def test_get_input_fn(self):
test_file = test_utils.test_tmpfile('test.tfrecord')
# Use a simple test example that consists of a read sequence of length 5.
example = example_pb2.Example()
read_sequence = 'ACGTA'
true_sequence = 'ACCTA'
aligned_qualities = [30, 30, 20, 30, 30]
features = example.features
features.feature['read_name'].bytes_list.value.append(
six.b('test_seq'))
features.feature['read_sequence'].int64_list.value.extend(
['ACGT'.index(b) for b in read_sequence])
features.feature['read_qualities'].int64_list.value.extend(
aligned_qualities)
features.feature['true_sequence'].int64_list.value.extend(
['ACGT'.index(b) for b in true_sequence])
features.feature['ref_match'].int64_list.value.extend([1, 1, 0, 1, 1])
with genomics_writer.TFRecordWriter(test_file) as writer:
writer.write(example)
features, label = ngs_errors.get_input_fn(
test_file,
ngs_read_length=len(read_sequence),
batch_size=1,
num_epochs=1)()
with tf.Session() as sess:
features_val, label_val = sess.run([features, label])
features_array = np.array(features_val)
self.assertEqual((1, 4, 5, 3), features_array.shape)
self.assertTrue(
np.array_equal(
np.array([[[1, 0, 0, 0, 1], [0, 1, 0, 0,
0], [0, 0, 1, 0, 0],
[0, 0, 0, 1, 0]]]), features_array[:, :, :, 0]))
self.assertTrue(
np.array_equal(
np.array([[[1, 1, 0, 1, 1], [1, 1, 0, 1,
1], [1, 1, 0, 1, 1],
[1, 1, 0, 1, 1]]]), features_array[:, :, :, 1]))
self.assertTrue(
np.array_equal(
np.array([[[30, 30, 20, 30, 30], [30, 30, 20, 30, 30],
[30, 30, 20, 30, 30], [30, 30, 20, 30, 30]]]),
features_array[:, :, :, 2]))
self.assertTrue(
np.array_equal(np.array([[0, 1, 1, 3, 0]]),
np.array(label_val)))
def make_ngs_error_examples(ref_path,
vcf_path,
bam_path,
examples_out_path,
max_reads=None):
"""Driver program for ngs_errors.
See module description for details.
Args:
ref_path: str. A path to an indexed fasta file.
vcf_path: str. A path to an indexed VCF file.
bam_path: str. A path to an SAM/BAM file.
examples_out_path: str. A path where we will write out examples.
max_reads: int or None. If not None, we will emit at most max_reads examples
to examples_out_path.
"""
# Create a ref_reader backed by ref.
ref_reader = fasta.IndexedFastaReader(ref_path)
# Create a vcf_reader backed by vcf.
vcf_reader = vcf.VcfReader(vcf_path)
# Create a sam_reader backed by bam. Provide an empty ReadRequirements
# proto to the reader so it enables standard filtering based on the default
# values of ReadRequirements. Also explicitly allow the reader to access an
# unindexed BAM, so only the iterate() function is enabled.
read_requirements = reads_pb2.ReadRequirements()
sam_reader = sam.SamReader(bam_path, read_requirements=read_requirements)
# Create our TFRecordWriter where we'll send our tf.Examples.
examples_out = genomics_writer.TFRecordWriter(examples_out_path)
# All our readers and writers are context managers, so use the `with`
# construct to open all of the inputs/outputs and close them when we are done
# looping over our reads.
n_examples = 0
with ref_reader, vcf_reader, sam_reader, examples_out:
# Loop over the reads in our BAM file:
for i, read in enumerate(sam_reader.iterate(), start=1):
# Get the Range proto describing the chrom/start/stop spanned by our read.
read_range = utils.read_range(read)
# Get all of the variants that overlap our read range.
variants = list(vcf_reader.query(read_range))
# Get the reference bases spanned by our read.
ref_bases = ref_reader.query(read_range)
# Check that we can use our read for generating an example.
if is_usable_training_example(read, variants, ref_bases):
n_examples += 1
# Convert read and ref_bases to a tf.Example with make_example.
example = make_example(read, ref_bases)
# And write it out to our TFRecord output file.
examples_out.write(example)
# Do a bit of convenient logging. This is very verbose if we convert a
# lot of reads...
logging.info((
'Added an example for read %s (span=%s) with cigar %s [%d added '
'of %d total reads]'), read.fragment_name,
ranges.to_literal(read_range),
cigar.format_cigar_units(read.alignment.cigar),
n_examples, i)
if max_reads is not None and n_examples >= max_reads:
return
def Writer(path, compression_type=None): """A convenience wrapper around genomics_writer.TFRecordWriter.""" return genomics_writer.TFRecordWriter(path, compression_type)