def setUpClass(cls):
"""Set up testing data for testing."""
"""
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;')]
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_one = parse_genome_property(property_rows_one)
property_two = parse_genome_property(property_rows_two)
cls.tree = GenomePropertiesTree(property_one, property_two)
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)
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 setUpClass(cls):
"""
Test Properties
--> 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; TIGR03564; 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)
cls.properties = [property_one, property_two, property_three]
def test_child_genome_property_identifiers(self):
"""Test that we can get child genome property identifiers."""
new_property = parse_genome_property(self.property_rows[1])
child_genome_property_identifiers = new_property.child_genome_property_identifiers
self.assertEqual(
child_genome_property_identifiers,
['GenProp0066', 'GenProp0067', 'GenProp0068', 'GenProp0069'])
def test_required_steps(self):
"""Test that a genome property can return its required steps."""
new_property = parse_genome_property(self.property_rows[1])
required_steps = new_property.required_steps
self.assertEquals(len(required_steps), 1)
self.assertEquals(required_steps[0].name,
'Selfish genetic elements One')
def test_json_creation(self):
"""Test that json can be created properly."""
new_property = parse_genome_property(self.property_rows[0])
json_dict = new_property.to_json(as_dict=True)
self.assertEqual(json_dict['id'], 'GenProp0002')
self.assertEqual(json_dict['name'], 'Coenzyme F420 utilization')
self.assertEqual(json_dict['type'], 'GUILD')
self.assertEqual(
json_dict['description'],
'Coenzyme F420 (a 7,8-didemethyl-8-hydroxy 5-deazaflavin)')
self.assertEqual(json_dict['notes'], 'Yo_Dog_its_Yolo')
def test_parse_genome_property(self):
"""Test that we can parse genome property rows."""
new_property = parse_genome_property(self.property_rows[0])
self.assertEqual(new_property.id, 'GenProp0002')
self.assertEqual(new_property.name, 'Coenzyme F420 utilization')
self.assertEqual(new_property.type, 'GUILD')
self.assertEqual(new_property.threshold, 0)
self.assertEqual(new_property.parents, [])
self.assertEqual(
new_property.description,
'Coenzyme F420 (a 7,8-didemethyl-8-hydroxy 5-deazaflavin)')
self.assertEqual(new_property.private_notes, 'Yo_Dog_its_Yolo')
self.assertEqual(new_property.public, True)
self.assertEqual(len(new_property.databases), 1)
self.assertEqual(len(new_property.references), 1)
self.assertEqual(len(new_property.steps), 3)
def test_collapse_genome_property_record(self):
"""Test that we can clean up the overall genome property file."""
property_rows = [
('AC', 'GenProp0002'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'),
('AU', 'Haft DH'),
('TH', '0'),
('RN', '[1]'),
('RM', '11726492'),
('RT',
'Structures of F420H2:NADP+ oxidoreductase with and without its'),
('RT', 'janky structure!'),
('RT', 'I surprised that worked!'),
('RA',
'Warkentin E, Mamat B, Sordel-Klippert M, Wicke M, Thauer RK, Iwata M,'
),
('RL', 'EMBO J. 2001;20:6561-6569.'),
('DC', 'Methane Biosynthesis'),
('DR', 'IUBMB; misc; methane;'),
('CC', 'Coenzyme F420 (a 7,8-didemethyl-8-hydroxy 5-deazaflavin)'),
('CC', 'is a very important enzyme!'),
('**', 'Yo_Dog_its_Yolo'),
('**', 'a new film by the cool dudes!'),
('--', ''),
('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03564; sufficient;'),
('--', ''),
('SN', '2'),
('ID', 'Methylene-5,6,7,8-tetrahydromethanopterin dehydrogenase'),
('RQ', '0'),
('EV', 'IPR002844; PF01993; sufficient;'),
('--', ''),
('SN', '3'),
('ID', 'PPOX-class probable F420-dependent enzyme'),
('RQ', '0'),
('EV', 'IPR019920; TIGR03618; sufficient;'),
('--', ''),
('SN', '10'),
('ID', 'F420-dependent oxidoreductase families'),
('RQ', '1'),
('EV', 'IPR019944; TIGR03554; sufficient;'),
('EV', 'IPR019946; TIGR03555; sufficient;'),
('EV', 'IPR019945; TIGR03557; sufficient;'),
('EV', 'IPR019951; TIGR03559; sufficient;'),
('EV', 'IPR019952; TIGR03560; sufficient;'),
('EV', 'IPR031017; TIGR04465; sufficient;'),
]
clean_genome_property_record = unwrap_genome_property_record(
property_rows)
first_genome_property = parse_genome_property(
clean_genome_property_record)
first_reference = first_genome_property.references[0]
self.assertEqual(
first_genome_property.description,
'Coenzyme F420 (a 7,8-didemethyl-8-hydroxy 5-deazaflavin) '
'is a very important enzyme!')
self.assertEqual(first_genome_property.private_notes,
'Yo_Dog_its_Yolo a new film by the cool dudes!')
self.assertEqual(
first_reference.title,
'Structures of F420H2:NADP+ oxidoreductase with and without its janky '
'structure! I surprised that worked!')
final_step = first_genome_property.steps[-1]
functional_elements = final_step.functional_elements
self.assertEqual(len(functional_elements), 1)
self.assertEqual(len(functional_elements[0].evidence), 6)
self.assertEqual(final_step.required, True)
self.assertEqual(final_step.functional_elements[0].name,
'F420-dependent oxidoreductase families')
def setUpClass(cls):
"""
Test Properties Rooted DAG Structure:
GenProp0002 --> --> GenProp0089
GenProp0066
GenProp0003 --> --> GenProp0092
Note 1: The structure of the property tree used above is not the common case.
Commonly there should be only a single root node.
"""
property_rows_one = [('AC', 'GenProp0002'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'Selfish genetic elements'), ('RQ', '0'),
('EV', 'GenProp0066;')]
property_rows_two = [('AC', 'GenProp0003'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'Selfish genetic elements'), ('RQ', '0'),
('EV', 'GenProp0066;')]
property_rows_three = [
('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_four = [('AC', 'GenProp0089'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03564; sufficient;')]
property_rows_five = [('AC', 'GenProp0092'),
('DE', 'Coenzyme F420 utilization'),
('TP', 'GUILD'), ('--', ''), ('SN', '1'),
('ID', 'LLM-family F420-associated subfamilies'),
('RQ', '0'),
('EV', 'IPR019910; TIGR03564; 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)
property_four = parse_genome_property(property_rows_four)
property_five = parse_genome_property(property_rows_five)
cls.raw_properties = [
property_one, property_two, property_three, property_four,
property_five
]
