def process(self, region):
"""Finds candidates and creates corresponding examples in a region.
Args:
region: A nucleus.genomics.v1.Range proto. Specifies the region on the
genome we should process.
Returns:
Three values. First is a list of the found candidates, which are
deepvariant.DeepVariantCall objects. The second value is a list of filled
in tf.Example protos. For example, these will include the candidate
variant, the pileup image, and, if in training mode, the truth variants
and labels needed for training. The third value is a list of
nucleus.genomics.v1.Variant protos containing gVCF information for all
reference sites, if gvcf generation is enabled, otherwise returns [].
"""
region_timer = timer.TimerStart()
# Print some basic information about what we are doing.
if not self.initialized:
self._initialize()
self.in_memory_sam_reader.replace_reads(self.region_reads(region))
candidates, gvcfs = self.candidates_in_region(region)
if in_training_mode(self.options):
examples = [
self.add_label_to_example(example, label)
for candidate, label in self.label_candidates(
candidates, region)
for example in self.create_pileup_examples(candidate)
]
else:
examples = [
example for candidate in candidates
for example in self.create_pileup_examples(candidate)
]
logging.info('Found %s candidates in %s [%d bp] [%0.2fs elapsed]',
len(examples), ranges.to_literal(region),
ranges.length(region), region_timer.Stop())
return candidates, examples, gvcfs
def assertCandidatesFromReadsEquals(self,
reads,
expected,
start=None,
end=None,
ref=None):
chrom = reads[0].alignment.position.reference_name
start = 0 if start is None else start
end = 20 if end is None else end
region = ranges.make_range(chrom, start, end)
if ref is None:
ref = 'A' * (ranges.length(region) + 512)
ref_reader = fasta.InMemoryFastaReader([(chrom, 0, ref)])
if isinstance(expected, type) and issubclass(expected, Exception):
with self.assertRaises(expected):
window_selector._candidates_from_reads(self.config, ref_reader,
reads, region)
else:
actual = window_selector._candidates_from_reads(
self.config, ref_reader, reads, region)
self.assertEqual(actual, expected)
def test_length_is_correct(self, region, expected_length):
self.assertEqual(expected_length, ranges.length(region))
