1 Background

2 Workflow

library(GenomicDataCommons)
library(tibble)

2.1 Genes and gene details

grep_fields('genes', 'symbol')
## [1] "symbol"
head(available_values('genes','symbol'))
## [1] "y_rna"    "c12orf79" "aff2"     "c2orf15"  "c6orf165" "cbs"
tp53 = genes() %>% 
  GenomicDataCommons::filter(symbol=='TP53') %>% 
  results(size=10000) %>% 
  as_tibble()

2.2 ssms

ssms() %>% 
    GenomicDataCommons::filter(
      chromosome==paste0('chr',tp53$gene_chromosome[1]) &
        start_position > tp53$gene_start[1] & 
        end_position < tp53$gene_end[1]) %>% 
    GenomicDataCommons::count()
## [1] 1429
ssms() %>% 
    GenomicDataCommons::filter(
      consequence.transcript.gene.symbol %in% c('TP53')) %>% 
    GenomicDataCommons::count()
## [1] 1426

2.3 convert to VRanges

library(VariantAnnotation)
vars = ssms() %>% 
    GenomicDataCommons::filter(
      consequence.transcript.gene.symbol %in% c('TP53')) %>% 
    GenomicDataCommons::results_all() %>%
    as_tibble()
vr = VRanges(seqnames = vars$chromosome,
             ranges = IRanges(start=vars$start_position, width=1),
             ref = vars$reference_allele,
             alt = vars$tumor_allele)
ssm_occurrences() %>% 
    GenomicDataCommons::filter(
      ssm.consequence.transcript.gene.symbol %in% c('TP53')) %>% 
    GenomicDataCommons::count()
## [1] 5368
var_samples = ssm_occurrences() %>% 
    GenomicDataCommons::filter(
      ssm.consequence.transcript.gene.symbol %in% c('TP53')) %>% 
    GenomicDataCommons::expand(c('case', 'ssm', 'case.project')) %>%
    GenomicDataCommons::results_all() %>% 
    as_tibble()
table(var_samples$case$disease_type)
## 
##                       Acinar Cell Neoplasms 
##                                           8 
##                Adenomas and Adenocarcinomas 
##                                        1549 
##        Adnexal and Skin Appendage Neoplasms 
##                                           1 
##                Complex Epithelial Neoplasms 
##                                          16 
##         Complex Mixed and Stromal Neoplasms 
##                                          72 
##       Cystic, Mucinous and Serous Neoplasms 
##                                         687 
##                Ductal and Lobular Neoplasms 
##                                         664 
##                   Epithelial Neoplasms, NOS 
##                                           9 
##                       Fibromatous Neoplasms 
##                                          15 
##                         Germ Cell Neoplasms 
##                                           1 
##                                     Gliomas 
##                                         515 
##                        Lipomatous Neoplasms 
##                                           6 
##                          Lymphoid Leukemias 
##                                           2 
##                     Mature B-Cell Lymphomas 
##                                           5 
##                       Mesothelial Neoplasms 
##                                          14 
##                   Miscellaneous Bone Tumors 
##                                           1 
##                           Myeloid Leukemias 
##                                          18 
##                         Myomatous Neoplasms 
##                                          60 
##                         Nerve Sheath Tumors 
##                                           1 
##                          Nevi and Melanomas 
##                                          96 
##                                Not Reported 
##                                           9 
##            Paragangliomas and Glomus Tumors 
##                                           1 
##                          Plasma Cell Tumors 
##                                          57 
##        Soft Tissue Tumors and Sarcomas, NOS 
##                                          34 
##                     Squamous Cell Neoplasms 
##                                        1277 
##                 Thymic Epithelial Neoplasms 
##                                           4 
## Transitional Cell Papillomas and Carcinomas 
##                                         246

2.4 OncoPrint

fnames = files() %>%
  GenomicDataCommons::filter(
    cases.project.project_id=='TCGA-SKCM' & data_format=='MAF' & data_type=='Masked Somatic Mutation' & analysis.workflow_type=='MuTect2 Variant Aggregation and Masking') %>%
  ids() %>%
  gdcdata()
## Rows: 1 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: "\t"
## chr (4): id, filename, md5, state
## dbl (1): size
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
library(maftools)
melanoma = read.maf(maf = fnames[1])
## -Reading
## -Validating
## -Silent variants: 166224 
## -Summarizing
## --Possible FLAGS among top ten genes:
##   TTN
##   MUC16
## -Processing clinical data
## --Missing clinical data
## -Finished in 36.4s elapsed (38.5s cpu)
maftools::oncoplot(melanoma)