parse_multi_gene_list.py

gene_list = []
with open('/home/ryan/multi_coding_subset.txt', 'r') as assoc:
  for line in assoc:
    intron,gene_vec = line.split('\t')
    gene_vec = gene_vec.replace('c','').replace('\"','').replace('(','').replace(')','').replace(' ','').replace('\n','')
    newvec = gene_vec.split(',')
    for i in newvec:
      if i not in gene_list:
        gene_list.append(str(i))

out = '/home/ryan/multi_coding_subset_genes.txt'
with open(out, 'w') as output:
  for i in gene_list:

    output.write((i + '\n').encode('utf-8'))