TCGAbiolinks to DESEq2

library(TCGAbiolinks)
library(dplyr)

1 Download Raw counts

library(TCGAbiolinks)
library(SummarizedExperiment)
query <- GDCquery(project = "TCGA-SARC",
                  sample.type = "Primary solid Tumor",
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification",
                  workflow.type = "HTSeq - FPKM",
                  barcode = c("TCGA-WK-A8Y0","TCGA-MJ-A68H"))
GDCdownload(query) 

2 not mapping genes

data <- GDCprepare(query,summarizedExperiment = FALSE)

## 
|                                                    |  0%                      
|==========================                          | 50% ~0 s remaining       
|====================================================|100% ~0 s remaining       
|====================================================|100%                      Completed after 0 s

dim(data)

## [1] 60483     3

data[1:4,1:2]

3 mapping genes

se <- GDCprepare(query,summarizedExperiment = TRUE)

## 
|                                                    |  0%                      
|==========================                          | 50% ~0 s remaining       
|====================================================|100% ~0 s remaining       
|====================================================|100%                      Completed after 0 s

## Starting to add information to samples

##  => Add clinical information to samples

## Add FFPE information. More information at: 
## => https://cancergenome.nih.gov/cancersselected/biospeccriteria 
## => http://gdac.broadinstitute.org/runs/sampleReports/latest/FPPP_FFPE_Cases.html

##  => 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

dim(se)

## [1] 56512     2

4 Genes not in the database

gene.information <- TCGAbiolinks::get.GRCh.bioMart("hg38")

## Accessing www.ensembl.org to get gene information

## Downloading genome information (try:0) Using: Human genes (GRCh38.p13)

## Cache found

# How many are not in the database
data$X1[!gsub("\\.[0-9]*$","",data$X1) %in% gene.information$ensembl_gene_id] %>% length

## [1] 3971

Examples not found:

• https://useast.ensembl.org/Homo_sapiens/Gene/Idhistory?g=ENSG00000277669
• https://useast.ensembl.org/Homo_sapiens/Gene/Idhistory?g=ENSG00000279937

# list of genes not in database
data$X1[!gsub("\\.[0-9]*$","",data$X1) %in% gene.information$ensembl_gene_id] %>%
     as.data.frame()

annotation <- rtracklayer::import.gff3("~/Downloads/gencode.v22.annotation.gff3.gz")
table(data$X1 %in% annotation$gene_id)

## 
## FALSE  TRUE 
##    50 60433

data$X1[!data$X1 %in% annotation$gene_id]

##  [1] "ENSGR0000264510.4"  "ENSGR0000167393.15" "ENSGR0000223773.5" 
##  [4] "ENSGR0000223511.4"  "ENSGR0000227159.6"  "ENSGR0000226179.4" 
##  [7] "ENSGR0000277120.3"  "ENSGR0000237801.4"  "ENSGR0000002586.16"
## [10] "ENSGR0000228410.4"  "ENSGR0000234958.4"  "ENSGR0000236017.6" 
## [13] "ENSGR0000265658.4"  "ENSGR0000197976.9"  "ENSGR0000198223.13"
## [16] "ENSGR0000185960.11" "ENSGR0000263835.4"  "ENSGR0000230542.4" 
## [19] "ENSGR0000281849.1"  "ENSGR0000124333.13" "ENSGR0000124334.15"
## [22] "ENSGR0000169084.11" "ENSGR0000276543.3"  "ENSGR0000178605.11"
## [25] "ENSGR0000225661.5"  "ENSGR0000185203.10" "ENSGR0000196433.10"
## [28] "ENSGR0000280767.1"  "ENSGR0000168939.9"  "ENSGR0000169100.11"
## [31] "ENSGR0000237531.4"  "ENSGR0000229232.4"  "ENSGR0000182484.13"
## [34] "ENSGR0000214717.8"  "ENSGR0000236871.5"  "ENSGR0000182378.11"
## [37] "ENSGR0000185291.9"  "ENSGR0000234622.4"  "ENSGR0000169093.13"
## [40] "ENSGR0000205755.9"  "ENSGR0000237040.4"  "ENSGR0000264819.4" 
## [43] "ENSGR0000223484.5"  "ENSGR0000182162.8"  "ENSGR0000228572.5" 
## [46] "ENSGR0000275287.3"  "ENSGR0000263980.4"  "ENSGR0000270726.4" 
## [49] "ENSGR0000223274.4"  "ENSGR0000223571.4"

annotation.protein.coding <- annotation[annotation$gene_type == "protein_coding"]
length(unique(annotation.protein.coding$gene_name))

## [1] 19712

5 Session information

devtools::session_info()

## ─ Session info ───────────────────────────────────────────────────────────────
##  setting  value                       
##  version  R version 3.6.1 (2019-07-05)
##  os       Ubuntu 19.10                
##  system   x86_64, linux-gnu           
##  ui       X11                         
##  language en_US                       
##  collate  en_US.UTF-8                 
##  ctype    en_US.UTF-8                 
##  tz       America/New_York            
##  date     2019-12-02                  
## 
## ─ Packages ───────────────────────────────────────────────────────────────────
##  ! package              * version   date       lib source        
##    annotate               1.64.0    2019-10-29 [1] Bioconductor  
##    AnnotationDbi          1.48.0    2019-10-29 [1] Bioconductor  
##    aroma.light            3.16.0    2019-10-29 [1] Bioconductor  
##    askpass                1.1       2019-01-13 [2] CRAN (R 3.6.1)
##    assertthat             0.2.1     2019-03-21 [2] CRAN (R 3.6.1)
##    backports              1.1.5     2019-10-02 [2] CRAN (R 3.6.1)
##    base64enc              0.1-3     2015-07-28 [2] CRAN (R 3.6.1)
##    Biobase              * 2.46.0    2019-10-29 [1] Bioconductor  
##    BiocFileCache          1.10.0    2019-10-29 [1] Bioconductor  
##    BiocGenerics         * 0.32.0    2019-10-29 [1] Bioconductor  
##    BiocParallel         * 1.20.0    2019-10-30 [1] Bioconductor  
##    biomaRt                2.42.0    2019-10-29 [1] Bioconductor  
##    Biostrings             2.54.0    2019-10-29 [1] Bioconductor  
##    bit                    1.1-14    2018-05-29 [2] CRAN (R 3.6.1)
##    bit64                  0.9-7     2017-05-08 [2] CRAN (R 3.6.1)
##    bitops                 1.0-6     2013-08-17 [2] CRAN (R 3.6.1)
##    blob                   1.2.0     2019-07-09 [2] CRAN (R 3.6.1)
##    broom                  0.5.2     2019-04-07 [2] CRAN (R 3.6.1)
##    callr                  3.3.2     2019-09-22 [2] CRAN (R 3.6.1)
##    circlize               0.4.8     2019-09-08 [2] CRAN (R 3.6.1)
##    cli                    1.1.0     2019-03-19 [2] CRAN (R 3.6.1)
##    clue                   0.3-57    2019-02-25 [2] CRAN (R 3.6.1)
##    cluster                2.1.0     2019-06-19 [4] CRAN (R 3.6.1)
##    codetools              0.2-16    2018-12-24 [4] CRAN (R 3.6.0)
##    colorspace             1.4-1     2019-03-18 [2] CRAN (R 3.6.1)
##    ComplexHeatmap         2.2.0     2019-10-29 [2] Bioconductor  
##    ConsensusClusterPlus   1.50.0    2019-10-29 [1] Bioconductor  
##    crayon                 1.3.4     2017-09-16 [2] CRAN (R 3.6.1)
##    curl                   4.3       2019-12-02 [2] CRAN (R 3.6.1)
##    data.table             1.12.6    2019-10-18 [1] CRAN (R 3.6.1)
##    DBI                    1.0.0     2018-05-02 [2] CRAN (R 3.6.1)
##    dbplyr                 1.4.2     2019-06-17 [2] CRAN (R 3.6.1)
##    DelayedArray         * 0.12.0    2019-10-29 [1] Bioconductor  
##    desc                   1.2.0     2018-05-01 [2] CRAN (R 3.6.1)
##    DESeq                  1.38.0    2019-10-29 [1] Bioconductor  
##    devtools               2.2.1     2019-09-24 [2] CRAN (R 3.6.1)
##    digest                 0.6.22    2019-10-21 [1] CRAN (R 3.6.1)
##    doParallel             1.0.15    2019-08-02 [2] CRAN (R 3.6.1)
##    downloader             0.4       2015-07-09 [2] CRAN (R 3.6.1)
##    dplyr                * 0.8.3     2019-07-04 [2] CRAN (R 3.6.1)
##    EDASeq                 2.20.0    2019-10-29 [1] Bioconductor  
##    edgeR                  3.28.0    2019-10-29 [1] Bioconductor  
##    ellipsis               0.3.0     2019-09-20 [2] CRAN (R 3.6.1)
##    evaluate               0.14      2019-05-28 [2] CRAN (R 3.6.1)
##    foreach                1.4.7     2019-07-27 [2] CRAN (R 3.6.1)
##    fs                     1.3.1     2019-05-06 [2] CRAN (R 3.6.1)
##    genefilter             1.68.0    2019-10-29 [1] Bioconductor  
##    geneplotter            1.64.0    2019-10-29 [1] Bioconductor  
##    generics               0.0.2     2018-11-29 [2] CRAN (R 3.6.1)
##    GenomeInfoDb         * 1.22.0    2019-10-29 [1] Bioconductor  
##    GenomeInfoDbData       1.2.2     2019-11-06 [1] Bioconductor  
##    GenomicAlignments      1.22.0    2019-10-29 [1] Bioconductor  
##    GenomicFeatures        1.38.0    2019-10-29 [1] Bioconductor  
##    GenomicRanges        * 1.38.0    2019-10-29 [1] Bioconductor  
##    GetoptLong             0.1.7     2018-06-10 [2] CRAN (R 3.6.1)
##    ggplot2                3.2.1     2019-08-10 [2] CRAN (R 3.6.1)
##    ggpubr                 0.2.4     2019-11-14 [2] CRAN (R 3.6.1)
##    ggrepel                0.8.1     2019-05-07 [2] CRAN (R 3.6.1)
##    ggsignif               0.6.0     2019-08-08 [2] CRAN (R 3.6.1)
##    ggthemes               4.2.0     2019-05-13 [2] CRAN (R 3.6.1)
##    GlobalOptions          0.1.1     2019-09-30 [2] CRAN (R 3.6.1)
##    glue                   1.3.1     2019-03-12 [2] CRAN (R 3.6.1)
##    gridExtra              2.3       2017-09-09 [2] CRAN (R 3.6.1)
##    gtable                 0.3.0     2019-03-25 [1] CRAN (R 3.6.1)
##    hms                    0.5.2     2019-10-30 [2] CRAN (R 3.6.1)
##    htmltools              0.4.0     2019-10-04 [2] CRAN (R 3.6.1)
##    httr                   1.4.1     2019-08-05 [2] CRAN (R 3.6.1)
##    hwriter                1.3.2     2014-09-10 [2] CRAN (R 3.6.1)
##    IRanges              * 2.20.0    2019-10-29 [1] Bioconductor  
##    iterators              1.0.12    2019-07-26 [2] CRAN (R 3.6.1)
##    jsonlite               1.6       2018-12-07 [2] CRAN (R 3.6.1)
##    km.ci                  0.5-2     2009-08-30 [2] CRAN (R 3.6.1)
##    KMsurv                 0.1-5     2012-12-03 [2] CRAN (R 3.6.1)
##    knitr                  1.26      2019-11-12 [2] CRAN (R 3.6.1)
##    lattice                0.20-38   2018-11-04 [4] CRAN (R 3.6.0)
##    latticeExtra           0.6-28    2016-02-09 [2] CRAN (R 3.6.1)
##    lazyeval               0.2.2     2019-03-15 [2] CRAN (R 3.6.1)
##    lifecycle              0.1.0     2019-08-01 [2] CRAN (R 3.6.1)
##    limma                  3.42.0    2019-10-29 [1] Bioconductor  
##    locfit                 1.5-9.1   2013-04-20 [2] CRAN (R 3.6.1)
##    magrittr               1.5       2014-11-22 [2] CRAN (R 3.6.1)
##    matlab                 1.0.2     2014-06-24 [2] CRAN (R 3.6.1)
##    Matrix                 1.2-18    2019-11-27 [2] CRAN (R 3.6.1)
##    matrixStats          * 0.55.0    2019-09-07 [2] CRAN (R 3.6.1)
##    memoise                1.1.0     2017-04-21 [2] CRAN (R 3.6.1)
##    mgcv                   1.8-31    2019-11-09 [4] CRAN (R 3.6.1)
##    munsell                0.5.0     2018-06-12 [2] CRAN (R 3.6.1)
##    nlme                   3.1-142   2019-11-07 [4] CRAN (R 3.6.1)
##    openssl                1.4.1     2019-07-18 [2] CRAN (R 3.6.1)
##    pillar                 1.4.2     2019-06-29 [2] CRAN (R 3.6.1)
##    pkgbuild               1.0.6     2019-10-09 [2] CRAN (R 3.6.1)
##    pkgconfig              2.0.3     2019-09-22 [2] CRAN (R 3.6.1)
##    pkgload                1.0.2     2018-10-29 [2] CRAN (R 3.6.1)
##    plyr                   1.8.4     2016-06-08 [2] CRAN (R 3.6.1)
##    png                    0.1-7     2013-12-03 [2] CRAN (R 3.6.1)
##    prettyunits            1.0.2     2015-07-13 [2] CRAN (R 3.6.1)
##    processx               3.4.1     2019-07-18 [2] CRAN (R 3.6.1)
##    progress               1.2.2     2019-05-16 [2] CRAN (R 3.6.1)
##    ps                     1.3.0     2018-12-21 [2] CRAN (R 3.6.1)
##    purrr                  0.3.3     2019-10-18 [1] CRAN (R 3.6.1)
##    R.methodsS3            1.7.1     2016-02-16 [2] CRAN (R 3.6.1)
##    R.oo                   1.23.0    2019-11-03 [1] CRAN (R 3.6.1)
##    R.utils                2.9.0     2019-06-13 [2] CRAN (R 3.6.1)
##    R6                     2.4.1     2019-11-12 [2] CRAN (R 3.6.1)
##    rappdirs               0.3.1     2016-03-28 [2] CRAN (R 3.6.1)
##    RColorBrewer           1.1-2     2014-12-07 [1] CRAN (R 3.6.1)
##    Rcpp                   1.0.3     2019-11-08 [2] CRAN (R 3.6.1)
##    RCurl                  1.95-4.12 2019-03-04 [2] CRAN (R 3.6.1)
##    readr                  1.3.1     2018-12-21 [2] CRAN (R 3.6.1)
##    remotes                2.1.0     2019-06-24 [2] CRAN (R 3.6.1)
##    rjson                  0.2.20    2018-06-08 [2] CRAN (R 3.6.1)
##    rlang                  0.4.2     2019-11-23 [2] CRAN (R 3.6.1)
##    rmarkdown              1.16      2019-10-01 [1] CRAN (R 3.6.1)
##    rprojroot              1.3-2     2018-01-03 [2] CRAN (R 3.6.1)
##    Rsamtools              2.2.0     2019-10-29 [1] Bioconductor  
##    RSQLite                2.1.2     2019-07-24 [2] CRAN (R 3.6.1)
##    rtracklayer            1.46.0    2019-10-29 [1] Bioconductor  
##    rvest                  0.3.5     2019-11-08 [2] CRAN (R 3.6.1)
##    S4Vectors            * 0.24.0    2019-10-29 [1] Bioconductor  
##    scales                 1.1.0     2019-11-18 [2] CRAN (R 3.6.1)
##    selectr                0.4-2     2019-11-20 [2] CRAN (R 3.6.1)
##    sessioninfo            1.1.1     2018-11-05 [2] CRAN (R 3.6.1)
##    shape                  1.4.4     2018-02-07 [2] CRAN (R 3.6.1)
##    ShortRead              1.44.0    2019-10-29 [1] Bioconductor  
##    stringi                1.4.3     2019-03-12 [2] CRAN (R 3.6.1)
##    stringr                1.4.0     2019-02-10 [2] CRAN (R 3.6.1)
##    SummarizedExperiment * 1.16.0    2019-10-29 [1] Bioconductor  
##    survival               3.1-7     2019-11-09 [4] CRAN (R 3.6.1)
##    survminer              0.4.6     2019-09-03 [2] CRAN (R 3.6.1)
##    survMisc               0.5.5     2018-07-05 [2] CRAN (R 3.6.1)
##    sva                    3.34.0    2019-10-29 [1] Bioconductor  
##  R TCGAbiolinks         * 2.14.0    <NA>       [2] <NA>          
##    testthat               2.3.1     2019-12-01 [2] CRAN (R 3.6.1)
##    tibble                 2.1.3     2019-06-06 [2] CRAN (R 3.6.1)
##    tidyr                  1.0.0     2019-09-11 [2] CRAN (R 3.6.1)
##    tidyselect             0.2.5     2018-10-11 [2] CRAN (R 3.6.1)
##    usethis                1.5.1     2019-07-04 [2] CRAN (R 3.6.1)
##    vctrs                  0.2.0     2019-07-05 [2] CRAN (R 3.6.1)
##    withr                  2.1.2     2018-03-15 [2] CRAN (R 3.6.1)
##    xfun                   0.10      2019-10-01 [1] CRAN (R 3.6.1)
##    XML                    3.98-1.20 2019-06-06 [2] CRAN (R 3.6.1)
##    xml2                   1.2.2     2019-08-09 [2] CRAN (R 3.6.1)
##    xtable                 1.8-4     2019-04-21 [2] CRAN (R 3.6.1)
##    XVector                0.26.0    2019-10-29 [1] Bioconductor  
##    yaml                   2.2.0     2018-07-25 [2] CRAN (R 3.6.1)
##    zeallot                0.1.0     2018-01-28 [2] CRAN (R 3.6.1)
##    zlibbioc               1.32.0    2019-10-29 [1] Bioconductor  
##    zoo                    1.8-6     2019-05-28 [2] CRAN (R 3.6.1)
## 
## [1] /home/tiagochst/R/x86_64-pc-linux-gnu-library/3.6
## [2] /usr/local/lib/R/site-library
## [3] /usr/lib/R/site-library
## [4] /usr/lib/R/library
## 
##  R ── Package was removed from disk.