def get_pathways_with_multiple_proteoforms():
map_proteins_to_proteoforms = read_dictionary_one_to_set(
config.GRAPHS_PATH,
"mapping_proteins_to_proteoforms.tsv",
col_indices=(0, 1))
pathways = get_pathways()["stId"]
selected_proteins = []
for protein, proteoforms in map_proteins_to_proteoforms.items():
if len(proteoforms) > 1:
selected_proteins.append(protein)
selected_pathways = []
for pathway in pathways:
filename = get_json_filename(config.proteins, config.no_sm,
config.PATHWAY_GRAPHS_PATH, pathway)
if not Path(filename).exists():
create_pathway_interaction_network(pathway, config.proteins,
config.no_sm,
config.PATHWAY_GRAPHS_PATH)
G = read_graph(filename)
if any(protein in selected_proteins for protein in list(G.nodes)):
selected_pathways.append(pathway)
return selected_pathways
def test_read_dictionary_missing_two_columns(self):
"""With a one column file, request default columns 0 and 1, report error"""
# Create file with three columns, some not in lexicographic order
file_name = TestCase.id(self) + '_single_column.txt'
with open(file_name, 'w') as file:
for x in range(5):
file.write(f"{x}\n")
with self.assertRaises(
ValueError,
msg=
'Should raise an exception because needed columns of the file are missing.'
):
read_dictionary_one_to_set('', file_name, order_pairs=True)
os.remove(file_name)
def get_pathways_with_multiple_proteoforms(data_path, output_path):
"""
Get list of pathways which contain proteins with multiple proteoforms
"""
map_proteins_to_proteoforms = read_dictionary_one_to_set(
data_path, "mapping_proteins_to_proteoforms.tsv", col_indices=(0, 1))
# Create list of proteins that have multiple proteoforms
selected_proteins = []
for protein, proteoforms in map_proteins_to_proteoforms.items():
if len(proteoforms) > 1:
selected_proteins.append(protein)
pathways = get_pathways()["stId"] # Get complete list of pathways
selected_pathways = []
for pathway in pathways:
participants = get_participants_by_pathway(pathway, config.proteins,
output_path)
# filename = get_json_filename(
# config.proteins, config.no_sm, output_path, pathway)
# if not Path(filename).exists():
# create_pathway_interaction_network(
# pathway, config.proteins, config.no_sm, output_path)
# G = read_graph(filename)
if any(protein in selected_proteins
for protein in set(participants["Id"])):
selected_pathways.append(pathway)
return selected_pathways
def setUp(self):
self.letters = {chr(ord('A') + i): i for i in range(23)}
languages = [('C++', '.cpp'), ('Python', '.py'), ('JavaScript', '.js'),
('C++', '.hpp'), ('C++', '.cpp')]
with open('languages.txt', 'w') as file_languages:
for entry in languages:
file_languages.write(f"{entry[0]}\t{entry[1]}\n")
self.languages = read_dictionary_one_to_set('./', 'languages.txt')
def test_read_dictionary_missing_index_columns(self):
"""With two columns file, indices other than (0, 1), like (1, 2), show error."""
# Create file with three columns, some not in lexicographic order
pairs = [('a', 'b'), ('c', 'b'), ('d', 'e')]
file_name = TestCase.id(self) + '_pairs.txt'
with open(file_name, 'w') as file:
for x, y in pairs:
file.write(f"{x}\t{y}\n")
with self.assertRaises(
ValueError,
msg=
'Should raise an exception because needed columns of the file are missing.'
):
read_dictionary_one_to_set('', file_name, col_indices=(1, 2))
os.remove(file_name)
def test_read_dictionary_skip_header(self):
# Create trio file with headers
trios = [('Column1', 'Column2', 'Column3'), (1, 1, 2), (2, 3, 2),
(3, 4, 5)]
file_name = TestCase.id(self) + '_pairs.txt'
with open(file_name, 'w') as file:
for x, y, z in trios:
file.write(f"{x}\t{y}\t{z}\n")
# Execute target method
result = read_dictionary_one_to_set('',
file_name,
order_pairs=True,
col_indices=(1, 2),
ignore_header=True)
# Check headers are not taken as key, value pairs
self.assertNotIn('Column1',
result.keys(),
msg="Missing key in dictionary")
self.assertIn('1', result.keys(), msg="Missing key in dictionary")
self.assertIn('2', result.keys(), msg="Missing key in dictionary")
self.assertIn('4', result.keys(), msg="Missing key in dictionary")
# Remove precondition files
os.remove(file_name)
def test_merge_dictionaries(self):
d1 = {'A': {'B', 'C'}, 'D': {'C'}, 'C': {'d'}}
d2 = {'A': {'a', 'b', 'c'}, 'B': {'b'}, 'C': {'c', 'd', 'e'}}
d = merge_dictionaries(d1, d2)
self.assertEqual(
4,
len(d.keys()),
msg="There is a wrong number of keys in the dictionary")
self.assertEqual(5,
len(d['A']),
msg="The number of elements in 'A' should be 5")
self.assertTrue('a' in d['A'])
self.assertTrue('D' in d)
self.assertEqual(1,
len(d['D']),
msg="The number of elements in 'D' should be 1")
self.assertTrue('B' in d)
self.assertEqual(1,
len(d['B']),
msg="The number of elements in 'B' should be 1")
self.assertEqual(3,
len(d['C']),
msg="The number of elements in 'C' should be 3")
self.assertTrue('c' in d['C'])
def test_read_dictionary_order_pairs_true(self):
# Create file with pairs. Some with inverted lexicographic order
pairs = [('a', 'b'), ('c', 'b'), ('d', 'e')]
file_name = TestCase.id(self) + '_pairs.txt'
with open(file_name, 'w') as file:
for x, y in pairs:
file.write(f"{x}\t{y}\n")
# Execute target method
result = read_dictionary_one_to_set('', file_name, order_pairs=True)
# Check the pairs order was corrected, showing them as key and value when word1 < word2 Lexicographical order
self.assertIn(
'b',
result.keys(),
msg="Missing key because it did not order the column values")
self.assertEqual(3, len(result.keys()), msg="Wrong number of columns")
os.remove(file_name)
def test_read_dictionary_indices_1_2(self):
# Create file with three columns, some not in lexicographic order
trios = [(1, 1, 2), (2, 3, 2), (3, 4, 5)]
file_name = TestCase.id(self) + '_pairs.txt'
with open(file_name, 'w') as file:
for x, y, z in trios:
file.write(f"{x}\t{y}\t{z}\n")
# Execute target method
result = read_dictionary_one_to_set('',
file_name,
order_pairs=True,
col_indices=(1, 2))
# Check values are correct
self.assertIn('1', result.keys(), msg="Missing key in dictionary")
self.assertIn('2', result.keys(), msg="Missing key in dictionary")
self.assertNotIn('3', result.keys(), msg="Incorrect key in dictionary")
self.assertIn('4', result.keys(), msg="Missing key in dictionary")
# Remove file
os.remove(file_name)