使用python转换 smRNA-Seq的测序数据

 

001、 方法1

root@PC1:/home/test3# ls
a.txt  test.py
root@PC1:/home/test3# cat a.txt          ## 测试文件
ACTGCCCTAAGTGCTCCTTCTGGC 2
ATAAGGTGCATCTAGTGCAGATA 25
TGAGGTAGTAGTTTGTGCTGTTT 100
TCCTACGAGTTGCATGGATTC 4
root@PC1:/home/test3# cat test.py        ## 测试程序
#!/usr/bin/python

in_file = open("a.txt", "r")
dict1 = {}

line = 0
for i in in_file:
    line += 1
    i = i.strip()
    temp = i.strip().split()
    key = ">" + "ESB" + "_" + str(line) + "_" + "x" + temp[-1]
    dict1[key] = temp[0]

for i,j in dict1.items():
    print(i)
    print(j)

root@PC1:/home/test3# python test.py            ## 执行程序
>ESB_1_x2
ACTGCCCTAAGTGCTCCTTCTGGC
>ESB_2_x25
ATAAGGTGCATCTAGTGCAGATA
>ESB_3_x100
TGAGGTAGTAGTTTGTGCTGTTT
>ESB_4_x4
TCCTACGAGTTGCATGGATTC

 

002、方法2

root@PC1:/home/test3# ls
a.txt  test.py
root@PC1:/home/test3# cat a.txt               ## 测试数据
ACTGCCCTAAGTGCTCCTTCTGGC 2
ATAAGGTGCATCTAGTGCAGATA 25
TGAGGTAGTAGTTTGTGCTGTTT 100
TCCTACGAGTTGCATGGATTC 4
root@PC1:/home/test3# cat test.py             ## 测试程序
#!/usr/bin/python
in_file = open("a.txt", "r")
lines = in_file.readlines()
dict1 = {}

for i in lines:
    temp = i.strip().split()
    seq = temp[0]
    dict1[seq] = temp[1]
num = 1

for i,j in dict1.items():
    print(">" + "ESB" + "_" + str(num) + "_" + "x" + j)
    print(i)
root@PC1:/home/test3# python test.py            ## 运行程序
>ESB_1_x2
ACTGCCCTAAGTGCTCCTTCTGGC
>ESB_1_x25
ATAAGGTGCATCTAGTGCAGATA
>ESB_1_x100
TGAGGTAGTAGTTTGTGCTGTTT
>ESB_1_x4
TCCTACGAGTTGCATGGATTC

 

003、方法3

root@PC1:/home/test3# ls
a.txt  test.py
root@PC1:/home/test3# cat a.txt                 ## 测试数据
ACTGCCCTAAGTGCTCCTTCTGGC 2
ATAAGGTGCATCTAGTGCAGATA 25
TGAGGTAGTAGTTTGTGCTGTTT 100
TCCTACGAGTTGCATGGATTC 4
root@PC1:/home/test3# cat test.py               ## 测试程序
#!/usr/bin/python
in_file = open("a.txt", "r")
lines = in_file.readlines()

num = 0
for i in lines:
    num += 1
    seq,value = i.strip().split()
    print(">" + "ESB" + "_" + str(num) + "_" + "x" + value)
    print(seq)

in_file.close()
root@PC1:/home/test3# python test.py             ## 执行程序
>ESB_1_x2
ACTGCCCTAAGTGCTCCTTCTGGC
>ESB_2_x25
ATAAGGTGCATCTAGTGCAGATA
>ESB_3_x100
TGAGGTAGTAGTTTGTGCTGTTT
>ESB_4_x4
TCCTACGAGTTGCATGGATTC

 

参考：https://www.jianshu.com/p/2475c3240a67