find_proteins.py

import gzip


def proteome_to_dict(proteome_lines):
    proteome_lines.append('nnIDnnn')
    protein = ''
    name = ''
    proteome = {}
    for line in proteome_lines:
        r = str(line)[2: -3] + '\n'
        if r.startswith("ID"):
            if protein != '':
                proteome[name] = protein
                protein = ''
            if r != 'ID\n':
                name = r.split()[1]
        protein += r
    return proteome


def proteins_in_both(proteome1, proteome2):
    name = ''
    for protein in proteome2.keys():
        name = protein.split('_')[1]
        break

    for protein in proteome1.keys():
        try:
            if proteome2[f'{protein.split("_")[0]}_{name}']:
                print(protein)
        except KeyError:
            continue
    return


with gzip.open('ecoli_reviewed_proteome.gz') as file:
    ecoli = file.readlines()
ecoli_proteome = proteome_to_dict(ecoli)

with gzip.open('bacsu_reviewed_proteome.gz') as file:
    bacsu = file.readlines()
bacsu_proteome = proteome_to_dict(bacsu)

proteins_in_both(ecoli_proteome, bacsu_proteome)