cmp_list_ids.py

import pdb

all_ids = set()
def parse_ids(ifile: str):
    """Parse ids from list. Ids are in first column"""
    info_d = dict()
    with open(ifile) as ifile1:
        for line in ifile1:
            line = line.rstrip("\n");
            if line.startswith("#"): continue
            els = line.split('\t')
            all_ids.add(els[0])
            info_d[els[0]] = els[1]
    return info_d

info_d1 = parse_ids('file1.tsv')
info_d2 = parse_ids('file2.tsv')

for id in all_ids:
    newline = f"{id}\t"
    if id in info_d1:
        newline+=f"{info_d1[id]}\t"
    else:
        newline+="NA\t"
    if id in info_d2:
        newline+=f"{info_d2[id]}"
    else:
        newline+="NA"
    print(newline)