Open sagarutturkar opened 1 year ago
Below is my code:
CancerProject <- "TARGET-OS" DataDirectory <- paste0("../GDC/",gsub("-","_",CancerProject)) FileNameData <- paste0(DataDirectory, "_","STAR_Counts",".rda") query <- GDCquery(project = CancerProject, data.category = "Transcriptome Profiling", data.type = "Gene Expression Quantification", workflow.type = "STAR - Counts") GDCdownload(query = query) data <- GDCprepare(query = query) # Object dataPrep <- TCGAanalyze_Preprocessing( object = data, cor.cut = 0.6 ) dataNorm <- TCGAanalyze_Normalization( tabDF = dataPrep, geneInfo = geneInfoHT, method = "gcContent" ) dataFilt <- TCGAanalyze_Filtering( tabDF = dataNorm, method = "quantile", qnt.cut = 0.25 ) dataDEGs <- TCGAanalyze_DEA( mat1 = dataFilt[,high], mat2 = dataFilt[,low], Cond1type = "High", Cond2type = "Low", fdr.cut = 0.01 , logFC.cut = 1, method = "glmLRT", pipeline = "edgeR" )
In the last part TCGAanalyze_DEA, I have manually defined samples based on a specific condition:
TCGAanalyze_DEA
> high [1] "TARGET-40-PAKZZK-01A-01R" "TARGET-40-PALFYN-01A-01R" "TARGET-40-PARBGW-01A-01R" "TARGET-40-PAKUZU-01A-01R" "TARGET-40-PANXSC-01A-01R" [6] "TARGET-40-PATJVI-01A-01R" "TARGET-40-PAMJXS-01A-01R" "TARGET-40-PALKGN-01A-01R" "TARGET-40-PALZGU-01A-01R" "TARGET-40-PAVECB-01A-01R" [11] "TARGET-40-PANZHX-01A-01R" "TARGET-40-PANGRW-01A-01R" "TARGET-40-PASUUH-01A-01R" "TARGET-40-PAVCLP-01A-01R" "TARGET-40-PAUTWB-01A-01R" [16] "TARGET-40-PAUTYB-01A-01R" "TARGET-40-PALWWX-01A-01R" "TARGET-40-0A4I0S-01A-01R" "TARGET-40-PAMEKS-01A-01R" "TARGET-40-PARJXU-01A-01R" [21] "TARGET-40-PARGTM-01A-01R" "TARGET-40-PARKAF-01A-01R" "TARGET-40-PASFCV-01A-01R" "TARGET-40-0A4I3S-01A-01R" "TARGET-40-PANVJJ-01A-01R" [26] "TARGET-40-PAPIJR-01A-01R" "TARGET-40-PAPNVD-01A-01R" "TARGET-40-0A4I5B-01A-01R" "TARGET-40-0A4HY5-01A-01R" "TARGET-40-0A4HLD-01A-01R" [31] "TARGET-40-PASYUK-01A-01R" "TARGET-40-0A4HXS-01A-01R" "TARGET-40-PASEBY-01A-01R" "TARGET-40-PAPXGT-01A-01R" "TARGET-40-0A4HMC-01A-01R" [36] "TARGET-40-0A4I48-01A-01R" "TARGET-40-PASNZV-01A-01R" "TARGET-40-PASRNE-01A-01R" "TARGET-40-0A4I4M-01A-01R" "TARGET-40-0A4I6O-01A-01R" [41] "TARGET-40-PATPBS-01A-01R" "TARGET-40-PATMIF-01A-01R" "TARGET-40-PATEEM-01A-01R" > low [1] "TARGET-40-PALECC-01A-01R" "TARGET-40-PARDAX-01A-01R" "TARGET-40-0A4I9K-01A-01R" "TARGET-40-PAPKWD-01A-01R" "TARGET-40-PAKXLD-01A-01R" [6] "TARGET-40-PALKDP-01A-01R" "TARGET-40-PAVALD-01A-01R" "TARGET-40-PAPFLB-01A-01R" "TARGET-40-PATMPU-01A-01R" "TARGET-40-0A4I0Q-01A-01R" [11] "TARGET-40-PATKSS-01A-01R" "TARGET-40-PAMRHD-01A-01R" "TARGET-40-PAMYYJ-01A-01R" "TARGET-40-PAMLKS-01A-01R" "TARGET-40-PAMHLF-01A-01R" [16] "TARGET-40-PAMHYN-01A-01R" "TARGET-40-PASEFS-01A-01R" "TARGET-40-PASKZZ-01A-01R" "TARGET-40-0A4I42-01A-01R" "TARGET-40-0A4I65-01A-01R" [21] "TARGET-40-PATAWV-01A-01R" "TARGET-40-0A4I0W-01A-01R" "TARGET-40-PAUBIT-01A-01R" "TARGET-40-PAUXPZ-01A-01R" "TARGET-40-PAUYTT-01A-01R" [26] "TARGET-40-PAUUML-01A-01R" "TARGET-40-PAUVUL-01A-01R" "TARGET-40-0A4HX8-01A-01R" "TARGET-40-PAMTCM-01A-01R" "TARGET-40-PARFTG-01A-01R" [31] "TARGET-40-PAPWWC-01A-01R" "TARGET-40-PAVDTY-01A-01R" "TARGET-40-PANMIG-01A-01R" "TARGET-40-0A4I4O-01A-01R" "TARGET-40-PANPUM-01A-01R" [36] "TARGET-40-PASSLM-01A-01R" "TARGET-40-PALHRL-01A-01R" "TARGET-40-PAKFVX-01A-01R" "TARGET-40-PATUXZ-01A-01R" "TARGET-40-PANSEN-01A-01R" [41] "TARGET-40-0A4I4E-01A-01R" "TARGET-40-PANGPE-01A-01R" "TARGET-40-0A4I8U-01A-01R" "TARGET-40-PANZZJ-01A-01R" "TARGET-40-PATMXR-01A-01R"
I get an error as:
Error in names(x) <- value : 'names' attribute [7] must be the same length as the vector [5]
Can you please help to figure out the error?
The code was initially written to support only TCGA samples. I fixed the part giving problems for non-TCGA samples. It should be working now.
Below is my code:
In the last part
TCGAanalyze_DEA
, I have manually defined samples based on a specific condition:I get an error as:
Error in names(x) <- value : 'names' attribute [7] must be the same length as the vector [5]
Can you please help to figure out the error?