Code
download_htseq_solidNormaldata <- function(selectedcancer){
print(selectedcancer)
suppressMessages({
query <- GDCquery(
project = selectedcancer,
data.category = "Transcriptome Profiling",
data.type = "Gene Expression Quantification",
sample.type = "Solid Tissue Normal",
workflow.type = "HTSeq - FPKM-UQ")
})
if (is.null(query)){
print(paste0("No FPKM-UQ data of solid normal tissue for ", selectedcancer))
} else{
sink(file = "/dev/null") # to remove progress bar from rmd
GDCdownload(query)
data <- GDCprepare(query,
save = TRUE,
save.filename = paste0(selectedcancer,".rda"))
sink()
print(data)
clin <- colData(data)
df_all <- assay(data)
}
}
tcga_projects <- TCGAbiolinks:::getGDCprojects()$project_id
mycancertypes <- tcga_projects[grepl("^TCGA-",tcga_projects)] # total 33
download_all <- sapply(mycancertypes[order(mycancertypes)],function(x) download_htseq_solidNormaldata(selectedcancer=x))
## [1] "TCGA-ACC"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-ACC"
## [1] "TCGA-BLCA"
## Downloading data for project TCGA-BLCA
## GDCdownload will download 19 files. A total of 9.617101 MB
## Downloading as: Mon_Nov_25_09_50_22_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## blca subtype information from:doi:10.1016/j.cell.2017.09.007
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-BLCA.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 19
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(19): TCGA-CU-A0YN-11A-11R-A10U-07 TCGA-BT-A20U-11A-11R-A14Y-07
## ... TCGA-K4-A3WV-11A-21R-A22U-07 TCGA-GC-A3WC-11A-11R-A22U-07
## colData names(238): barcode patient ... subtype_Fusion in TNFRSF21
## subtype_Fusion in ASIP
## [1] "TCGA-BRCA"
## Downloading data for project TCGA-BRCA
## GDCdownload will download 113 files. A total of 59.697166 MB
## Downloading as: Mon_Nov_25_09_50_45_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## brca subtype information from:doi.org/10.1016/j.ccell.2018.03.014
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-BRCA.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 113
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(113): TCGA-E2-A1LH-11A-22R-A14D-07
## TCGA-BH-A0DG-11A-43R-A12P-07 ... TCGA-E9-A1RH-11A-34R-A169-07
## TCGA-BH-A0BW-11A-12R-A115-07
## colData names(83): barcode patient ... subtype_PARADIGM Clusters
## subtype_Pan-Gyn Clusters
## [1] "TCGA-CESC"
## Downloading data for project TCGA-CESC
## GDCdownload will download 3 files. A total of 1.521645 MB
## Downloading as: Mon_Nov_25_09_51_35_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## cesc subtype information from:doi:10.1038/nature21386
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-CESC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 3
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(3): TCGA-HM-A3JJ-11A-12R-A21T-07 TCGA-FU-A3EO-11A-13R-A213-07
## TCGA-MY-A5BF-11A-11R-A26T-07
## colData names(127): barcode patient ... subtype_GEXP:APOBEC3H:164668
## subtype_patient
## [1] "TCGA-CHOL"
## Downloading data for project TCGA-CHOL
## GDCdownload will download 9 files. A total of 4.328599 MB
## Downloading as: Mon_Nov_25_09_51_42_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## chol subtype information from:doi:10.1016/j.celrep.2017.02.033
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-CHOL.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 9
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(9): TCGA-W5-AA2U-11A-11R-A41I-07 TCGA-ZU-A8S4-11A-11R-A41I-07
## ... TCGA-W5-AA31-11A-11R-A41I-07 TCGA-W5-AA2X-11A-11R-A41I-07
## colData names(204): barcode patient ... subtype_20 subtype_21
## [1] "TCGA-COAD"
## Downloading data for project TCGA-COAD
## Of the 41 files for download 41 already exist.
## All samples have been already downloaded
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## coad subtype information from:doi:10.1038/nature11252
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-COAD.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 41
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(41): TCGA-A6-5665-11A-01R-1653-07 TCGA-AA-3511-11A-01R-1839-07
## ... TCGA-AZ-6605-11A-01R-1839-07 TCGA-AZ-6601-11A-01R-1774-07
## colData names(107): barcode patient ...
## subtype_vascular_invasion_present subtype_vital_status
## [1] "TCGA-DLBC"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-DLBC"
## [1] "TCGA-ESCA"
## Downloading data for project TCGA-ESCA
## GDCdownload will download 11 files. A total of 6.146252 MB
## Downloading as: Mon_Nov_25_09_52_05_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## esca subtype information from:doi:10.1038/nature20805
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-ESCA.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 11
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(11): TCGA-IC-A6RE-11A-12R-A336-31 TCGA-V5-AASX-11A-11R-A38D-31
## ... TCGA-L5-A4OJ-11A-12R-A260-31 TCGA-V5-A7RE-11A-11R-A354-31
## colData names(140): barcode patient ... subtype_GEA-CIN Integrated
## Cluster - MKL-KNN-4 subtype_GEA-CIN Integrated Cluster - MKL-KNN-7
## [1] "TCGA-GBM"
## Downloading data for project TCGA-GBM
## GDCdownload will download 5 files. A total of 2.658072 MB
## Downloading as: Mon_Nov_25_09_52_15_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## gbm subtype information from:doi:10.1016/j.cell.2015.12.028
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-GBM.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 5
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(5): TCGA-06-0680-11A-32R-A36H-07 TCGA-06-0678-11A-32R-A36H-07
## TCGA-06-0675-11A-32R-A36H-07 TCGA-06-AABW-11A-31R-A36H-07
## TCGA-06-0681-11A-41R-A36H-07
## colData names(74): barcode patient ...
## subtype_Telomere.length.estimate.in.blood.normal..Kb.
## subtype_Telomere.length.estimate.in.tumor..Kb.
## [1] "TCGA-HNSC"
## Downloading data for project TCGA-HNSC
## GDCdownload will download 44 files. A total of 22.121259 MB
## Downloading as: Mon_Nov_25_09_52_24_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## hnsc subtype information from:doi:10.1038/nature14129
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-HNSC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 44
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(44): TCGA-CV-7097-11A-01R-2016-07 TCGA-CV-7416-11A-01R-2081-07
## ... TCGA-CV-6955-11A-01R-2016-07 TCGA-CV-6939-11A-01R-1915-07
## colData names(76): barcode patient ... subtype_Copy.Number
## subtype_PARADIGM
## [1] "TCGA-KICH"
## Downloading data for project TCGA-KICH
## GDCdownload will download 24 files. A total of 12.707799 MB
## Downloading as: Mon_Nov_25_09_52_45_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## kich subtype information from:doi:10.1016/j.ccr.2014.07.014
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-KICH.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 24
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(24): TCGA-KN-8426-11A-01R-2315-07 TCGA-KO-8403-11A-01R-2315-07
## ... TCGA-KN-8430-11A-01R-2315-07 TCGA-KL-8336-11A-01R-2315-07
## colData names(95): barcode patient ... subtype_Copy.Pattern
## subtype_Notable.Molecular.Observations
## [1] "TCGA-KIRC"
## Downloading data for project TCGA-KIRC
## GDCdownload will download 72 files. A total of 37.644714 MB
## Downloading as: Mon_Nov_25_09_53_01_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## kirc subtype information from:doi:10.1038/nature12222
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-KIRC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 72
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(72): TCGA-CZ-5458-11A-01R-1503-07 TCGA-CZ-5989-11A-01R-1672-07
## ... TCGA-CW-6087-11A-01R-1672-07 TCGA-B2-5641-11A-01R-1541-07
## colData names(62): barcode patient ... subtype_mRNA_cluster
## subtype_microRNA_cluster
## [1] "TCGA-KIRP"
## Downloading data for project TCGA-KIRP
## GDCdownload will download 32 files. A total of 16.829865 MB
## Downloading as: Mon_Nov_25_09_53_31_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## kirp subtype information from:doi:10.1056/NEJMoa1505917
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-KIRP.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 32
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(32): TCGA-P4-A5E8-11A-12R-A28H-07 TCGA-BQ-5894-11A-01R-1592-07
## ... TCGA-BQ-5884-11A-01R-1592-07 TCGA-GL-6846-11A-01R-1965-07
## colData names(210): barcode patient ... subtype_VHL.copy..log2.normal.
## subtype_NF2.copy..log2.normal.
## [1] "TCGA-LAML"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-LAML"
## [1] "TCGA-LGG"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-LGG"
## [1] "TCGA-LIHC"
## Downloading data for project TCGA-LIHC
## GDCdownload will download 50 files. A total of 23.991988 MB
## Downloading as: Mon_Nov_25_09_53_52_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-LIHC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 50
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(50): TCGA-EP-A3RK-11A-11R-A22L-07 TCGA-BC-A10T-11A-11R-A131-07
## ... TCGA-G3-A3CH-11A-11R-A22L-07 TCGA-FV-A3I0-11A-11R-A22L-07
## colData names(63): barcode patient ... name sample.aux
## [1] "TCGA-LUAD"
## Downloading data for project TCGA-LUAD
## GDCdownload will download 59 files. A total of 30.327633 MB
## Downloading as: Mon_Nov_25_09_54_32_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## luad subtype information from:doi:10.1038/nature13385
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-LUAD.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 59
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(59): TCGA-55-6971-11A-01R-1949-07 TCGA-44-6778-11A-01R-1858-07
## ... TCGA-91-6849-11A-01R-1949-07 TCGA-49-6761-11A-01R-1949-07
## colData names(83): barcode patient ... subtype_Ploidy.ABSOLUTE.calls
## subtype_Purity.ABSOLUTE.calls
## [1] "TCGA-LUSC"
## Downloading data for project TCGA-LUSC
## GDCdownload will download 49 files. A total of 25.951806 MB
## Downloading as: Mon_Nov_25_09_55_04_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## lusc subtype information from:doi:10.1038/nature11404
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-LUSC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 49
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(49): TCGA-33-6737-11A-01R-1820-07 TCGA-77-7335-11A-01R-2045-07
## ... TCGA-77-7138-11A-01R-2045-07 TCGA-22-4593-11A-01R-1820-07
## colData names(76): barcode patient ... subtype_Homozygous.Deletions
## subtype_Expression.Subtype
## [1] "TCGA-MESO"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-MESO"
## [1] "TCGA-OV"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-OV"
## [1] "TCGA-PAAD"
## Downloading data for project TCGA-PAAD
## GDCdownload will download 4 files. A total of 2.134398 MB
## Downloading as: Mon_Nov_25_09_55_35_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## paad subtype information from:doi:10.1016/j.ccell.2017.07.007
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-PAAD.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 4
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(4): TCGA-H6-A45N-11A-12R-A26U-07 TCGA-HV-A5A3-11A-11R-A26U-07
## TCGA-YB-A89D-11A-11R-A36G-07 TCGA-H6-8124-11A-01R-2404-07
## colData names(119): barcode patient ... subtype_Year of tobacco smoking
## onset subtype_patient
## [1] "TCGA-PCPG"
## Downloading data for project TCGA-PCPG
## GDCdownload will download 3 files. A total of 1.511128 MB
## Downloading as: Mon_Nov_25_09_56_02_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## pcpg subtype information from:doi:10.1016/j.ccell.2017.01.001
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-PCPG.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 3
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(3): TCGA-SQ-A6I4-11A-11R-A35L-07 TCGA-P8-A5KC-11A-11R-A35K-07
## TCGA-P8-A5KD-11A-11R-A35K-07
## colData names(150): barcode patient ... subtype_RPPA Cluster
## subtype_Presence of Adrenal Cortical Cells/Tissue on Pathology
## Re-review
## [1] "TCGA-PRAD"
## Downloading data for project TCGA-PRAD
## GDCdownload will download 52 files. A total of 27.097879 MB
## Downloading as: Mon_Nov_25_09_56_17_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## prad subtype information from:doi:10.1016/j.cell.2015.10.025
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-PRAD.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 52
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(52): TCGA-EJ-7783-11A-01R-2118-07 TCGA-CH-5761-11A-01R-1580-07
## ... TCGA-G9-6362-11A-01R-1789-07 TCGA-HC-7740-11A-01R-2118-07
## colData names(145): barcode patient ... subtype_AR_V7_ratio
## subtype_AR_V7_presence
## [1] "TCGA-READ"
## Downloading data for project TCGA-READ
## GDCdownload will download 10 files. A total of 5.128913 MB
## Downloading as: Mon_Nov_25_09_56_51_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## read subtype information from:doi:10.1038/nature11252
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-READ.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 10
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(10): TCGA-AF-2689-11A-01R-A32Z-07 TCGA-AG-3725-11A-01R-1736-07
## ... TCGA-AG-3742-11A-01R-1660-07 TCGA-AF-2692-11A-01R-A32Z-07
## colData names(106): barcode patient ...
## subtype_vascular_invasion_present subtype_vital_status
## [1] "TCGA-SARC"
## Downloading data for project TCGA-SARC
## GDCdownload will download 2 files. A total of 989.131 KB
## Downloading as: Mon_Nov_25_09_57_09_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## sarc subtype information from:doi:10.1016/j.cell.2017.10.014
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-SARC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 2
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(2): TCGA-K1-A3PO-11A-12R-A21T-07 TCGA-FX-A2QS-11A-11R-A21T-07
## colData names(107): barcode patient ... subtype_CIN subtype_Mutation
## Load
## [1] "TCGA-SKCM"
## Downloading data for project TCGA-SKCM
## GDCdownload will download: 517.985 KB
## Downloading as: 7b98f1f0-ec44-4414-8e1c-0d29a386e45c.FPKM-UQ.txt.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## skcm subtype information from:doi:10.1016/j.cell.2015.05.044
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Accessing www.ensembl.org (mirror useast)
## Downloading genome information (try:1) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-SKCM.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 1
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(1): TCGA-GN-A4U8-11A-11R-A32P-07
## colData names(166): barcode patient ... subtype_DIPYRIM.C.T.n.C.T..mut
## subtype_SHATTERSEEK_Chromothripsis_calls
## [1] "TCGA-STAD"
## Downloading data for project TCGA-STAD
## GDCdownload will download 32 files. A total of 17.059642 MB
## Downloading as: Mon_Nov_25_09_59_23_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## stad subtype information from:doi:10.1038/nature13480
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-STAD.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 32
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(32): TCGA-BR-6453-11A-01R-1802-13 TCGA-BR-6454-11A-01R-1802-13
## ... TCGA-CG-5734-11A-01R-1602-13 TCGA-BR-7715-11A-01R-2055-13
## colData names(109): barcode patient ... subtype_CIMP.Category
## subtype_stringAsFactor
## [1] "TCGA-TGCT"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-TGCT"
## [1] "TCGA-THCA"
## Downloading data for project TCGA-THCA
## GDCdownload will download 58 files. A total of 30.745843 MB
## Downloading as: Mon_Nov_25_09_59_48_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## thca subtype information from:doi:10.1016/j.cell.2014.09.050
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-THCA.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 58
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(58): TCGA-KS-A41J-11A-12R-A23N-07 TCGA-BJ-A2N8-11A-11R-A18C-07
## ... TCGA-EL-A3ZK-11A-11R-A23N-07 TCGA-BJ-A3PR-11A-11R-A220-07
## colData names(238): barcode patient ... subtype_TERT_AC subtype_TERT_Q
## [1] "TCGA-THYM"
## Downloading data for project TCGA-THYM
## GDCdownload will download 2 files. A total of 1.085485 MB
## Downloading as: Mon_Nov_25_10_00_16_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-THYM.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 2
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(2): TCGA-X7-A8D7-11A-11R-A42C-07 TCGA-X7-A8D6-11A-22R-A42C-07
## colData names(54): barcode patient ... name sample.aux
## [1] "TCGA-UCEC"
## Downloading data for project TCGA-UCEC
## GDCdownload will download 35 files. A total of 18.035498 MB
## Downloading as: Mon_Nov_25_10_00_42_2019.tar.gz
## Starting to add information to samples
## => Add clinical information to samples
## => Adding subtype information to samples
## ucec subtype information from:doi:10.1038/nature12113
## Accessing www.ensembl.org to get gene information
## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)
## Cache found
## From the 60483 genes we couldn't map 3971
## Saving file:TCGA-UCEC.rda
## File saved
## class: RangedSummarizedExperiment
## dim: 56512 35
## metadata(1): data_release
## assays(1): HTSeq - FPKM-UQ
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
## ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
## original_ensembl_gene_id
## colnames(35): TCGA-DI-A2QY-11A-11R-A19W-07 TCGA-FL-A1YF-11A-12R-A16F-07
## ... TCGA-FL-A1YI-11A-11R-A16F-07 TCGA-DI-A2QU-11A-11R-A18M-07
## colData names(78): barcode patient ... subtype_cna_cluster_k4
## subtype_mrna_expression_cluster
## [1] "TCGA-UCS"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-UCS"
## [1] "TCGA-UVM"
## [1] "No FPKM-UQ data of solid normal tissue for TCGA-UVM"
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