肿瘤突变负荷(TMB)与等位基因突变的肿瘤异质性(MATH)分数的计算

library(TCGAbiolinks)
query_SNV <- GDCquery(project = "TCGA-COAD",
                      data.category = "Simple Nucleotide Variation",
                      data.type = "Masked Somatic Mutation",
                      workflow.type = "MuTect2 Variant Aggregation and Masking")
GDCdownload(query_SNV)

FilePath = dir("./GDCdata",".somatic.maf.gz$",recursive=T,full.names = T)
maf <- read.maf(FilePath,isTCGA=TRUE)

##计算TMB
tmb <- tmb(maf = maf,
           captureSize = 50,
           logScale = T)
head(tmb)

> head(tmb)
   Tumor_Sample_Barcode total total_perMB total_perMB_log
1:         TCGA-CA-5255    39        0.78     -0.10790540
2:         TCGA-AZ-4323    40        0.80     -0.09691001
3:         TCGA-A6-2685    42        0.84     -0.07572071
4:         TCGA-AA-3488    42        0.84     -0.07572071
5:         TCGA-AA-3869    42        0.84     -0.07572071
6:         TCGA-AZ-4684    42        0.84     -0.07572071

#计算mutant-allele tumor heterogeneity
barcode <- unique(maf@data$Tumor_Sample_Barcode)
head(barcode)
MATH <- data.frame()
for (i in barcode){
  out.math = inferHeterogeneity(maf = maf, tsb = i)
  Tumor_Sample_Barcode=unique(out.math$clusterData$Tumor_Sample_Barcode)
  m = unique(out.math$clusterData$MATH)
  out = data.frame(Tumor_Sample_Barcode, m)
  MATH = rbind(MATH, out)
}
head(MATH)

> head(MATH)
  Tumor_Sample_Barcode        m
1         TCGA-AA-3966 41.51257
2         TCGA-AD-6901 51.32077
3         TCGA-AA-3673 32.15131
4         TCGA-A6-2679 42.79428
5         TCGA-AD-6895 29.01535
6         TCGA-AA-3975 66.23341