拼接两个文件中名字相同的序列

目的：有两个序列文件，我们要把名字相同的序列首尾拼接起来

# ly-2021-08-29  version-01
# Usage: python infile1 infile2 > outfile
# 每条序列必须处于同一行

a = []
b = []
with open("1.txt", "r+") as file1:
    for line1 in file1.readlines():
        line1 = line.strip()
        a.append(line1)
with open("2.txt", "r+") as file2:
    for line2 in file2.readlines():
        line2 = line2.strip()
        b.append(line2)
for k in a:
    for v in b:
        if k==v: #要求序列名完全相同
            print(k)
            print(b[b.index(k)]+1)] + a[a.index(v)+1])

# ly-2021-08-30  version-02
# Reviewed: 不要求序列只能处在一行

# Usage: py infile1 infile2 > outfile

#!/usr/bin/python
import sys

a=[]
b=[]
flag=0
with open(sys.argv[1], "r+") as file1:
    for line in file1.readlines():
        if flag==0:
            a.append(line)
            flag+=1
        else:
            if ">" not in line:
                line=line.strip()
                b.append(line)
                item1="".join(b)
            else:
                item1=""
                item="".join(b)
                a.append(item)
                b=[]
                a.append(line)
a.append(item1)
#print(a)


c=[]
d=[]
flag=0
with open(sys.argv[2], "r+") as file2:
    for line in file2.readlines():
        if flag==0:
            c.append(line)
            flag+=1
        else:
            if ">" not in line:
                line=line.strip()
                d.append(line)
                item1="".join(d) #用于处理最后一个序列
            else:
                item1=""
                item="".join(d) #将前一个if里的列表d里的元素拼接起来。如果没有item1，可以发现最后一条序列是处理不到的
                c.append(item)
                d=[] #清空，用于下一次if循环
                c.append(line)
c.append(item1)
#print(c)

for k in a:
    for v in c:
        if k==v: #要求序列名完全相同
            print(k, end="")
            print(a[a.index(k)+1]+c[c.index(v)+1])

# ly-2021-08-30  version-03
# Reversed: function
# Usage: py infile1 infile2 > outfile

#!/usr/bin/python
import sys
def INFILE(x):
    a=[]
    b=[]
    flag=0
    with open(x, "r+") as file1:
        for line in file1.readlines():
            if flag==0:
                a.append(line)
                flag+=1
            else:
                if ">" not in line:
                    line=line.strip()
                    b.append(line)
                    item1="".join(b)  #用于处理最后一个序列
                else:
                    item1=""
                    item="".join(b)  #将前一个if里的列表d里的元素拼接起来。如果没有item1，可以发现最后一条序列是处理不到的
                    a.append(item)
                    b=[]  #清空，用于下一次if循环
                    a.append(line)
    a.append(item1)
    #print(a)
    return a
c=INFILE(x=sys.argv[1])
d=INFILE(x=sys.argv[2])

for k in c:
    for v in d:
        if k==v: #要求序列名完全相同
            print(k, end="")
            print(c[c.index(k)+1]+d[d.index(v)+1]) 

标签：item1,flag,print,名字,拼接,序列,line,append
来源： https://www.cnblogs.com/ly-zy/p/15203769.html