作业链接
下载网址
然后找到LIHC
点击进去下载即可
#TP53的ensemble id 为ENSG00000141510 zcat TCGA-LIHC.htseq_counts.tsv.gz | grep -E 'Ensembl_ID|ENSG00000141510' >TP53_tcga_expression.txt
library(dplyr) tp53_tcga = read.table('TP53_tcga_expression.txt',header = T,check.names = F) rownames(tp53_tcga) = 'TP53' tp53_tcga = tp53_tcga[,-1]
> table(colnames(tp53_tcga) %>% sub('TCGA-\\w+-\\w+-','',.) ) 01A 01B 02A 02B 11A 369 2 2 1 50 #tumor个数:369+2+2+1=374 #normal个数:50 #一共424个样本
其中01-09是tumor样本;10-29是normal样本;
这里只保留01A和11A这两种最常用的样本
01代表的是Primary Solid Tumor;11代表的是Solid Tissue Normal,具体详见https://gdc.cancer.gov/resources-tcga-users/tcga-code-tables/sample-type-codes
#只保留01和11两类样本 tp53_tcga <- colnames(tp53_tcga) %>% grepl('-[01]1A', . ,perl = T) %>% which(.) %>% tp53_tcga[,.]
#对保留下来的样本进行统计 > table(colnames(tp53_tcga) %>% sub('TCGA-\\w+-\\w+-','',.) ) 01A 11A 369 50
如下所示,A10Q这个相同即代表的是同一个捐献者
01A代表是取的肿瘤部位的样品,11A代表取的正常组织的样品
TCGA-BC-A10Q-01A 11.514714054138487
TCGA-BC-A10Q-11A 9.843921051289035
提取有上述配对情况的病人id,共计50个
> names(which((colnames(tp53_tcga) %>% sub('-[01]1A','',.) %>% table(.))==2)) [1] "TCGA-BC-A10Q" "TCGA-BC-A10R" "TCGA-BC-A10T" "TCGA-BC-A10U" "TCGA-BC-A10W" "TCGA-BC-A10X" "TCGA-BC-A10Y" "TCGA-BC-A10Z" "TCGA-BC-A110" [10] "TCGA-BC-A216" "TCGA-BD-A2L6" "TCGA-BD-A3EP" "TCGA-DD-A113" "TCGA-DD-A114" "TCGA-DD-A116" "TCGA-DD-A118" "TCGA-DD-A119" "TCGA-DD-A11A" [19] "TCGA-DD-A11B" "TCGA-DD-A11C" "TCGA-DD-A11D" "TCGA-DD-A1EB" "TCGA-DD-A1EC" "TCGA-DD-A1EE" "TCGA-DD-A1EG" "TCGA-DD-A1EH" "TCGA-DD-A1EI" [28] "TCGA-DD-A1EJ" "TCGA-DD-A1EL" "TCGA-DD-A39V" "TCGA-DD-A39W" "TCGA-DD-A39X" "TCGA-DD-A39Z" "TCGA-DD-A3A1" "TCGA-DD-A3A2" "TCGA-DD-A3A3" [37] "TCGA-DD-A3A4" "TCGA-DD-A3A5" "TCGA-DD-A3A6" "TCGA-DD-A3A8" "TCGA-EP-A12J" "TCGA-EP-A26S" "TCGA-EP-A3RK" "TCGA-ES-A2HT" "TCGA-FV-A23B" [46] "TCGA-FV-A2QR" "TCGA-FV-A3I0" "TCGA-FV-A3I1" "TCGA-FV-A3R2" "TCGA-G3-A3CH"
根据上述提取到的样本名字进一步拿到其对应的tumor和normal的表达量数据
tumor_and_normal = names(which((colnames(tp53_tcga) %>% sub('-[01]1A','',.) %>% table(.))==2)) normal = tp53_tcga[,paste0(tumor_and_normal,"-11A")] tumor = tp53_tcga[,paste0(tumor_and_normal,"-01A")]
> normal TCGA-BC-A10Q-11A TCGA-BC-A10R-11A TCGA-BC-A10T-11A TCGA-BC-A10U-11A TCGA-BC-A10W-11A TCGA-BC-A10X-11A TCGA-BC-A10Y-11A TP53 9.843921 10.06474 10.13955 9.896332 9.79279 10.36304 10.56986 TCGA-BC-A10Z-11A TCGA-BC-A110-11A TCGA-BC-A216-11A TCGA-BD-A2L6-11A TCGA-BD-A3EP-11A TCGA-DD-A113-11A TCGA-DD-A114-11A TP53 10.71167 9.810572 9.575539 10.80574 9.930737 9.623881 10.87498 TCGA-DD-A116-11A TCGA-DD-A118-11A TCGA-DD-A119-11A TCGA-DD-A11A-11A TCGA-DD-A11B-11A TCGA-DD-A11C-11A TCGA-DD-A11D-11A TP53 9.847057 8.839204 10.01262 10.59246 9.259743 8.668885 9.971544 TCGA-DD-A1EB-11A TCGA-DD-A1EC-11A TCGA-DD-A1EE-11A TCGA-DD-A1EG-11A TCGA-DD-A1EH-11A TCGA-DD-A1EI-11A TCGA-DD-A1EJ-11A TP53 10.42731 10.11894 9.609179 10.03067 10.28309 10.29806 10.68212 TCGA-DD-A1EL-11A TCGA-DD-A39V-11A TCGA-DD-A39W-11A TCGA-DD-A39X-11A TCGA-DD-A39Z-11A TCGA-DD-A3A1-11A TCGA-DD-A3A2-11A TP53 10.13699 9.544964 10.26796 10.41574 9.854868 8.897845 10.16993 TCGA-DD-A3A3-11A TCGA-DD-A3A4-11A TCGA-DD-A3A5-11A TCGA-DD-A3A6-11A TCGA-DD-A3A8-11A TCGA-EP-A12J-11A TCGA-EP-A26S-11A TP53 9.346514 11.37829 9.529431 9.278449 9.544964 9.764872 9.949827 TCGA-EP-A3RK-11A TCGA-ES-A2HT-11A TCGA-FV-A23B-11A TCGA-FV-A2QR-11A TCGA-FV-A3I0-11A TCGA-FV-A3I1-11A TCGA-FV-A3R2-11A TP53 10.0348 10.89709 10.39553 10.47675 9.642052 10.02375 10.0348 TCGA-G3-A3CH-11A TP53 9.368506
input <- data.frame(normal = as.numeric(normal), tumor = as.numeric(tumor)) library(ggpubr) ggpaired(input, cond1 = "normal", cond2 = "tumor", fill = "condition", palette = "jco")
参考
http://rpkgs.datanovia.com/ggpubr/reference/ggpaired.html