def test_assign_step_multiple_functional_elements_all_none_present(self):
"""Test assignment of multiple elements when all are not present."""
test_cache = AssignmentCache()
parent_genome_property = GenomeProperty(accession_id='GenProp0065',
name='YOLO',
property_type="TEMP")
step = [
('--', ''),
('SN', '1'),
('ID', 'Aferr subtype specific proteins'),
('EV', 'IPR017545; TIGR03114;'), # NO
('TG', 'GO:0043571;'),
('ID', 'Yolo subtype specific proteins'),
('EV', 'IPR017545; TIGR03115;'), # NO
('TG', 'GO:0043571;')
]
parsed_step = parse_steps(step)[0]
parsed_step.parent = parent_genome_property
step_assignment = assign_step(test_cache, parsed_step)
self.assertEqual(step_assignment, 'NO')
self.assertEqual(test_cache.get_step_assignment('GenProp0065', 1),
'NO')
def test_assignment_cache_synchronization(self):
"""Test that the assignment file can be properly synchronized."""
test_cache = AssignmentCache()
test_tree = self.test_tree
test_cache.cache_property_assignment('GenProp0456', 'YES')
test_cache.cache_property_assignment('GenProp0710', 'YES')
sanitized_cache = create_synchronized_assignment_cache(test_cache, test_tree)
self.assertEqual(len(sanitized_cache.property_assignments), 1)
self.assertEqual(sanitized_cache.get_property_assignment('GenProp0710'), 'YES')
def test_genome_property_assignment_two_required_all_present(self):
"""Test assignment of genome properties when two markers are required and all are present."""
test_cache = AssignmentCache(interpro_member_database_identifiers=[
'TIGR03564', 'TIGR03567', 'TIGR03568'
])
property_rows = [
('AC', 'GenProp0089'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'),
('--', ''),
('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '1'),
('EV', 'IPR019910; TIGR03564; sufficient;'), # YES
('--', ''),
('SN', '2'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '1'),
('EV', 'IPR019910; TIGR03567; sufficient;'), # YES
('--', ''),
('SN', '3'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03568; sufficient;') # YES
]
test_property = parse_genome_property(property_rows)
test_property.threshold = 0
assignment = assign_genome_property(test_cache, test_property)
self.assertEqual(assignment, 'YES')
def test_genome_property_assignment_two_required_three_absent(self):
"""Test assignment of genome properties when two markers are required and none are present."""
test_cache = AssignmentCache()
property_rows = [
('AC', 'GenProp0089'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'),
('--', ''),
('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '1'),
('EV', 'IPR019910; TIGR03564; sufficient;'), # NO
('--', ''),
('SN', '2'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '1'),
('EV', 'IPR019910; TIGR03567; sufficient;'), # NO
('--', ''),
('SN', '3'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03568; sufficient;') # NO
]
test_property = parse_genome_property(property_rows)
test_property.threshold = 0
assignment = assign_genome_property(test_cache, test_property)
self.assertEqual(assignment, 'NO')
def test_assign_functional_element_all_identifiers(self):
"""Test assignment of a functional element when all evidence markers are present."""
test_cache = AssignmentCache(interpro_member_database_identifiers=[
'TIGR03114', 'TIGR03117', 'TIGR03120'
])
functional_element = [
('--', ''),
('SN', '1'),
('ID', 'Aferr subtype specific proteins'),
('RQ', '0'),
('EV', 'IPR017545; TIGR03114; sufficient;'), # Yes
('EV', 'IPR017547; TIGR03117;'), # Yes
('TG', 'GO:0043571;'),
('EV', 'IPR017552; TIGR03120;'), # Yes
('TG', 'GO:0043573;')
]
parsed_functional_element = parse_functional_elements(
functional_element)[0]
assignment = assign_functional_element(test_cache,
parsed_functional_element)
self.assertEqual(assignment, 'YES')
def test_assign_functional_element_none_sufficient_all_not_present(self):
"""Test assignment of a functional element when no sufficient identifiers and none present."""
test_cache = AssignmentCache(interpro_member_database_identifiers=[
'TIGR03115', 'TIGR03118', 'TIGR03121'
])
functional_element = [
('--', ''),
('SN', '1'),
('ID', 'Aferr subtype specific proteins'),
('RQ', '0'),
('EV', 'IPR017545; TIGR03114;'), # NO
('EV', 'IPR017547; TIGR03117;'), # NO
('TG', 'GO:0043571;'),
('EV', 'IPR017552; TIGR03120;'), # NO
('TG', 'GO:0043573;')
]
parsed_functional_element = parse_functional_elements(
functional_element)[0]
assignment = assign_functional_element(test_cache,
parsed_functional_element)
self.assertEqual(assignment, 'NO')
def test_genome_property_assignment_non_required_none_present(self):
"""Test assignment of genome properties when no markers are present and none are required."""
test_cache = AssignmentCache()
test_property = self.tree.root
assignment = assign_genome_property(test_cache, test_property)
self.assertEqual(assignment, 'NO')
def test_genome_property_assignment_non_required_one_present(self):
"""Test assignment of a genome property when one marker is present but none are required."""
test_cache = AssignmentCache(
interpro_member_database_identifiers=['TIGR03565'])
test_property = self.tree.root
assignment = assign_genome_property(test_cache, test_property)
self.assertEqual(assignment, 'PARTIAL')
def parse_genome_property_longform_file(longform_file):
"""
Parses longform genome properties assignment files.
:param longform_file: A longform genome properties assignment file handle object.
:return: An assignment cache object.
"""
property_id = ''
step_number = ''
assignment_cache = AssignmentCache(sample_name=splitext(basename(longform_file.name))[0])
for line in longform_file:
if 'PROPERTY:' in line:
property_id = line.split(':')[1].strip()
elif 'STEP NUMBER:' in line:
step_number = int(line.split(':')[1].strip())
elif 'RESULT:' in line:
assignment = line.split(':')[1].strip().upper()
if 'STEP' in line:
assignment_cache.cache_step_assignment(property_id, step_number, assignment)
else:
assignment_cache.cache_property_assignment(property_id, assignment)
else:
continue
return assignment_cache
def parse_interproscan_file(interproscan_file):
"""
Parses InterProScan TSV files into an assignment cache.
:param interproscan_file: A InterProScan file handle object.
:return: An assignment cache object.
"""
identifiers = []
tsv_reader = csv.reader(interproscan_file, delimiter='\t')
for row in tsv_reader:
matched_interpro_member_database_id = row[4]
identifiers.append(matched_interpro_member_database_id)
return AssignmentCache(interpro_member_database_identifiers=identifiers,
sample_name=splitext(basename(interproscan_file.name))[0])
def test_get_identifiers(self):
"""Test that we can get the correct assignment identifiers from the cache."""
test_cache = AssignmentCache()
test_cache.cache_property_assignment('GenProp0067', 'YES')
test_cache.cache_property_assignment('GenProp0092', 'NO')
identifiers = test_cache.genome_property_identifiers
identifiers.sort()
self.assertEqual(identifiers, ['GenProp0067', 'GenProp0092'])
def test_assign_evidence_from_no_interpro_identifiers(self):
"""Test we can assign evidence when no InterPro identifiers are in the assignment cache."""
test_cache = AssignmentCache()
evidence = [('--', ''), ('SN', '1'),
('ID', 'Aferr subtype specific proteins'),
('DN', 'Crispy Proteins'), ('RQ', '0'),
('EV', 'IPR017545; TIGR03114; sufficient;'),
('TG', 'GO:0043571;')]
evidence = parse_evidences(evidence)[0]
assignment = assign_evidence(test_cache, evidence)
self.assertEqual(assignment, 'NO')
def test_assign_evidence_when_missing_interpro_identifiers(self):
"""Test assign evidence based on InterPro identifiers that are missing from the assignment cache."""
test_cache = AssignmentCache(interpro_member_database_identifiers=[
'TIGR03192', 'TIGR03193', 'TIGR03194'
])
evidence = [('--', ''), ('SN', '1'),
('ID', 'Aferr subtype specific proteins'),
('DN', 'Crispy Proteins'), ('RQ', '0'),
('EV', 'IPR017545; TIGR03114; sufficient;'),
('TG', 'GO:0043571;')]
evidence = parse_evidences(evidence)[0]
assignment = assign_evidence(test_cache, evidence)
self.assertEqual(assignment, 'NO')
def test_cache_flush(self):
"""Test that the cache can be properly flushed."""
test_cache = AssignmentCache()
test_cache.cache_property_assignment('GenProp0067', 'YES')
test_cache.cache_property_assignment('GenProp0092', 'NO')
test_cache.cache_step_assignment('GenProp0067', 1, 'YES')
test_cache.cache_step_assignment('GenProp0092', 1, 'NO')
test_cache.flush_property_from_cache('GenProp0067')
self.assertEqual(test_cache.get_property_assignment("GenProp0067"),
None)
self.assertEqual(test_cache.get_step_assignment("GenProp0067", 1),
None)
self.assertEqual(len(test_cache.property_assignments), 1)
self.assertEqual(len(test_cache.step_assignments), 1)
def setUpClass(cls):
"""Set up testing data for testing."""
prebuilt_cache = AssignmentCache()
prebuilt_cache.cache_property_assignment('GenProp0053', 'YES')
prebuilt_cache.cache_property_assignment('GenProp0052', 'NO')
prebuilt_cache.cache_property_assignment('GenProp0051', 'PARTIAL')
prebuilt_cache.cache_step_assignment('GenProp0053', 1, 'YES')
prebuilt_cache.cache_step_assignment('GenProp0053', 2, 'NO')
prebuilt_cache.cache_step_assignment('GenProp0053', 3, 'YES')
cls.cache = prebuilt_cache
"""
Test Properties Rooted DAG Structure:
--> GenProp0089
GenProp0066
--> GenProp0092
"""
property_rows_one = [('AC', 'GenProp0066'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'Selfish genetic elements'), ('RQ', '0'),
('EV', 'GenProp0089;'), ('--', ''), ('SN', '2'),
('ID', 'Selfish genetic elements'), ('RQ', '0'),
('EV', 'GenProp0092;')]
property_rows_two = [('AC', 'GenProp0089'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03564; sufficient;')]
property_rows_three = [('AC', 'GenProp0092'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID',
'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03565; sufficient;')]
property_one = parse_genome_property(property_rows_one)
property_two = parse_genome_property(property_rows_two)
property_three = parse_genome_property(property_rows_three)
raw_properties = [property_one, property_two, property_three]
cls.tree = GenomePropertiesTree(*raw_properties)
