def test_label_variant(self):
variant = test_utils.make_variant(start=10, alleles=['A', 'C'])
tvariant = test_utils.make_variant(start=10,
alleles=['A', 'C'],
gt=[0, 1])
example = tf_utils.make_example(variant, ['C'], 'foo',
self.default_shape,
self.default_format)
labeler = mock.Mock()
labeler.match = mock.Mock(return_value=[True, tvariant])
labeler.match_to_alt_count = mock.Mock(return_value=1)
self.processor.labeler = labeler
labeled = example_pb2.Example()
labeled.CopyFrom(example)
self.processor.label_variant(labeled, variant)
labeler.match.assert_called_once_with(variant)
labeler.match_to_alt_count.assert_called_once_with(
variant, tvariant, ['C'])
for key, value in example.features.feature.iteritems():
self.assertEqual(value, labeled.features.feature[key])
self.assertEqual(1, tf_utils.example_label(labeled))
self.assertEqual(tvariant, tf_utils.example_truth_variant(labeled))
def create_pileup_examples(self, dv_call):
"""Creates a tf.Example for DeepVariantCall.
This function calls PileupImageCreator.create_pileup_images on dv_call to
get raw image tensors for each alt_allele option (see docs for details).
These tensors are encoded as pngs, and all of the key information is encoded
as a tf.Example via a call to tf_utils.make_example.
Args:
dv_call: A DeepVariantCall.
Returns:
A list of tf.Example protos.
"""
pileup_images = self.pic.create_pileup_images(dv_call)
if pileup_images is None:
# We cannot build a PileupImage for dv_call, issue a warning.
logging.warning('Could not create PileupImage for candidate at %s:%s',
dv_call.variant.reference_name, dv_call.variant.start)
return []
examples = []
for alt_alleles, image_tensor in pileup_images:
encoded_tensor, shape, tensor_format = self._encode_tensor(image_tensor)
examples.append(
tf_utils.make_example(
dv_call.variant,
alt_alleles,
encoded_tensor,
shape=shape,
image_format=tensor_format))
return examples
def test_label_variant_raises_for_non_confident_variant(self):
variant = test_utils.make_variant(start=10, alleles=['A', 'C'], gt=[0, 1])
self.processor.labeler = mock.Mock()
self.processor.labeler.match = mock.Mock(return_value=[False, variant])
example = tf_utils.make_example(variant, ['C'], 'foo', self.default_shape,
self.default_format)
self.assertFalse(self.processor.label_variant(example, variant))
def testExampleSetLabel(self):
example = tf_utils.make_example(self.variant, self.alts, self.encoded_image,
self.default_shape, self.default_format)
self.assertIsNotAFeature('label', example)
for label in [0, 1, 2]:
tf_utils.example_set_label(example, label)
self.assertEqual(label, tf_utils.example_label(example))
def testMakeExampleMultiAllelic(self):
alts = ['AA', 'CC', 'GG']
self.variant.alternate_bases[:] = alts
# Providing GG, AA checks that we're sorting the indices.
example = tf_utils.make_example(self.variant, ['GG', 'AA'], 'foo',
self.default_shape, self.default_format)
self.assertEqual([0, 2], tf_utils.example_alt_alleles_indices(example))
self.assertEqual(['AA', 'GG'], tf_utils.example_alt_alleles(example))
self.assertEqual('1:11:C->AA/GG', tf_utils.example_key(example))
def testExampleSetTruthVariant(self):
example = tf_utils.make_example(self.variant, self.alts,
self.encoded_image, self.default_shape,
self.default_format)
full_tvariant = variants_pb2.Variant(
variant_set_id='variant_set_id',
id='id',
names=['name1'],
created=1234,
reference_name='1',
start=10,
end=11,
reference_bases='C',
alternate_bases=['A'],
filter=['PASS'],
quality=1234.5,
calls=[
variants_pb2.VariantCall(call_set_id='call_set_id',
call_set_name='call_set_name',
genotype=[0, 1],
phaseset='phaseset',
genotype_likelihood=[0.1, 0.2, 0.3])
])
test_utils.set_list_values(full_tvariant.info['key'], [1])
test_utils.set_list_values(full_tvariant.calls[0].info['key'], [2])
simple_tvariant = variants_pb2.Variant(
reference_name='1',
start=10,
end=11,
reference_bases='C',
alternate_bases=['A'],
filter=['PASS'],
quality=1234.5,
calls=[
variants_pb2.VariantCall(call_set_name='call_set_name',
genotype=[0, 1])
])
test_utils.set_list_values(simple_tvariant.calls[0].info['key'], [2])
self.assertIsNotAFeature('truth_variant/encoded', example)
tf_utils.example_set_truth_variant(example,
full_tvariant,
simplify=False)
self.assertEqual(full_tvariant,
tf_utils.example_truth_variant(example))
# Check that reencoding with simplify=True produces the simplified version.
tf_utils.example_set_truth_variant(example,
full_tvariant,
simplify=True)
self.assertEqual(simple_tvariant,
tf_utils.example_truth_variant(example))
def testMakeExample(self):
example = tf_utils.make_example(self.variant, self.alts, self.encoded_image,
self.default_shape, self.default_format)
self.assertEqual(self.encoded_image,
tf_utils.example_encoded_image(example))
self.assertEqual(
'raw', example.features.feature['image/format'].bytes_list.value[0])
self.assertEqual(self.variant, tf_utils.example_variant(example))
self.assertEqual('1:11-11', tf_utils.example_locus(example))
self.assertEqual([0], tf_utils.example_alt_alleles_indices(example))
self.assertEqual('1:11:C->A', tf_utils.example_key(example))
def testAltAllelesWithVariant(self):
alts = list(self.variant.alternate_bases)
example = tf_utils.make_example(self.variant, alts, six.b('foo'),
self.default_shape, self.default_format)
self.assertEqual([0], tf_utils.example_alt_alleles_indices(example))
with mock.patch(
'deepvariant.tf_utils.example_variant'
) as mock_ex_variant:
# Providing variant directly avoids the call to example_variant().
self.assertEqual(
alts, tf_utils.example_alt_alleles(example, variant=self.variant))
mock_ex_variant.assert_not_called()
# Checks that we load the variant if needed and that our mock is working.
mock_ex_variant.return_value = self.variant
self.assertEqual(alts, tf_utils.example_alt_alleles(example))
mock_ex_variant.assert_called_once_with(example)
def testExampleImageShape(self):
example = tf_utils.make_example(self.variant, self.alts,
self.encoded_image, self.default_shape,
self.default_format)
self.assertEqual(self.default_shape,
tf_utils.example_image_shape(example))
def _example_for_variant(self, variant):
return tf_utils.make_example(variant, list(variant.alternate_bases), 'foo',
self.default_shape, self.default_format)
def _example_for_variant(self, variant):
return tf_utils.make_example(variant, list(variant.alternate_bases),
six.b('foo'), self.default_shape,
self.default_format)