Tumor-Normal Matched Pairwise DE using DEseq2
0
1
Entering edit mode
9 months ago

Hi, I want to perform pairwise differential analysis for BRCA tumor subtype Luminal A and normal sample. I have used the following code to download and process the data from TCGA using TCGAbiolinks package in R. How should prepare this data to run paired differential analysis in Deseq2/edgeR.

 library(TCGAbiolinks)
query.BRCA.tumor<- GDCquery(project = "TCGA-BRCA", data.category = "Transcriptome Profiling", data.type = "Gene", Expression Quantification", workflow.type = "HTSeq - Counts", experimental.strategy = "RNA-Seq",  sample.type = "Primary Tumor")

GDCdownload(query.BRCA.tumor)
prep.BRCA.tumor <- GDCprepare(query = query.BRCA.tumor, summarizedExperiment = TRUE)
query.BRCA.normal <- GDCquery(project = "TCGA-BRCA", data.category = "Transcriptome Profiling", data.type = "Gene Expression Quantification", workflow.type = "HTSeq - Counts", experimental.strategy = "RNA-Seq", sample.type = "Solid Tissue Normal")
GDCdownload(query.BRCA.normal)
prep.BRCA.normal <- GDCprepare(query = query.BRCA.normal, summarizedExperiment = TRUE)

dataSubt_BRCA <-TCGAquery_subtype(tumor = "BRCA")
samplePam50_BRCA.LumA <- dataSubt_BRCA[dataSubt_BRCA$BRCA_Subtype_PAM50 %in% "LumA",]

 samples.normal = subset(prep.BRCA.normal, select = colData(prep.BRCA.normal)$patient %in% 
  samplePam50_BRCA.LumA$patient)

  samples.tumor <- subset(prep.BRCA.tumor, select = colData(prep.BRCA.tumor)$patient %in% 
 colData(samples.normal)$patient)

  Matched.Samples.Normal <- subset(samples.normal, 
                             select = colData(samples.normal)$patient 
                             %in% colData(samples.tumor)$patient)


   Matched.Samples.LumA<- subset(prep.BRCA.tumor, 
                            select = colData(samples.tumor)$patient 
                            %in% colData(samples.normal)$patient)

   pre_Matched.normal <- TCGAanalyze_Preprocessing(object = Matched.Samples.Normal, cor.cut = 0.6, datatype = "HTSeq - Counts")

   pre_Matched.LumA <- TCGAanalyze_Preprocessing(object = Matched.Samples.LumA, cor.cut = 0.6, datatype = "HTSeq - Counts")
   matched_data.norm <- TCGAanalyze_Normalization(tabDF = cbind(pre_Matched.normal, pre_Matched.LumA), geneInfo = geneInfoHT, method = "gcContent")
   matched_data.norm <- TCGAanalyze_Normalization(tabDF = matched_data.norm, geneInfo = geneInfoHT, method = "geneLength")
   matched_data_filt <- TCGAanalyze_Filtering(tabDF = matched_data.norm, method = "quantile", qnt.cut = 0.25)

    samplesNT <- TCGAquery_SampleTypes(barcode = colnames(matched_data_filt),
                               typesample = c("NT"))

   MatchedNTdataFilt <- AllMatcheddataFilt[,samplesMatchedNT]
   MatchedNTdataFilt <- MatchedNTdataFilt[, order(colnames(MatchedNTdataFilt))]

   samplesTP <- TCGAquery_SampleTypes(barcode = colnames(matched_data_filt), 
                               typesample = c("TP"))

   matched_NT_filt <- matched_data_filt[,samplesNT]
   matched_LumA_filt <- matched_data_filt[, samplesTP]
DESeq2 TCGAbiolinks DE • 370 views
ADD COMMENT
2
Entering edit mode

You can use xena browser to download the row_counts which can be used for input for DESeq2

ADD REPLY
0
Entering edit mode

I already have the above data from TCGA. I would like to prepare this for paired analysis in DESeq2.

ADD REPLY
2
Entering edit mode

you can find it here Make sure the that your data are row counts

ADD REPLY

Login before adding your answer.

Traffic: 1355 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.

Powered by the version 2.3.6