Working with simple somatic mutations

Sean Davis

Monday, November 07, 2022

Background

Workflow

library(GenomicDataCommons)
library(tibble)

Genes and gene details

grep_fields('genes', 'symbol')

## [1] "symbol"

head(available_values('genes','symbol'))

## [1] "y_rna" "ids"   "matr3" "or4m2" "tubb3" "a1bg"

tp53 = genes() %>% 
  GenomicDataCommons::filter(symbol=='TP53') %>% 
  results(size=10000) %>% 
  as_tibble()

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] 1306

ssms() %>% 
    GenomicDataCommons::filter(
      consequence.transcript.gene.symbol %in% c('TP53')) %>% 
    GenomicDataCommons::count()

## [1] 1303

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] 5093

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 
##                                           7 
##                Adenomas and Adenocarcinomas 
##                                        1516 
##        Adnexal and Skin Appendage Neoplasms 
##                                           1 
##                Complex Epithelial Neoplasms 
##                                          16 
##         Complex Mixed and Stromal Neoplasms 
##                                          69 
##       Cystic, Mucinous and Serous Neoplasms 
##                                         616 
##                Ductal and Lobular Neoplasms 
##                                         628 
##                   Epithelial Neoplasms, NOS 
##                                          12 
##                       Fibromatous Neoplasms 
##                                          12 
##                         Germ Cell Neoplasms 
##                                           1 
##                                     Gliomas 
##                                         480 
##                        Lipomatous Neoplasms 
##                                           6 
##                          Lymphoid Leukemias 
##                                           1 
##                     Mature B-Cell Lymphomas 
##                                           5 
##                       Mesothelial Neoplasms 
##                                          11 
##                   Miscellaneous Bone Tumors 
##                                           1 
##                   Myelodysplastic Syndromes 
##                                           3 
##                           Myeloid Leukemias 
##                                          30 
##                         Myomatous Neoplasms 
##                                          59 
##                              Neoplasms, NOS 
##                                           9 
##                         Nerve Sheath Tumors 
##                                           1 
##                          Nevi and Melanomas 
##                                          85 
##                                Not Reported 
##                                           6 
##                          Plasma Cell Tumors 
##                                          53 
##        Soft Tissue Tumors and Sarcomas, NOS 
##                                          32 
##                     Squamous Cell Neoplasms 
##                                        1203 
##                 Thymic Epithelial Neoplasms 
##                                           4 
## Transitional Cell Papillomas and Carcinomas 
##                                         226

OncoPrint

fnames <- files() %>%
  GenomicDataCommons::filter(
    cases.project.project_id=='TCGA-SKCM' &
      data_format=='maf' &
      data_type=='Masked Somatic Mutation' &
      analysis.workflow_type ==
        'Aliquot Ensemble Somatic Variant Merging and Masking'
  ) %>%
  results(size = 6) %>%
    ids() %>% 
      gdcdata()

library(maftools)
melanoma = read.maf(maf = fnames[2])

## -Reading
## -Validating
## -Silent variants: 266 
## -Summarizing
## --Possible FLAGS among top ten genes:
##   TTN
##   HMCN1
## -Processing clinical data
## --Missing clinical data
## -Finished in 1.043s elapsed (1.038s cpu)

maftools::oncoplot(melanoma)

## Warning in min(x): no non-missing arguments to min; returning Inf

## Warning in max(x): no non-missing arguments to max; returning -Inf