RNA-seq data - checking non TCGA/TARGET projects

1 GDC projects

2 HTSeq counts

# the followingprojects do not have RNA-seq data 
# - VAREPOP-APOLLO
# - FM-AD
# - BEATAML1.0-CRENOLANIB
project <- grep("TCGA|TARGET|VAREPOP|FM-AD|CRENO",sort(getGDCprojects()$project_id),
                invert = TRUE,
                value = TRUE)
for(proj in project){
    cat("\n\n## ", proj,"\n\n")
    tryCatch({
        query <- GDCquery(
            project = proj,
            data.category = "Transcriptome Profiling", 
            data.type = "Gene Expression Quantification",
            workflow.type = "HTSeq - Counts"
        )
        query <- GDCquery(
            project = proj,
            data.category = "Transcriptome Profiling", 
            data.type = "Gene Expression Quantification",
            workflow.type = "HTSeq - Counts",
            barcode = getResults(query)$cases[1:10] 
        )
        GDCdownload(query)
        invisible(capture.output(
            data <- GDCprepare(query)
        ))
        kexpand.df(proj)
    }, error = function(e){
        message(e)
    })
    cat("\n\n")
}

2.1 BEATAML1.0-COHORT

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): BA2611R BA3038R ... BA2842R BA2450R
## colData names(30): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.2 CGCI-BLGSP

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): BLGSP-71-06-00162-01A BLGSP-71-06-00159-01A ...
##   BLGSP-71-08-00029-01A BLGSP-71-08-00508-01B
## colData names(55): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.3 CPTAC-2

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): ad5c848c-ae26-42c8-874e-387a09
##   2ddefa4f-77aa-416f-93f3-904e07 ... a2f03d85-5f1a-4b3e-9dbf-74e67e
##   4798bb9d-7100-43aa-b615-85897d
## colData names(35): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.4 CPTAC-3

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): C3L-00448-01 C3L-00096-01 ... C3N-00491-02 C3N-00390-06
## colData names(69): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.5 CTSP-DLBCL1

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): DLBCL11280-sample DLBCL11295-sample ... DLBCL11319-sample
##   DLBCL11284-sample
## colData names(42): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.6 GENIE-DFCI

case_count	file_count	data_category
14232	14232	Simple Nucleotide Variation
14232	14232	Copy Number Variation

2.7 GENIE-GRCC

case_count	file_count	data_category
1038	1038	Simple Nucleotide Variation

2.8 GENIE-JHU

case_count	file_count	data_category
3320	3320	Simple Nucleotide Variation

2.9 GENIE-MDA

case_count	file_count	data_category
3857	3857	Simple Nucleotide Variation

2.10 GENIE-MSK

case_count	file_count	data_category
16823	16823	Simple Nucleotide Variation
16823	16823	Copy Number Variation
2824	2824	Somatic Structural Variation

2.11 GENIE-NKI

case_count	file_count	data_category
801	801	Simple Nucleotide Variation

2.12 GENIE-UHN

case_count	file_count	data_category
2632	2632	Simple Nucleotide Variation

2.13 GENIE-VICC

case_count	file_count	data_category
2052	2052	Simple Nucleotide Variation
1473	1473	Copy Number Variation
308	308	Somatic Structural Variation

2.14 HCMI-CMDC

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): HCM-CSHL-0063-C18-85A HCM-CSHL-0065-C20-06A ...
##   HCM-BROD-0011-C71-01A HCM-BROD-0012-C71-01A
## colData names(58): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.15 MMRF-COMMPASS

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): MMRF_2475_1_BM_CD138pos MMRF_2836_1_BM_CD138pos ...
##   MMRF_2597_1_BM_CD138pos MMRF_2807_1_BM_CD138pos
## colData names(41): barcode sample ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.16 NCICCR-DLBCL

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): DLBCL11676-sample DLBCL10991-sample ... DLBCL10951-sample
##   DLBCL10995-sample
## colData names(32): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.17 OHSU-CNL

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): 3784R 2474R ... 4191R 2648R
## colData names(31): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

2.18 ORGANOID-PANCREATIC

## class: RangedSummarizedExperiment 
## dim: 56512 10 
## metadata(1): data_release
## assays(1): HTSeq - Counts
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(10): S158 S181 ... S194 S211
## colData names(31): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

3 STAR counts

# the followingprojects do not have RNA-seq data 
# - VAREPOP-APOLLO
# - FM-AD
# - BEATAML1.0-CRENOLANIB
project <- c("CPTAC-3","MMRF-COMMPASS","TARGET-OS","CGCI-BLGSP")
for(proj in project){
    cat("\n\n## ", proj,"\n\n")
    tryCatch({
        query <- GDCquery(
            project = proj,
            data.category = "Transcriptome Profiling", 
            data.type = "Gene Expression Quantification",
              workflow.type = "STAR - Counts"
        )
        query <- GDCquery(
            project = proj,
            data.category = "Transcriptome Profiling", 
            data.type = "Gene Expression Quantification",
              workflow.type = "STAR - Counts",
            barcode = getResults(query)$cases[1:4] 
        )
        GDCdownload(query)
        invisible(capture.output(
            data <- GDCprepare(query)
        ))
        kexpand.df(paste0("START counts - ", proj))
    }, error = function(e){
        message(e)
    })
    cat("\n\n")
}

3.1 CPTAC-3

## class: RangedSummarizedExperiment 
## dim: 56512 4 
## metadata(1): data_release
## assays(3): unstranded stranded_first stranded_second
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(4): C3N-00383-04 C3N-00847-01 C3L-02365-01 C3L-01248-01
## colData names(65): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

3.2 MMRF-COMMPASS

## class: RangedSummarizedExperiment 
## dim: 56512 4 
## metadata(1): data_release
## assays(3): unstranded stranded_first stranded_second
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(4): MMRF_2091_1_BM_CD138pos MMRF_2422_1_BM_CD138pos
##   MMRF_1048_1_BM_CD138pos MMRF_2608_1_BM_CD138pos
## colData names(39): barcode sample ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

3.3 TARGET-OS

## class: RangedSummarizedExperiment 
## dim: 56512 4 
## metadata(1): data_release
## assays(3): unstranded stranded_first stranded_second
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(4): TARGET-40-PANMIG-01A-01R TARGET-40-PATMXR-01A-01R
##   TARGET-40-PAKXLD-01A-01R TARGET-40-0A4HXS-01A-01R
## colData names(46): nucleic.acid.code tumor.code ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths

3.4 CGCI-BLGSP

## class: RangedSummarizedExperiment 
## dim: 56512 4 
## metadata(1): data_release
## assays(3): unstranded stranded_first stranded_second
## rownames(56512): ENSG00000000003 ENSG00000000005 ... ENSG00000281912
##   ENSG00000281920
## rowData names(3): ensembl_gene_id external_gene_name
##   original_ensembl_gene_id
## colnames(4): BLGSP-71-08-00194-01A BLGSP-71-06-00155-01A
##   BLGSP-71-19-00113-01A BLGSP-71-08-00036-01A
## colData names(52): sample sample_submitter_id ... project_id name

## GRanges object with 56512 ranges and 3 metadata columns:
##                   seqnames              ranges strand | ensembl_gene_id
##                      <Rle>           <IRanges>  <Rle> |     <character>
##   ENSG00000000003     chrX 100627108-100639991      - | ENSG00000000003
##   ENSG00000000005     chrX 100584936-100599885      + | ENSG00000000005
##   ENSG00000000419    chr20   50934867-50958555      - | ENSG00000000419
##   ENSG00000000457     chr1 169849631-169894267      - | ENSG00000000457
##   ENSG00000000460     chr1 169662007-169854080      + | ENSG00000000460
##               ...      ...                 ...    ... .             ...
##   ENSG00000281904     chr2   90365737-90367699      + | ENSG00000281904
##   ENSG00000281909    chr15   22480439-22484840      - | ENSG00000281909
##   ENSG00000281910    chr16   58559796-58559931      - | ENSG00000281910
##   ENSG00000281912     chr1   45303910-45305619      + | ENSG00000281912
##   ENSG00000281920     chr2   65623272-65628424      + | ENSG00000281920
##                   external_gene_name original_ensembl_gene_id
##                          <character>              <character>
##   ENSG00000000003             TSPAN6       ENSG00000000003.13
##   ENSG00000000005               TNMD        ENSG00000000005.5
##   ENSG00000000419               DPM1       ENSG00000000419.11
##   ENSG00000000457              SCYL3       ENSG00000000457.12
##   ENSG00000000460           C1orf112       ENSG00000000460.15
##               ...                ...                      ...
##   ENSG00000281904         AC233263.6        ENSG00000281904.1
##   ENSG00000281909            HERC2P7        ENSG00000281909.1
##   ENSG00000281910           SNORA50A        ENSG00000281910.1
##   ENSG00000281912          LINC01144        ENSG00000281912.1
##   ENSG00000281920         AC007389.5        ENSG00000281920.1
##   -------
##   seqinfo: 24 sequences from an unspecified genome; no seqlengths