def verify_examples(self, examples_filename, region, options,
verify_labels):
# Do some simple structural checks on the tf.Examples in the file.
expected_labels = [
'variant/encoded', 'locus', 'image/format', 'image/encoded',
'alt_allele_indices/encoded'
]
if verify_labels:
expected_labels += ['label', 'truth_variant/encoded']
examples = list(io_utils.read_tfrecords(examples_filename))
for example in examples:
for label_feature in expected_labels:
self.assertIn(label_feature, example.features.feature)
# pylint: disable=g-explicit-length-test
self.assertGreater(
len(tf_utils.example_alt_alleles_indices(example)), 0)
if verify_labels:
# Check that our variant and our truth_variant both have the same start.
self.assertEqual(
variantutils.variant_position(
tf_utils.example_variant(example)),
variantutils.variant_position(
tf_utils.example_truth_variant(example)))
# Check that the variants in the examples are good.
variants = [tf_utils.example_variant(x) for x in examples]
self.verify_variants(variants, region, options, is_gvcf=False)
return examples
def add_label_to_example(self, example, label):
"""Adds label information about the assigned label to our example.
Args:
example: A tf.Example proto. We will write truth_variant and label into
this proto.
label: A variant_labeler.Label object containing the labeling information
to add to our example.
Returns:
The example proto with label fields added.
Raises:
ValueError: if label isn't confident.
"""
if not label.is_confident:
raise ValueError('Cannot add a non-confident label to an example',
example, label)
alt_alleles_indices = tf_utils.example_alt_alleles_indices(example)
# Set the genotype of the candidate variant to the labeled value.
candidate = label.variant
_set_variant_genotype(candidate, label.genotype)
tf_utils.example_set_variant(example, candidate)
# Set the label of the example to the # alts given our alt_alleles_indices.
tf_utils.example_set_label(example,
label.label_for_alt_alleles(alt_alleles_indices))
return 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 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 verify_examples(self, examples_filename, region, options, verify_labels):
# Do some simple structural checks on the tf.Examples in the file.
expected_features = [
'variant/encoded', 'locus', 'image/format', 'image/encoded',
'alt_allele_indices/encoded'
]
if verify_labels:
expected_features += ['label']
examples = list(io_utils.read_tfrecords(examples_filename))
for example in examples:
for label_feature in expected_features:
self.assertIn(label_feature, example.features.feature)
# pylint: disable=g-explicit-length-test
self.assertGreater(len(tf_utils.example_alt_alleles_indices(example)), 0)
# Check that the variants in the examples are good.
variants = [tf_utils.example_variant(x) for x in examples]
self.verify_variants(variants, region, options, is_gvcf=False)
return examples
def verify_examples(self, examples_filename, region, options, verify_labels):
# Do some simple structural checks on the tf.Examples in the file.
expected_features = [
'variant/encoded', 'locus', 'image/format', 'image/encoded',
'alt_allele_indices/encoded'
]
if verify_labels:
expected_features += ['label']
examples = list(tfrecord.read_tfrecords(examples_filename))
for example in examples:
for label_feature in expected_features:
self.assertIn(label_feature, example.features.feature)
# pylint: disable=g-explicit-length-test
self.assertNotEmpty(tf_utils.example_alt_alleles_indices(example))
# Check that the variants in the examples are good.
variants = [tf_utils.example_variant(x) for x in examples]
self.verify_variants(variants, region, options, is_gvcf=False)
return examples
def example_matches_call_variants_output(example,
call_variants_output):
return (tf_utils.example_variant(example)
== call_variants_output.variant
and tf_utils.example_alt_alleles_indices(example)
== call_variants_output.alt_allele_indices.indices)
def test_call_end2end(self, model, shard_inputs, include_debug_info):
FLAGS.include_debug_info = include_debug_info
(call_variants_outputs, examples, batch_size,
max_batches) = self._call_end2end_helper(
testdata.GOLDEN_CALLING_EXAMPLES, model, shard_inputs)
# Check that we have the right number of output protos.
self.assertEqual(
len(call_variants_outputs),
batch_size * max_batches if max_batches else len(examples))
# Check that our CallVariantsOutput (CVO) have the following critical
# properties:
# - we have one CVO for each example we processed.
# - the variant in the CVO is exactly what was in the example.
# - the alt_allele_indices of the CVO match those of its corresponding
# example.
# - there are 3 genotype probabilities and these are between 0.0 and 1.0.
# We can only do this test when processing all of the variants (max_batches
# is None), since we processed all of the examples with that model.
if max_batches is None:
self.assertItemsEqual(
[cvo.variant for cvo in call_variants_outputs],
[tf_utils.example_variant(ex) for ex in examples])
# Check the CVO debug_info: not filled if include_debug_info is False;
# else, filled by logic based on CVO.
if not include_debug_info:
for cvo in call_variants_outputs:
self.assertEqual(
cvo.debug_info,
deepvariant_pb2.CallVariantsOutput.DebugInfo())
else:
for cvo in call_variants_outputs:
self.assertEqual(cvo.debug_info.has_insertion,
variant_utils.has_insertion(cvo.variant))
self.assertEqual(cvo.debug_info.has_deletion,
variant_utils.has_deletion(cvo.variant))
self.assertEqual(cvo.debug_info.is_snp,
variant_utils.is_snp(cvo.variant))
self.assertEqual(cvo.debug_info.predicted_label,
np.argmax(cvo.genotype_probabilities))
def example_matches_call_variants_output(example,
call_variants_output):
return (tf_utils.example_variant(example)
== call_variants_output.variant
and tf_utils.example_alt_alleles_indices(example)
== call_variants_output.alt_allele_indices.indices)
for call_variants_output in call_variants_outputs:
# Find all matching examples.
matches = [
ex for ex in examples if example_matches_call_variants_output(
ex, call_variants_output)
]
# We should have exactly one match.
self.assertEqual(len(matches), 1)
example = matches[0]
# Check that we've faithfully copied in the alt alleles (though currently
# as implemented we find our example using this information so it cannot
# fail). Included here in case that changes in the future.
self.assertEqual(
list(tf_utils.example_alt_alleles_indices(example)),
list(call_variants_output.alt_allele_indices.indices))
# We should have exactly three genotype probabilities (assuming our
# ploidy == 2).
self.assertEqual(len(call_variants_output.genotype_probabilities),
3)
# These are probabilities so they should be between 0 and 1.
self.assertTrue(
0 <= gp <= 1
for gp in call_variants_output.genotype_probabilities)
def test_call_end2end(self, model, shard_inputs, include_debug_info):
FLAGS.include_debug_info = include_debug_info
examples = list(
io_utils.read_tfrecords(testdata.GOLDEN_CALLING_EXAMPLES))
if shard_inputs:
# Create a sharded version of our golden examples.
source_path = test_utils.test_tmpfile('sharded@{}'.format(3))
io_utils.write_tfrecords(examples, source_path)
else:
source_path = testdata.GOLDEN_CALLING_EXAMPLES
batch_size = 4
if model.name == 'random_guess':
# For the random guess model we can run everything.
max_batches = None
else:
# For all other models we only run a single batch for inference.
max_batches = 1
outfile = test_utils.test_tmpfile('call_variants.tfrecord')
call_variants.call_variants(
examples_filename=source_path,
checkpoint_path=modeling.SKIP_MODEL_INITIALIZATION_IN_TEST,
model=model,
output_file=outfile,
batch_size=batch_size,
max_batches=max_batches)
call_variants_outputs = list(
io_utils.read_tfrecords(outfile,
deepvariant_pb2.CallVariantsOutput))
# Check that we have the right number of output protos.
self.assertEqual(
len(call_variants_outputs),
batch_size * max_batches if max_batches else len(examples))
# Check that our CallVariantsOutput (CVO) have the following critical
# properties:
# - we have one CVO for each example we processed.
# - the variant in the CVO is exactly what was in the example.
# - the alt_allele_indices of the CVO match those of its corresponding
# example.
# - there are 3 genotype probabilities and these are between 0.0 and 1.0.
# We can only do this test when processing all of the variants (max_batches
# is None), since we processed all of the examples with that model.
if max_batches is None:
self.assertItemsEqual(
[cvo.variant for cvo in call_variants_outputs],
[tf_utils.example_variant(ex) for ex in examples])
# Check the CVO debug_info: not filled if include_debug_info is False;
# else, filled by logic based on CVO.
if not include_debug_info:
for cvo in call_variants_outputs:
self.assertEqual(
cvo.debug_info,
deepvariant_pb2.CallVariantsOutput.DebugInfo())
else:
for cvo in call_variants_outputs:
self.assertEqual(cvo.debug_info.has_insertion,
variant_utils.has_insertion(cvo.variant))
self.assertEqual(cvo.debug_info.has_deletion,
variant_utils.has_deletion(cvo.variant))
self.assertEqual(cvo.debug_info.is_snp,
variant_utils.is_snp(cvo.variant))
self.assertEqual(cvo.debug_info.predicted_label,
np.argmax(cvo.genotype_probabilities))
def example_matches_call_variants_output(example,
call_variants_output):
return (tf_utils.example_variant(example)
== call_variants_output.variant
and tf_utils.example_alt_alleles_indices(example)
== call_variants_output.alt_allele_indices.indices)
for call_variants_output in call_variants_outputs:
# Find all matching examples.
matches = [
ex for ex in examples if example_matches_call_variants_output(
ex, call_variants_output)
]
# We should have exactly one match.
self.assertEqual(len(matches), 1)
example = matches[0]
# Check that we've faithfully copied in the alt alleles (though currently
# as implemented we find our example using this information so it cannot
# fail). Included here in case that changes in the future.
self.assertEqual(
list(tf_utils.example_alt_alleles_indices(example)),
list(call_variants_output.alt_allele_indices.indices))
# We should have exactly three genotype probabilities (assuming our
# ploidy == 2).
self.assertEqual(len(call_variants_output.genotype_probabilities),
3)
# These are probabilities so they should be between 0 and 1.
self.assertTrue(
0 <= gp <= 1
for gp in call_variants_output.genotype_probabilities)
def example_matches_call_variants_output(example, call_variants_output):
return (tf_utils.example_variant(example) == call_variants_output.variant
and tf_utils.example_alt_alleles_indices(
example) == call_variants_output.alt_allele_indices.indices)
def test_call_end2end(self, model, shard_inputs, include_debug_info):
FLAGS.include_debug_info = include_debug_info
examples = list(io_utils.read_tfrecords(testdata.GOLDEN_CALLING_EXAMPLES))
if shard_inputs:
# Create a sharded version of our golden examples.
source_path = test_utils.test_tmpfile('sharded@{}'.format(3))
io_utils.write_tfrecords(examples, source_path)
else:
source_path = testdata.GOLDEN_CALLING_EXAMPLES
batch_size = 4
if model.name == 'random_guess':
# For the random guess model we can run everything.
max_batches = None
else:
# For all other models we only run a single batch for inference.
max_batches = 1
outfile = test_utils.test_tmpfile('call_variants.tfrecord')
call_variants.call_variants(
examples_filename=source_path,
checkpoint_path=modeling.SKIP_MODEL_INITIALIZATION_IN_TEST,
model=model,
output_file=outfile,
batch_size=batch_size,
max_batches=max_batches)
call_variants_outputs = list(
io_utils.read_tfrecords(outfile, deepvariant_pb2.CallVariantsOutput))
# Check that we have the right number of output protos.
self.assertEqual(
len(call_variants_outputs), batch_size * max_batches
if max_batches else len(examples))
# Check that our CallVariantsOutput (CVO) have the following critical
# properties:
# - we have one CVO for each example we processed.
# - the variant in the CVO is exactly what was in the example.
# - the alt_allele_indices of the CVO match those of its corresponding
# example.
# - there are 3 genotype probabilities and these are between 0.0 and 1.0.
# We can only do this test when processing all of the variants (max_batches
# is None), since we processed all of the examples with that model.
if max_batches is None:
self.assertItemsEqual([cvo.variant for cvo in call_variants_outputs],
[tf_utils.example_variant(ex) for ex in examples])
# Check the CVO debug_info: not filled if include_debug_info is False;
# else, filled by logic based on CVO.
if not include_debug_info:
for cvo in call_variants_outputs:
self.assertEqual(cvo.debug_info,
deepvariant_pb2.CallVariantsOutput.DebugInfo())
else:
for cvo in call_variants_outputs:
self.assertEqual(cvo.debug_info.has_insertion,
variant_utils.has_insertion(cvo.variant))
self.assertEqual(cvo.debug_info.has_deletion,
variant_utils.has_deletion(cvo.variant))
self.assertEqual(cvo.debug_info.is_snp, variant_utils.is_snp(
cvo.variant))
self.assertEqual(cvo.debug_info.predicted_label,
np.argmax(cvo.genotype_probabilities))
def example_matches_call_variants_output(example, call_variants_output):
return (tf_utils.example_variant(example) == call_variants_output.variant
and tf_utils.example_alt_alleles_indices(
example) == call_variants_output.alt_allele_indices.indices)
for call_variants_output in call_variants_outputs:
# Find all matching examples.
matches = [
ex for ex in examples
if example_matches_call_variants_output(ex, call_variants_output)
]
# We should have exactly one match.
self.assertEqual(len(matches), 1)
example = matches[0]
# Check that we've faithfully copied in the alt alleles (though currently
# as implemented we find our example using this information so it cannot
# fail). Included here in case that changes in the future.
self.assertEqual(
list(tf_utils.example_alt_alleles_indices(example)),
list(call_variants_output.alt_allele_indices.indices))
# We should have exactly three genotype probabilities (assuming our
# ploidy == 2).
self.assertEqual(len(call_variants_output.genotype_probabilities), 3)
# These are probabilities so they should be between 0 and 1.
self.assertTrue(
0 <= gp <= 1 for gp in call_variants_output.genotype_probabilities)
def convert_to_class(self, example): """Convert label to the class id.""" alt_alleles_indices = tf_utils.example_alt_alleles_indices(example) # Set the label of the example to the # alts given our alt_alleles_indices. return self.label_for_alt_alleles(alt_alleles_indices)
