TCGA学习笔记8-临床信息提取

上面，我们对KIRC的表达数据做了差异分析，并对有差异的基因做了主成份分析和聚类热图，在进行下一步分析之前，我们需要对临床数据进行提取。我们先回顾一下，在学习笔记1中，我们在TCGA上下载到的表达数据包含来自530个CASES的611个FILES，即数据来自530个病人，但由于从某些病人身上收集了不止一个样本，因此，样本数大于病例数。

> library(rjson)
> clinical_trials <- fromJSON(file="clinical.cart.2020-06-25.json") # 类型是列表
> n= length(clinical_trials)
> n
[1] 530 # 530个CASES，与预期一致
>id=classification_of_tumor=tumor_stage=gender=year_of_birth=year_of_death=year_of_diagnosis=days_to_death=age=deadORlive=race=alcohol=years_smoked=c(rep(0,n))
(rep(0,n)) # 定义变量
> age
  [1] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 [33] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 [65] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 [97] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[129] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[161] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[193] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[225] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[257] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[289] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[321] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[353] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[385] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[417] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[449] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[481] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
[513] 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
> for(i in 1:n){
+   id[i]=clinical_trials[[i]]$diagnoses[[1]]$submitter_id
+   classification_of_tumor[i]=clinical_trials[[i]]$diagnoses[[1]]$classification_of_tumor
+   tumor_stage[i]=clinical_trials[[i]]$diagnoses[[1]]$tumor_stage
+   gender[i]=clinical_trials[[i]]$demographic$gender
+   year_of_birth[i]=ifelse(is.null(clinical_trials[[i]]$demographic$year_of_birth),"not reported",clinical_trials[[i]]$demographic$year_of_birth)
+   year_of_death[i]=ifelse(is.null(clinical_trials[[i]]$demographic$year_of_death),"not reported",clinical_trials[[i]]$demographic$year_of_death) # 此处使用ifelse()，因为不一定有这个数据，比如有些CASE这里显示“Pairlist of length 0"，以下同
+   year_of_diagnosis[i]=ifelse(is.null(clinical_trials[[i]]$diagnoses[[1]]$year_of_diagnosis),"not reported",clinical_trials[[i]]$diagnoses[[1]]$year_of_diagnosis)
+   days_to_death[i]=ifelse(is.null(clinical_trials[[i]]$demographic$days_to_death),"not reported",clinical_trials[[i]]$demographic$days_to_death)
+   age[i]=ifelse(is.null(clinical_trials[[i]]$demographic$age_at_index),"not reported",clinical_trials[[i]]$demographic$age_at_index)
+   deadORlive[i]=ifelse(is.null(clinical_trials[[i]]$demographic$vital_status),"not reported",clinical_trials[[i]]$demographic$vital_status)
+   race[i]=ifelse(is.null(clinical_trials[[i]]$demographic$race),"not reported",clinical_trials[[i]]$demographic$race)
+   alcohol[i]=ifelse(is.null(clinical_trials[[i]]$exposures[[1]]$alcohol_history),"not reported",clinical_trials[[i]]$exposures[[1]]$alcohol_history)
+   years_smoked[i]=ifelse(is.null(clinical_trials[[i]]$exposures[[1]]$years_smoked),"not reported",clinical_trials[[i]]$exposures[[1]]$years_smoked)
+ }  
> kidney_clinic <- data.frame(
+   id,
+   classification_of_tumor,
+   tumor_stage,
+   gender,
+   year_of_birth,
+   year_of_death,
+   year_of_diagnosis,
+   days_to_death,
+   age,
+   deadORlive,
+   race,
+   alcohol,
+   years_smoked
+ )
> dim(kidney_clinic)
[1] 530  13
> head(kidney_clinic)
                      id classification_of_tumor tumor_stage gender
1 TCGA-CZ-5986_diagnosis            not reported     stage i   male
2 TCGA-CZ-4858_diagnosis            not reported    stage ii   male
3 TCGA-B8-5551_diagnosis            not reported     stage i female
4 TCGA-B0-4817_diagnosis            not reported   stage iii   male
5 TCGA-BP-4325_diagnosis            not reported     stage i female
6 TCGA-B0-4698_diagnosis            not reported    stage iv   male
  year_of_birth year_of_death year_of_diagnosis days_to_death age
1          1945  not reported              2006  not reported  61
2          1966  not reported              2005          2105  39
3          1945  not reported              2010  not reported  65
4          1921          2004              2002          1019  81
5          1937  not reported              2001  not reported  64
6          1928          2003              2003            42  75
  deadORlive                      race      alcohol years_smoked
1      Alive                     white Not Reported not reported
2       Dead                     white Not Reported not reported
3      Alive black or african american Not Reported not reported
4       Dead                     white Not Reported not reported
5      Alive                     white Not Reported not reported
6       Dead                     white Not Reported not reported

至此，临床分类信息就提取完成了，在后面的分析中，我们需要用到这个数据，比如绘制生存曲线。