---
title: "Data_acquisition"
author: "SL"
date: "2023/10/18"
output: html_document
---
```{r}
rm(list = ls())
gc()
getwd()
```

```{r}
library(data.table)
library(openxlsx)

library(tidyverse)

library(VennDiagram)
library(RColorBrewer)

library(clusterProfiler)
```

# 定义自噬相关基因
```{r}
HADB <- read.xlsx("Autophagy_genes/HADB.xlsx")
head(HADB)
HADB <- HADB %>% distinct(Symbol,.keep_all = T)

HAMDB <- fread("Autophagy_genes/HAMDB.csv")
names(HAMDB)
HAMDB <- HAMDB %>% filter(Species_Evidence=="Human") %>% 
  dplyr::select(Symbol) %>% 
  distinct(Symbol,.keep_all=T)
head(HAMDB)
```

取交叉
```{r}
Autophagy <- HAMDB %>% inner_join(HADB) 
Autophagy
fwrite(Autophagy,"Autophagy_genes/Autophagy.txt",quote = T,sep="\t")
```

韦恩图
```{r}
A <- HADB$Symbol
B <- HAMDB$Symbol

# 定义颜色
display.brewer.all(type='qual')
#从内置色板Set3中选出4个颜色使用。
brewer.pal(3,'Set1')
color <- c("#E41A1C","#377EB8")

venn.plot <- venn.diagram(
  list(HADB=A,
       HAMDB=B),
  filename= NULL, #韦恩图的名字
  imgaetype= "pdf",
  lty = 1,
  lwd = 3, #边框线宽度
  fontface="bold", #标签字体
  col = "black",  #圈的颜色
  fill = color,#对应每个圈的颜色，有几个数据集，就需要有相应数量的颜色
  alpha = 0.60,  #透明度
  cat.col = "black",#此处设置每个数据集的名称颜色，也可以使用c（）函数输入颜色
  cat.cex = 1, #每个区域label名称的大小
  cat.fontface = "bold",
  margin = 0.1,
  cex = 2.0,#标签字体大小
  label.col = "black",
  hyper.test=T
)

pdf(file="Autophagy_genes/Autophagy_genes.pdf")
grid.draw(venn.plot)
dev.off()
```


# 获取I期LUAD数据

TCGA
```{r}
# exp
TCGA_exp <- fread("/home/rstudio/Dataset/TCGA/LUAD/TCGA.LUAD.sampleMap_HiSeqV2.gz",
              data.table = F)
head(TCGA_exp)
rownames(TCGA_exp) <- TCGA_exp$sample
TCGA_exp <- TCGA_exp %>% dplyr::select(ends_with("01"))
colnames(TCGA_exp) <- str_sub(colnames(TCGA_exp),1,12)
head(TCGA_exp)

```
选取生存期完整的I期患者临床数据
```{r}
TCGA_clinical <- fread("/home/rstudio/Dataset/TCGA/LUAD/clinical.csv",data.table = F)
head(TCGA_clinical)

table(TCGA_clinical$Stage)
TCGA_clinical <- TCGA_clinical %>% filter(Stage=="I",PFI.time>0) 
fwrite(TCGA_clinical,"TCGA/TCGA_clinical.txt",quote = T,sep = "\t")
head(TCGA_clinical)
```

选取相应的表达矩阵
```{r}
TCGA_exp <- TCGA_exp[,TCGA_clinical$Patients_ID]
head(TCGA_exp)
TCGA_exp <- as.data.frame(t(TCGA_exp))
TCGA_exp <- data.frame(Patients_ID=rownames(TCGA_exp),TCGA_exp)
fwrite(TCGA_exp,"TCGA/TCGA_exp.txt",quote = T,sep = "\t")
```

GSE