1.安装加载RTCGA：R包

#加载包
library(RTCGA)
library(RTCGA.clinical)
library(RTCGA.miRNASeq)
library(RTCGA.mRNA)
library(RTCGA.rnaseq)
library(RTCGA.mutations)

2.指定基因HSF1从癌症里获取芯片表达数据

Breast invasive carcinoma (BRCA)
Ovarian serous cystadenocarcinoma (OV)
Lung squamous cell carcinoma (LUSC)

expr<-expressionsTCGA(BRCA.mRNA,OV.mRNA,LUSC.mRNA,
                      extract.cols = c("HSF1")
                      )
expr
  bcr_patient_barcode          dataset      HSF1
   <chr>                        <chr>       <dbl>
 1 TCGA-A1-A0SD-01A-11R-A115-07 BRCA.mRNA -0.290 
 2 TCGA-A1-A0SE-01A-11R-A084-07 BRCA.mRNA  0.134 
 3 TCGA-A1-A0SH-01A-11R-A084-07 BRCA.mRNA  0.332 
 4 TCGA-A1-A0SJ-01A-11R-A084-07 BRCA.mRNA  0.614 
 5 TCGA-A1-A0SK-01A-12R-A084-07 BRCA.mRNA  1.09  
 6 TCGA-A1-A0SM-01A-11R-A084-07 BRCA.mRNA -0.124 
 7 TCGA-A1-A0SO-01A-22R-A084-07 BRCA.mRNA -1.3   
 8 TCGA-A1-A0SP-01A-11R-A084-07 BRCA.mRNA  0.797 
 9 TCGA-A2-A04N-01A-11R-A115-07 BRCA.mRNA  0.0912
10 TCGA-A2-A04P-01A-31R-A034-07 BRCA.mRNA  1.04  
# ... with 1,295 more rows

3.查看cancers种类

nb_samples<-table(expr$dataset)
> nb_samples

BRCA.mRNA LUSC.mRNA   OV.mRNA 
      590       154       561 
>

4.修改前两列

expr$dataset<-gsub(pattern = ".mRNA",replacement = "",expr$dataset)
expr$bcr_patient_barcode<-paste0(expr$dataset,c(1:590,1:561,1:154))

修改前

修改后

5.绘制基因HSF1在不同的癌症的表达量boxplot

library(ggpubr)
my_comparisons <- list(c("BRCA", "OV"), c("OV", "LUSC"))
ggboxplot(expr, x = "dataset", y = "HSF1",
          title = "HSF1", ylab = "Expression",
          color = "dataset", palette = "jco")+
  stat_compare_means(comparisons =my_comparisons)

boxplot