shell 和 R 实现具有映射关系的数据的批量替换

 

1、测试数据

root@PC1:/home/test# ls
5gene_CDs.bed  id_mapping.txt
root@PC1:/home/test# head -n 3 5gene_CDs.bed
chr6    117609654       117609965       NM_001378891.1_cds_0_0_chr6_117609655_r 0       -
chr6    117622136       117622300       NM_001378891.1_cds_1_0_chr6_117622137_r 0       -
chr6    117629956       117630091       NM_001378891.1_cds_2_0_chr6_117629957_r 0       -
root@PC1:/home/test# head -n 3 id_mapping.txt   ## 在5gene_CDs.bed文件中实现id_mapping.txt中第二列对第一列的批量替换
NM_001378891.1  ROS1
NM_001378902.1  ROS1
NM_002944.3     ROS1

 

2、shell实现

root@PC1:/home/test# ls
5gene_CDs.bed  id_mapping.txt
root@PC1:/home/test# head -n 3 5gene_CDs.bed
chr6    117609654       117609965       NM_001378891.1_cds_0_0_chr6_117609655_r 0       -
chr6    117622136       117622300       NM_001378891.1_cds_1_0_chr6_117622137_r 0       -
chr6    117629956       117630091       NM_001378891.1_cds_2_0_chr6_117629957_r 0       -
root@PC1:/home/test# head -n 3 id_mapping.txt
NM_001378891.1  ROS1
NM_001378902.1  ROS1
NM_002944.3     ROS1
root@PC1:/home/test# cp 5gene_CDs.bed 5gene_CDs.bed.bak  ## 要在源文件中修改，防止以外发生对数据做备份
root@PC1:/home/test# ls
5gene_CDs.bed  5gene_CDs.bed.bak  id_mapping.txt
root@PC1:/home/test# cat id_mapping.txt | while read {i,j}; do sed -i "s/$i/$j/" 5gene_CDs.bed; done   ## 循环中i和j分别存储每行中对应的两个变量
root@PC1:/home/test# head -n 3 5gene_CDs.bed
chr6    117609654       117609965       ROS1_cds_0_0_chr6_117609655_r   0       -
chr6    117622136       117622300       ROS1_cds_1_0_chr6_117622137_r   0       -
chr6    117629956       117630091       ROS1_cds_2_0_chr6_117629957_r   0       -

 

3、R实现

> dir()
[1] "5gene_CDs.bed"  "id_mapping.txt"
> mapping=read.table("id_mapping.txt",sep="\t")
> head(mapping,2)
              V1   V2
1 NM_001378891.1 ROS1
2 NM_001378902.1 ROS1
> bed=read.table("5gene_CDs.bed",sep="\t")
> head(bed, 2)
    V1        V2        V3                                      V4 V5 V6
1 chr6 117609654 117609965 NM_001378891.1_cds_0_0_chr6_117609655_r  0  -
2 chr6 117622136 117622300 NM_001378891.1_cds_1_0_chr6_117622137_r  0  -
> for (i in 1:nrow(mapping)) {
+   bed$V4 <- sub(mapping$V1[i], mapping$V2[i], bed$V4)
+ }
> head(bed,2)
    V1        V2        V3                            V4 V5 V6
1 chr6 117609654 117609965 ROS1_cds_0_0_chr6_117609655_r  0  -
2 chr6 117622136 117622300 ROS1_cds_1_0_chr6_117622137_r  0  -

 

测试数据来源： https://mp.weixin.qq.com/s?__biz=MzI4ODE0NTE3OA==&mid=2649219537&idx=1&sn=6974c6e3b91b6e91ac407563f10d3835&chksm=f3d1aba4c4a622b243e58434d561e2a08db148fb98499eaec626f6e186ec5cfa912c6db5ab93&mpshare=1&scene=23&srcid=1118L4C0wtH1cYHmjtZD2lrk&sharer_sharetime=1637166249484&sharer_shareid=4ed060cc4cd1efce40e3ab6dd8d8c7d4#rd