def _onp_ordered_combiner_test(self, inputs, expected):
input_muts = iter(self._tuples_to_MutationData(inputs))
expected_muts = self._tuples_to_MutationData(expected)
mut_factory = MutationDataFactory()
combiner = OnpQueue(input_muts, mut_factory)
results = list(combiner.get_combined_mutations())
self._assert_mutation_lists_equal(expected_muts, results)
def _onp_ordered_combiner_test(self,inputs, expected):
input_muts = iter(self._tuples_to_MutationData(inputs))
expected_muts = self._tuples_to_MutationData(expected)
mut_factory = MutationDataFactory()
combiner = OnpQueue(input_muts, mut_factory)
results = list(combiner.get_combined_mutations())
self._assert_mutation_lists_equal(expected_muts, results)
def test_tnp_blank_snp(self):
"""Test a harder scenario for ONP combination"""
mut1 = MutationData(chr=1,start=100, end=100, ref_allele="G", alt_allele="A")
mut1.createAnnotation("phasing_id", "value1", "INPUT")
mut1.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut2 = MutationData(chr=1,start=101, end=101, ref_allele="C", alt_allele="T")
mut2.createAnnotation("phasing_id", "value1", "INPUT")
mut2.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut3 = MutationData(chr=1,start=102, end=102, ref_allele="C", alt_allele="T")
mut3.createAnnotation("phasing_id", "value1", "INPUT")
mut3.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Note the differing ID in mut4
mut4 = MutationData(chr=1,start=103, end=103, ref_allele="C", alt_allele="T")
mut4.createAnnotation("phasing_id", "value2", "INPUT")
mut4.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut5 = MutationData(chr=1,start=104, end=104, ref_allele="C", alt_allele="T")
mut5.createAnnotation("phasing_id", "value1", "INPUT")
mut5.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Note separate chromosome for mut6
mut6 = MutationData(chr=2,start=105, end=105, ref_allele="C", alt_allele="T")
mut6.createAnnotation("phasing_id", "value1", "INPUT")
mut6.createAnnotation("phasing_genotype", "0|1", "INPUT")
gt_alts = ["ATT", "T", "T", "T"]
mutations = [mut1, mut2, mut3, mut4, mut5, mut6]
mdf = MutationDataFactory()
queue = OnpQueue(mutations, mdf)
for i, mut in enumerate(queue.get_combined_mutations()):
self.assertTrue(gt_alts[i] == mut.alt_allele)
def test_indel(self):
"""Test indel not used in onp combination no matter what the phasing info"""
mut1 = MutationData(chr=1,start=100, end=100, ref_allele="G", alt_allele="A")
mut1.createAnnotation("phasing_id", "value1", "INPUT")
mut1.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut2 = MutationData(chr=1,start=101, end=101, ref_allele="C", alt_allele="T")
mut2.createAnnotation("phasing_id", "value1", "INPUT")
mut2.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut3 = MutationData(chr=1,start=102, end=102, ref_allele="C", alt_allele="T")
mut3.createAnnotation("phasing_id", "value1", "INPUT")
mut3.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Indel
mut4 = MutationData(chr=1,start=103, end=104, ref_allele="-", alt_allele="TT")
mut4.createAnnotation("phasing_id", "value1", "INPUT")
mut4.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut5 = MutationData(chr=1, start=104, end=104, ref_allele="C", alt_allele="T")
mut5.createAnnotation("phasing_id", "value1", "INPUT")
mut5.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut6 = MutationData(chr=1, start=105, end=105, ref_allele="C", alt_allele="T")
mut6.createAnnotation("phasing_id", "value1", "INPUT")
mut6.createAnnotation("phasing_genotype", "0|1", "INPUT")
gt_alts = ["ATT", "TT", "TT"]
mutations = [mut1, mut2, mut3, mut4, mut5, mut6]
mdf = MutationDataFactory()
queue = OnpQueue(mutations, mdf)
for i, mut in enumerate(queue.get_combined_mutations()):
self.assertTrue(gt_alts[i] == mut.alt_allele)
def test_tnp_blank_snp(self):
"""Test a harder scenario for ONP combination"""
mut1 = MutationData(chr=1,
start=100,
end=100,
ref_allele="G",
alt_allele="A")
mut1.createAnnotation("phasing_id", "value1", "INPUT")
mut1.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut2 = MutationData(chr=1,
start=101,
end=101,
ref_allele="C",
alt_allele="T")
mut2.createAnnotation("phasing_id", "value1", "INPUT")
mut2.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut3 = MutationData(chr=1,
start=102,
end=102,
ref_allele="C",
alt_allele="T")
mut3.createAnnotation("phasing_id", "value1", "INPUT")
mut3.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Note the differing ID in mut4
mut4 = MutationData(chr=1,
start=103,
end=103,
ref_allele="C",
alt_allele="T")
mut4.createAnnotation("phasing_id", "value2", "INPUT")
mut4.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut5 = MutationData(chr=1,
start=104,
end=104,
ref_allele="C",
alt_allele="T")
mut5.createAnnotation("phasing_id", "value1", "INPUT")
mut5.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Note separate chromosome for mut6
mut6 = MutationData(chr=2,
start=105,
end=105,
ref_allele="C",
alt_allele="T")
mut6.createAnnotation("phasing_id", "value1", "INPUT")
mut6.createAnnotation("phasing_genotype", "0|1", "INPUT")
gt_alts = ["ATT", "T", "T", "T"]
mutations = [mut1, mut2, mut3, mut4, mut5, mut6]
mdf = MutationDataFactory()
queue = OnpQueue(mutations, mdf)
for i, mut in enumerate(queue.get_combined_mutations()):
self.assertTrue(gt_alts[i] == mut.alt_allele)
def _onp_unordered_combiner_test(self,inputs, expected):
"""Convert input and expected tuples into MutationData objects, then run the inputs through the ONP combiner on
the inputs and compare to the expected"""
input_muts = iter(self._tuples_to_MutationData(inputs))
expected = self._tuples_to_MutationData(expected)
combiner = OnpQueue(input_muts)
results = list(combiner.get_combined_mutations())
self.assert_mutations_match_expected(expected, results)
def test_indel(self):
"""Test indel not used in onp combination no matter what the phasing info"""
mut1 = MutationData(chr=1,
start=100,
end=100,
ref_allele="G",
alt_allele="A")
mut1.createAnnotation("phasing_id", "value1", "INPUT")
mut1.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut2 = MutationData(chr=1,
start=101,
end=101,
ref_allele="C",
alt_allele="T")
mut2.createAnnotation("phasing_id", "value1", "INPUT")
mut2.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut3 = MutationData(chr=1,
start=102,
end=102,
ref_allele="C",
alt_allele="T")
mut3.createAnnotation("phasing_id", "value1", "INPUT")
mut3.createAnnotation("phasing_genotype", "0|1", "INPUT")
# Indel
mut4 = MutationData(chr=1,
start=103,
end=104,
ref_allele="-",
alt_allele="TT")
mut4.createAnnotation("phasing_id", "value1", "INPUT")
mut4.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut5 = MutationData(chr=1,
start=104,
end=104,
ref_allele="C",
alt_allele="T")
mut5.createAnnotation("phasing_id", "value1", "INPUT")
mut5.createAnnotation("phasing_genotype", "0|1", "INPUT")
mut6 = MutationData(chr=1,
start=105,
end=105,
ref_allele="C",
alt_allele="T")
mut6.createAnnotation("phasing_id", "value1", "INPUT")
mut6.createAnnotation("phasing_genotype", "0|1", "INPUT")
gt_alts = ["ATT", "TT", "TT"]
mutations = [mut1, mut2, mut3, mut4, mut5, mut6]
mdf = MutationDataFactory()
queue = OnpQueue(mutations, mdf)
for i, mut in enumerate(queue.get_combined_mutations()):
self.assertTrue(gt_alts[i] == mut.alt_allele)
def _onp_unordered_combiner_test(self,inputs, expected):
"""Convert input and expected tuples into MutationData objects, then run the inputs through the ONP combiner on
the inputs and compare to the expected"""
input_muts = iter(self._tuples_to_MutationData(inputs))
expected = self._tuples_to_MutationData(expected)
mdf = MutationDataFactory()
combiner = OnpQueue(input_muts, mdf)
results = list(combiner.get_combined_mutations())
self.assert_mutations_match_expected(expected, results)
def test_mutation_combiner_identical_annotation(self):
"""Test that annotations with all identical values are not repeated with | between them"""
mut1 = MutationDataFactory.default_create(chr=1,
start=100,
end=100,
ref_allele="G",
alt_allele="A")
mut1.createAnnotation("SampleName", "John Doe")
mut2 = MutationDataFactory.default_create(chr=1,
start=101,
end=101,
ref_allele="C",
alt_allele="T")
mut2.createAnnotation("SampleName", "John Doe")
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1,
start=100,
end=101,
ref_allele="GC",
alt_allele="AT")
expected.createAnnotation("SampleName", "John Doe")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def test_mutation_combiner_ordering(self):
"""Test that ordering of combined attributes makes matches original order"""
mut1 = MutationDataFactory.default_create(chr=1,
start=100,
end=100,
ref_allele="G",
alt_allele="A")
mut1.createAnnotation("SomeDepth", "2")
mut1.createAnnotation("AnotherDepth", "1")
mut2 = MutationDataFactory.default_create(chr=1,
start=101,
end=101,
ref_allele="C",
alt_allele="T")
mut2.createAnnotation("SomeDepth", "1")
mut2.createAnnotation("AnotherDepth", "2")
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1,
start=100,
end=101,
ref_allele="GC",
alt_allele="AT")
expected.createAnnotation("SomeDepth", "2|1")
expected.createAnnotation("AnotherDepth", "1|2")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def test_mutation_combiner(self):
"""Test that attributes and annotations are set properly with combine mutations"""
mut1 = MutationDataFactory.default_create(chr=1,
start=100,
end=100,
ref_allele="G",
alt_allele="A")
mut1.createAnnotation("SomeValue", "value1", "INPUT", "STRING",
"a value")
mut2 = MutationDataFactory.default_create(chr=1,
start=101,
end=101,
ref_allele="C",
alt_allele="T")
mut2.createAnnotation("SomeValue", "value2", tags=["IT"])
mut2.createAnnotation("AnotherValue", "5")
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1,
start=100,
end=101,
ref_allele="GC",
alt_allele="AT")
expected.createAnnotation("SomeValue",
"value1|value2",
"INPUT",
"STRING",
"a value",
tags=["IT"])
expected.createAnnotation("AnotherValue", "5")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def test_mutation_combiner(self):
"""Test that attributes and annotations are set properly with combine mutations"""
mut1 = MutationDataFactory.default_create(chr=1,start=100, end=100, ref_allele="G", alt_allele="A")
mut1.createAnnotation("SomeValue", "value1", "INPUT", "STRING", "a value")
mut2 = MutationDataFactory.default_create(chr=1,start=101, end=101, ref_allele="C", alt_allele="T")
mut2.createAnnotation("SomeValue", "value2", tags=["IT"])
mut2.createAnnotation("AnotherValue","5")
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1, start=100, end=101, ref_allele="GC", alt_allele="AT")
expected.createAnnotation("SomeValue", "value1|value2", "INPUT", "STRING", "a value", tags=["IT"])
expected.createAnnotation("AnotherValue", "5")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def test_mutation_combiner_identical_annotation(self):
"""Test that annotations with all identical values are not repeated with | between them"""
mut1 = MutationDataFactory.default_create(chr=1,start=100, end=100, ref_allele="G", alt_allele="A")
mut1.createAnnotation("SampleName", "John Doe")
mut2 = MutationDataFactory.default_create(chr=1,start=101, end=101, ref_allele="C", alt_allele="T")
mut2.createAnnotation("SampleName", "John Doe" )
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1, start=100, end=101, ref_allele="GC", alt_allele="AT")
expected.createAnnotation("SampleName", "John Doe")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def test_mutation_combiner_ordering(self):
"""Test that ordering of combined attributes makes matches original order"""
mut1 = MutationDataFactory.default_create(chr=1,start=100, end=100, ref_allele="G", alt_allele="A")
mut1.createAnnotation("SomeDepth", "2")
mut1.createAnnotation("AnotherDepth", "1")
mut2 = MutationDataFactory.default_create(chr=1,start=101, end=101, ref_allele="C", alt_allele="T")
mut2.createAnnotation("SomeDepth", "1" )
mut2.createAnnotation("AnotherDepth", "2")
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([mut1, mut2], mdf)
expected = MutationDataFactory.default_create(chr=1, start=100, end=101, ref_allele="GC", alt_allele="AT")
expected.createAnnotation("SomeDepth", "2|1")
expected.createAnnotation("AnotherDepth","1|2")
self.assertTrue(result.attributesEqual(expected))
self.assertEqual(result, expected)
def createMutations(self):
mutations = self.input_creator.createMutations()
queue = OnpQueue(mutations)
for mut in queue.get_combined_mutations():
yield mut
def test_mutation_combiner_no_mut(self):
"""Combining no mutations should return None"""
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([], mdf)
self.assertIsNone(result)
def test_mutation_combiner_no_mut(self):
"""Combining no mutations should return None"""
mdf = MutationDataFactory()
result = OnpQueue._combine_mutations([], mdf)
self.assertIsNone(result)
def test_mutation_combiner_no_mut(self):
"""Combining no mutations should return None"""
result = OnpQueue._combine_mutations([])
self.assertIsNone(result)
def createMutations(self):
mutations = self.input_creator.createMutations()
queue = OnpQueue(mutations, self._mutation_data_factory)
for mut in queue.get_combined_mutations():
yield mut
