def default_options(read_requirements=None):
"""Creates a PileupImageOptions populated with good default values."""
if not read_requirements:
read_requirements = core_pb2.ReadRequirements(
min_base_quality=DEFAULT_MIN_BASE_QUALITY,
min_mapping_quality=DEFAULT_MIN_MAPPING_QUALITY,
min_base_quality_mode=core_pb2.ReadRequirements.ENFORCED_BY_CLIENT)
return deepvariant_pb2.PileupImageOptions(
reference_band_height=5,
base_color_offset_a_and_g=40,
base_color_offset_t_and_c=30,
base_color_stride=70,
allele_supporting_read_alpha=1.0,
allele_unsupporting_read_alpha=0.6,
reference_matching_read_alpha=0.2,
reference_mismatching_read_alpha=1.0,
indel_anchoring_base_char='*',
reference_alpha=0.4,
reference_base_quality=60,
positive_strand_color=70,
negative_strand_color=240,
base_quality_cap=40,
mapping_quality_cap=60,
height=100,
width=221,
read_overlap_buffer_bp=5,
read_requirements=read_requirements,
multi_allelic_mode=deepvariant_pb2.PileupImageOptions.
ADD_HET_ALT_IMAGES,
# Fixed random seed produced with 'od -vAn -N4 -tu4 < /dev/urandom'.
random_seed=2101079370)
def test_realigner_end2end(self):
ref_reader = genomics_io.make_ref_reader(test_utils.CHR20_FASTA)
config = realigner.realigner_config(FLAGS)
reads_realigner = realigner.Realigner(config, ref_reader)
region_str = 'chr20:10,000,000-10,009,999'
regions = ranges.RangeSet.from_regions([region_str])
for region in regions.partition(1000):
with genomics_io.make_sam_reader(
test_utils.CHR20_BAM,
core_pb2.ReadRequirements()) as sam_reader:
in_reads = list(sam_reader.query(region))
windows, out_reads = reads_realigner.realign_reads(
in_reads, region)
# We should always get back all of the reads we sent in. Instead of just
# checking the lengths are the same, make sure all the read names are the
# same.
self.assertCountEqual([r.fragment_name for r in in_reads],
[r.fragment_name for r in out_reads])
# Make sure we assembled at least one windows in the region.
self.assertNotEqual(0, len(windows))
# Check each window to make sure it's reasonable.
for window in windows:
# We always expect the reference sequence to be one of our haplotypes.
ref_seq = ref_reader.bases(window.span)
self.assertIn(ref_seq, set(window.haplotypes))
def default_options(add_flags=True, flags=None):
"""Creates a DeepVariantOptions proto populated with reasonable defaults.
Args:
add_flags: bool. defaults to True. If True, we will push the value of
certain FLAGS into our options. If False, those option fields are left
uninitialized.
flags: object. If not None, use as the source of flags,
else use global FLAGS.
Returns:
deepvariant_pb2.DeepVariantOptions protobuf.
Raises:
ValueError: If we observe invalid flag values.
"""
if not flags:
flags = FLAGS
read_reqs = core_pb2.ReadRequirements(
min_base_quality=10,
min_mapping_quality=10,
min_base_quality_mode=core_pb2.ReadRequirements.ENFORCED_BY_CLIENT)
pic_options = pileup_image.default_options(read_requirements=read_reqs)
allele_counter_options = deepvariant_pb2.AlleleCounterOptions(
partition_size=flags.partition_size, read_requirements=read_reqs)
if flags.sample_name:
sample_name = flags.sample_name
elif flags.reads:
sample_name = extract_sample_name_from_reads(flags.reads)
else:
sample_name = _UNKNOWN_SAMPLE
variant_caller_options = deepvariant_pb2.VariantCallerOptions(
min_count_snps=flags.vsc_min_count_snps,
min_count_indels=flags.vsc_min_count_indels,
min_fraction_snps=flags.vsc_min_fraction_snps,
min_fraction_indels=flags.vsc_min_fraction_indels,
# Not specified by default: fraction_reference_sites_to_emit,
# Fixed random seed produced with 'od -vAn -N4 -tu4 < /dev/urandom'.
random_seed=1400605801,
sample_name=sample_name,
p_error=0.001,
max_gq=50,
gq_resolution=1,
ploidy=2)
options = deepvariant_pb2.DeepVariantOptions(
exclude_contigs=[
# The two canonical names for the contig representing the human
# mitochondrial sequence.
'chrM',
'MT',
# From hs37d5.
# (ftp://ftp.1000genomes.ebi.ac.uk/vol1/ftp/technical/reference/phase2_reference_assembly_sequence/README_human_reference_20110707) # pylint:disable=line-too-long
'GL000207.1',
'GL000226.1',
'GL000229.1',
'GL000231.1',
'GL000210.1',
'GL000239.1',
'GL000235.1',
'GL000201.1',
'GL000247.1',
'GL000245.1',
'GL000197.1',
'GL000203.1',
'GL000246.1',
'GL000249.1',
'GL000196.1',
'GL000248.1',
'GL000244.1',
'GL000238.1',
'GL000202.1',
'GL000234.1',
'GL000232.1',
'GL000206.1',
'GL000240.1',
'GL000236.1',
'GL000241.1',
'GL000243.1',
'GL000242.1',
'GL000230.1',
'GL000237.1',
'GL000233.1',
'GL000204.1',
'GL000198.1',
'GL000208.1',
'GL000191.1',
'GL000227.1',
'GL000228.1',
'GL000214.1',
'GL000221.1',
'GL000209.1',
'GL000218.1',
'GL000220.1',
'GL000213.1',
'GL000211.1',
'GL000199.1',
'GL000217.1',
'GL000216.1',
'GL000215.1',
'GL000205.1',
'GL000219.1',
'GL000224.1',
'GL000223.1',
'GL000195.1',
'GL000212.1',
'GL000222.1',
'GL000200.1',
'GL000193.1',
'GL000194.1',
'GL000225.1',
'GL000192.1',
'NC_007605',
'hs37d5',
],
# Fixed random seed produced with 'od -vAn -N4 -tu4 < /dev/urandom'.
random_seed=609314161,
# # Not specified by default: calling_regions = 3;
read_requirements=read_reqs,
allele_counter_options=allele_counter_options,
variant_caller_options=variant_caller_options,
pic_options=pic_options,
n_cores=1,
task_id=0,
num_shards=0,
min_shared_contigs_basepairs=0.9,
)
if add_flags:
if flags.mode == 'training':
options.mode = deepvariant_pb2.DeepVariantOptions.TRAINING
elif flags.mode == 'calling':
options.mode = deepvariant_pb2.DeepVariantOptions.CALLING
else:
raise ValueError('Unexpected mode', flags.mode)
if flags.ref:
options.reference_filename = flags.ref
if flags.reads:
options.reads_filename = flags.reads
if flags.confident_regions:
options.confident_regions_filename = flags.confident_regions
if flags.truth_variants:
options.truth_variants_filename = flags.truth_variants
if flags.downsample_fraction != NO_DOWNSAMPLING:
options.downsample_fraction = flags.downsample_fraction
if flags.multi_allelic_mode:
multi_allelic_enum = {
'include_het_alt_images':
deepvariant_pb2.PileupImageOptions.ADD_HET_ALT_IMAGES,
'exclude_het_alt_images':
deepvariant_pb2.PileupImageOptions.NO_HET_ALT_IMAGES,
}[flags.multi_allelic_mode]
options.pic_options.multi_allelic_mode = multi_allelic_enum
if flags.pileup_image_height:
options.pic_options.height = flags.pileup_image_height
if flags.pileup_image_width:
options.pic_options.width = flags.pileup_image_width
num_shards, examples, candidates, gvcf = io_utils.resolve_filespecs(
flags.task, flags.examples or '', flags.candidates or '',
flags.gvcf or '')
options.examples_filename = examples
options.candidates_filename = candidates
options.gvcf_filename = gvcf
# redacted
regions_flag = flags.regions
if isinstance(regions_flag, str):
regions_flag = regions_flag.split()
options.calling_regions.extend(regions_flag)
options.task_id = flags.task
options.num_shards = 0 if num_shards is None else num_shards
if flags.realign_reads:
options.realigner_enabled = True
options.realigner_options.CopyFrom(
realigner.realigner_config(flags))
options.max_reads_per_partition = flags.max_reads_per_partition
if (options.mode == deepvariant_pb2.DeepVariantOptions.TRAINING
and flags.training_random_emit_ref_sites != NO_RANDOM_REF):
options.variant_caller_options.fraction_reference_sites_to_emit = (
flags.training_random_emit_ref_sites)
return options
def default_options(add_flags=True, flags_obj=None):
"""Creates a DeepVariantOptions proto populated with reasonable defaults.
Args:
add_flags: bool. defaults to True. If True, we will push the value of
certain FLAGS into our options. If False, those option fields are left
uninitialized.
flags_obj: object. If not None, use as the source of flags,
else use global FLAGS.
Returns:
deepvariant_pb2.DeepVariantOptions protobuf.
Raises:
ValueError: If we observe invalid flag values.
"""
if not flags_obj:
flags_obj = FLAGS
read_reqs = core_pb2.ReadRequirements(
min_base_quality=10,
min_mapping_quality=10,
min_base_quality_mode=core_pb2.ReadRequirements.ENFORCED_BY_CLIENT)
pic_options = pileup_image.default_options(read_requirements=read_reqs)
allele_counter_options = deepvariant_pb2.AlleleCounterOptions(
partition_size=flags_obj.partition_size, read_requirements=read_reqs)
if flags_obj.sample_name:
sample_name = flags_obj.sample_name
elif flags_obj.reads:
with genomics_io.make_sam_reader(flags_obj.reads) as sam_reader:
sample_name = extract_sample_name_from_sam_reader(sam_reader)
else:
sample_name = _UNKNOWN_SAMPLE
variant_caller_options = deepvariant_pb2.VariantCallerOptions(
min_count_snps=flags_obj.vsc_min_count_snps,
min_count_indels=flags_obj.vsc_min_count_indels,
min_fraction_snps=flags_obj.vsc_min_fraction_snps,
min_fraction_indels=flags_obj.vsc_min_fraction_indels,
# Not specified by default: fraction_reference_sites_to_emit,
# Fixed random seed produced with 'od -vAn -N4 -tu4 < /dev/urandom'.
random_seed=1400605801,
sample_name=sample_name,
p_error=0.001,
max_gq=50,
gq_resolution=flags_obj.gvcf_gq_binsize,
ploidy=2)
options = deepvariant_pb2.DeepVariantOptions(
exclude_contigs=exclude_contigs.EXCLUDED_HUMAN_CONTIGS,
# Fixed random seed produced with 'od -vAn -N4 -tu4 < /dev/urandom'.
random_seed=609314161,
# # Not specified by default: calling_regions = 3;
read_requirements=read_reqs,
allele_counter_options=allele_counter_options,
variant_caller_options=variant_caller_options,
pic_options=pic_options,
n_cores=1,
task_id=0,
num_shards=0,
min_shared_contigs_basepairs=0.9,
)
if add_flags:
if flags_obj.mode == 'training':
options.mode = deepvariant_pb2.DeepVariantOptions.TRAINING
elif flags_obj.mode == 'calling':
options.mode = deepvariant_pb2.DeepVariantOptions.CALLING
else:
raise ValueError('Unexpected mode', flags_obj.mode)
if flags_obj.ref:
options.reference_filename = flags_obj.ref
if flags_obj.reads:
options.reads_filename = flags_obj.reads
if flags_obj.confident_regions:
options.confident_regions_filename = flags_obj.confident_regions
if flags_obj.truth_variants:
options.truth_variants_filename = flags_obj.truth_variants
if flags_obj.downsample_fraction != NO_DOWNSAMPLING:
options.downsample_fraction = flags_obj.downsample_fraction
if flags_obj.multi_allelic_mode:
multi_allelic_enum = {
'include_het_alt_images':
deepvariant_pb2.PileupImageOptions.ADD_HET_ALT_IMAGES,
'exclude_het_alt_images':
deepvariant_pb2.PileupImageOptions.NO_HET_ALT_IMAGES,
}[flags_obj.multi_allelic_mode]
options.pic_options.multi_allelic_mode = multi_allelic_enum
if flags_obj.pileup_image_height:
options.pic_options.height = flags_obj.pileup_image_height
if flags_obj.pileup_image_width:
options.pic_options.width = flags_obj.pileup_image_width
num_shards, examples, candidates, gvcf = io_utils.resolve_filespecs(
flags_obj.task, flags_obj.examples or '', flags_obj.candidates
or '', flags_obj.gvcf or '')
options.examples_filename = examples
options.candidates_filename = candidates
options.gvcf_filename = gvcf
options.calling_regions.extend(parse_regions_flag(flags_obj.regions))
options.exclude_calling_regions.extend(
parse_regions_flag(flags_obj.exclude_regions))
options.task_id = flags_obj.task
options.num_shards = 0 if num_shards is None else num_shards
options.realigner_enabled = flags_obj.realign_reads
if options.realigner_enabled:
options.realigner_options.CopyFrom(
realigner.realigner_config(flags_obj))
options.max_reads_per_partition = flags_obj.max_reads_per_partition
if (options.mode == deepvariant_pb2.DeepVariantOptions.TRAINING
and flags_obj.training_random_emit_ref_sites != NO_RANDOM_REF):
options.variant_caller_options.fraction_reference_sites_to_emit = (
flags_obj.training_random_emit_ref_sites)
return options