CHIP-seq流程学习笔记（10）-使用intersect()函数提取ChIP-seq和RNA-seq中的共有基因

参考文章：R中常用函数使用说明

# 利用intersect函数对RNA_seq和ChIP_seq中的交集gene_symbol进行提取。
# 参考文章：https://blog.csdn.net/woodcorpse/article/details/80494605?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522160471856319195264746932%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=160471856319195264746932&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~baidu_landing_v2~default-1-80494605.pc_first_rank_v2_rank_v28&utm_term=R%E4%B8%ADintersect&spm=1018.2118.3001.4449
# 交集intersect：两个向量的交集，集合可以是数字、字符串等

# ChIP_seq中的差异peak在上面已经定义，分别是：
# Scr_vs_shTgm1_2_cond1即Scr中上调的peak，即敲除shTgm1_2后降低的peak
ChIP_seq_group_1_down_genes <- as.vector(Scr_vs_shTgm1_2_cond1_V2$SYMBOL)
# Scr_vs_shTgm1_2_cond2即敲除shTgm1_2后升高的peak
ChIP_seq_group_1_up_genes <- as.vector(Scr_vs_shTgm1_2_cond2_V2$SYMBOL)
# Scr_vs_shTgm2_1_cond1即Scr中上调的peak，即敲除shTgm2_1后降低的peak
ChIP_seq_group_2_down_genes <-as.vector(Scr_vs_shTgm2_1_cond1_V2$SYMBOL)
# Scr_vs_shTgm2_1_cond2即敲除shTgm2_1后升高的peak
ChIP_seq_group_2_up_genes <- as.vector(Scr_vs_shTgm2_1_cond2_V2$SYMBOL)

# RNA_seq中的差异gene需要再重新读入，分别是：
# 敲除shTgm1_2后降低的genes
RNA_seq_group_1_down_genes <- read.csv("G:/daizhongye/RNA-seq/2020_10_29/Rtreatment/significant_different_genes/significant_pvalue_different_genes_group_1_genecount_down.csv", header = TRUE,sep = ",")
# 敲除shTgm1_2后升高的genes
RNA_seq_group_1_up_genes <- read.csv("G:/daizhongye/RNA-seq/2020_10_29/Rtreatment/significant_different_genes/significant_pvalue_different_genes_group_1_genecount_up.csv", header = TRUE,sep = ",")
# 敲除shTgm2_1后降低的genes
RNA_seq_group_2_down_genes <- read.csv("G:/daizhongye/RNA-seq/2020_10_29/Rtreatment/significant_different_genes/significant_pvalue_different_genes_group_2_genecount_down.csv", header = TRUE,sep = ",")
# 敲除shTgm2_1后升高的genes
RNA_seq_group_2_up_genes <- read.csv("G:/daizhongye/RNA-seq/2020_10_29/Rtreatment/significant_different_genes/significant_pvalue_different_genes_group_2_genecount_up.csv", header = TRUE,sep = ",")
 
# 将RNA_seq中的差异genes对应的一列提取出来，并转化为向量形式
RNA_seq_group_1_down_genes_V1 <- as.vector(RNA_seq_group_1_down_genes$X)
RNA_seq_group_1_up_genes_V1 <- as.vector(RNA_seq_group_1_up_genes$X)
RNA_seq_group_2_down_genes_V1 <- as.vector(RNA_seq_group_2_down_genes$X)
RNA_seq_group_2_up_genes_V1 <- as.vector(RNA_seq_group_2_up_genes$X)

# 提取ChIP_seq和RNA_seq中共有的gene交集
group_1_down_genes <- intersect(ChIP_seq_group_1_down_genes,RNA_seq_group_1_down_genes_V1)
group_1_up_genes <- intersect(ChIP_seq_group_1_up_genes,RNA_seq_group_1_up_genes_V1)
group_2_down_genes <- intersect(ChIP_seq_group_2_down_genes,RNA_seq_group_2_down_genes_V1)
group_2_up_genes <- intersect(ChIP_seq_group_2_up_genes,RNA_seq_group_2_up_genes_V1)