Combine two gene files

col.py

#!/usr/bin/env python

# first open the two files and read their lines into lists
f1 = open('file1.txt', 'r')
f2 = open('file2.txt', 'r')
lines1 = f1.readlines()
lines2 = f2.readlines()
f1.close()
f2.close()

# now create a dictionary (keyword mapping) to map the gene name to the
# count column for the second file. This allows you to type mapping['aaaD'] and
# you will get the count value back
mapping = {}
for line in lines2:
    a = line.strip().split('\t')
    mapping[a[1]] = a[3]

# Now walk through the lines from the first file and append the count column
# from the second file which you have stored in the mapping dictionary.
newlines = ''
for line in lines1:
    gene = line.strip().split('\t')[1]
    # the try/except statement handles if the gene isn't in the second file but
    # is in the first. It just puts a zero for the count if it isn't.
    try:
       newlines += line.strip() + '\t' + mapping[gene] + '\n'
    except KeyError:
       newlines += line.strip() + '\t' + '0' + '\n'

# Finally save a new file with the new columns written
f3 = open('file3.txt', 'w')
f3.writelines(newlines)
f3.close()

# the short version :)

with open('file2.txt') as f:
    mapping = {x.strip().split('\t')[1]: x.strip().split('\t')[3] for x in
            f.readlines()}

with open('file1.txt') as f:
    newlines = ''
    for line in f.readlines():
        newlines += line.strip() + '\t' + mapping[line.strip().split('\t')[1]] + '\n'

with open('file3.txt', 'w') as f:
    f.writelines(newlines)

file1.txt

1	gene	descriptor	count
2	aaaD	testing1	2
3	aaaA	testing2	2

file2.txt

1	gene	descriptor	count
2	aaaD	testing1	3
3	aaaA	testing2	4