# total number of proteins read from file
protein_count = 0
# counters for TF and nucleus proteins
tf_nucleus_count = 0
not_tf_nucleus_count = 0
tf_not_nucleus_count = 0
not_tf_not_nucleus_count = 0
for line in yeast_file:
protein_count += 1
fields = line.strip().split("\t")
protein_id = fields[0]
protein_identifiers.append(protein_id)
go_terms = getGOTerms(fields[0])
go_terms_dict[protein_id] = go_terms
if "GO:0005634" in go_terms: # check if nucleus
if "GO:0003700" in go_terms: # check if TF
tf_nucleus_count += 1
else:
not_tf_nucleus_count += 1
else:
if "GO:0003700" in go_terms: # check if TF
tf_not_nucleus_count += 1
else:
not_tf_not_nucleus_count += 1
file.close()
print "Exercise 4.1 - protein identifiers: ", protein_identifiers
print "Exercise 4.2 - GO Terms"
# counters for TF and nucleus proteins
tf_nucleus_count = 0
not_tf_nucleus_count = 0
tf_not_nucleus_count = 0
not_tf_not_nucleus_count = 0
for line in yeast_file:
protein_count += 1
fields = line.strip().split("\t")
protein_id = fields[0]
protein_identifiers.append(protein_id) # ex 5.1
yeast_file.close()
# dictionary of go_terms with the gene ID as the key
go_terms_dict = getGOTerms(protein_identifiers)
for protein_id in go_terms_dict:
go_terms = go_terms_dict.get(protein_id)
if "GO:0005634" in go_terms: # check if nucleus
if "GO:0003700" in go_terms: # check if TF
tf_nucleus_count += 1
else:
not_tf_nucleus_count += 1
else:
if "GO:0003700" in go_terms: # check if TF
tf_not_nucleus_count += 1
else:
not_tf_not_nucleus_count += 1