"Harvard Dataverse","publicationDate":"2007-11-28","storageIdentifier":"s3://1902.1/10649","effectiveDatasetFileCountLimit":1000,"datasetFileUploadsAvailable":999,"datasetType":"dataset","locks":[],"latestVersion":{"id":66707,"datasetId":64833,"datasetPersistentId":"doi:10.7910/DVN/ZVHDGA","datasetType":"dataset","storageIdentifier":"s3://1902.1/10649","versionNumber":1,"internalVersionNumber":1,"versionMinorNumber":0,"versionState":"RELEASED","latestVersionPublishingState":"RELEASED","deaccessionNote":"Initial version","deaccessionLink":"","distributionDate":"2007","productionDate":"2007","lastUpdateTime":"2007-11-28T05:00:00Z","releaseTime":"2007-11-28T00:00:00Z","createTime":"2007-10-01T16:21:30Z","alternativePersistentId":"hdl:1902.1/10649","publicationDate":"2007-11-28","citationDate":"2007-11-28","effectiveDatasetFileCountLimit":1000,"datasetFileUploadsAvailable":999,"license":{"name":"CC0 1.0","uri":"http://creativecommons.org/publicdomain/zero/1.0","iconUri":"https://licensebuttons.net/p/zero/1.0/88x31.png","rightsIdentifier":"CC0-1.0","rightsIdentifierScheme":"SPDX","schemeUri":"https://spdx.org/licenses/","languageCode":"en"},"fileAccessRequest":false,"metadataBlocks":{"citation":{"displayName":"Citation Metadata","name":"citation","fields":[{"typeName":"title","multiple":false,"typeClass":"primitive","value":"Replication data for: Random-set Methods Identify Distinct Aspects of the Enrichment Signal in Gene-set Analysis"},{"typeName":"author","multiple":true,"typeClass":"compound","value":[{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Michael A. Newton"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Wisconsin–Madison"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Fernando A. Quintana"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"Pontificia Universidad Católica de Chile"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"ohan A. den Boon"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Wisconsin–Madison"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"Srikumar Sengupta"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"WiCell Research Institute"}},{"authorName":{"typeName":"authorName","multiple":false,"typeClass":"primitive","value":"and Paul Ahlquist"},"authorAffiliation":{"typeName":"authorAffiliation","multiple":false,"typeClass":"primitive","value":"University of Wisconsin–Madison and Howard Hughes Medical Institute"}}]},{"typeName":"datasetContact","multiple":true,"typeClass":"compound","value":[{"datasetContactEmail":{"typeName":"datasetContactEmail","multiple":false,"typeClass":"primitive","value":"N/A"}}]},{"typeName":"dsDescription","multiple":true,"typeClass":"compound","value":[{"dsDescriptionValue":{"typeName":"dsDescriptionValue","multiple":false,"typeClass":"primitive","value":"A prespecified set of genes may be enriched, to varying degrees, for genes that have altered expression levels relative to two or more states of a cell. Knowing the enrichment of gene sets defined by functional categories, such as gene ontology (GO) annotations, is valuable for analyzing the biological signals in microarray expression data. A common approach to measuring enrichment is by cross-classifying genes according to membership in a functional category and membership on a selected list of significantly altered genes. A small Fisher’s exact test p-value, for example, in this 2×2 table is indicative of enrichment. Other category analysis methods retain the quantitative gene-level scores and measure significance by referring a category-level statistic to a permutation distribution associated with the original differential expression problem. We describe a class of random-set scoring methods that measure distinct components of the enrichment signal. The class includes Fisher’s test based on selected genes and also tests that average gene-level evidence across the category. Averaging and selection methods are compared empirically using Affymetrix data on expression in nasopharyngeal cancer tissue, and theoretically using a location model of differential expression. We find that each method has a domain of superiority in the state space of enrichment problems, and that both methods have bene\nfits in practice. Our analysis also addresses two problems related to multiple-category inference, namely, that equally enriched categories are not detected with equal probability if they are of different sizes, and also that there is dependence among category statistics owing to shared genes. Random-set enrichment calculations do not require Monte Carlo for implementation. They are made available in the R package allez."}}]},{"typeName":"keyword","multiple":true,"typeClass":"compound","value":[{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"Conditional testing"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"gene ontology"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"gene set enrichment analysis"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"host-virus association in nasopharyngeal carcinoma"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"selection versus average evidence"}},{"keywordValue":{"typeName":"keywordValue","multiple":false,"typeClass":"primitive","value":"significance analysis of function and expression"}}]},{"typeName":"publication","multiple":true,"typeClass":"compound","value":[{"publicationCitation":{"typeName":"publicationCitation","multiple":false,"typeClass":"primitive","value":"Michael A. Newton, Fernando A. Quintana, Johan A. den Boon, Srikumar Sengupta, and Paul Ahlquist. 2007. \"Random-set Methods Identify Distinct Aspects of the Enrichment Signal in Gene-set Analysis.\" Ann. Appl. Statist. Volume 1, Number 1 (2007), 85-106.   <a href=\"http://projecteuclid.org/DPubS?service=UI&amp;version=1.0&amp;verb=Display&amp;handle=euclid.aoas/1183143730\" target= \"_new\">article available here</a>"}}]},{"typeName":"notesText","multiple":false,"typeClass":"primitive","value":"Subject: STANDARD DEPOSIT TERMS 1.0  Type: DATAPASS:TERMS:STANDARD:1.0  Notes: This study was deposited under the of the Data-PASS standard deposit terms. A copy of the usage agreement is included in the file section of this study.;"},{"typeName":"productionDate","multiple":false,"typeClass":"primitive","value":"2007"},{"typeName":"distributor","multiple":true,"typeClass":"compound","value":[{"distributorName":{"typeName":"distributorName","multiple":false,"typeClass":"primitive","value":"Institute for Mathematical Statistics"},"distributorURL":{"typeName":"distributorURL","multiple":false,"typeClass":"primitive","value":"http://www.imstat.org/aoas/"},"distributorLogoURL":{"typeName":"distributorLogoURL","multiple":false,"typeClass":"primitive","value":"http://www.imstat.org/images/imslogo1.gif"}}]},{"typeName":"distributionDate","multiple":false,"typeClass":"primitive","value":"2007"},{"typeName":"dateOfDeposit","multiple":false,"typeClass":"primitive","value":"2007-10-01"}]}},"files":[{"description":"Supplementary Materials for Newton et al.","label":"supplement.pdf","restricted":false,"version":1,"datasetVersionId":66707,"categories":["1. Documentation"],"dataFile":{"id":655291,"persistentId":"doi:10.7910/DVN/ZVHDGA/4BS80I","pidURL":"https://doi.org/10.7910/DVN/ZVHDGA/4BS80I","filename":"supplement.pdf","contentType":"application/pdf","friendlyType":"Adobe PDF","filesize":397804,"description":"Supplementary Materials for Newton et al.","categories":["1. Documentation"],"storageIdentifier":"s3://dvn-cloud:5853","rootDataFileId":-1,"md5":"2b1f9cc90a02328ef24ac155fa26ec9a","checksum":{"type":"MD5","value":"2b1f9cc90a02328ef24ac155fa26ec9a"},"tabularData":false,"creationDate":"2007-10-01","publicationDate":"2007-11-27","lastUpdateTime":"2007-11-28T05:00:00Z","fileAccessRequest":false}}]}}}