def insertion_variant():
bam = os.path.join(get_data_folder(), "some_indels.bam")
variant = Variant(chrom="1", pos=10122622, id="rs57037935", ref='T', allele='TG',
quality=50, filter=[], info={}, format=['GT', 'PS', 'DP', 'ADALL', 'AD', 'GQ'],
samples=[['1/1', None, 546, [0, 246], [25, 25], 330]], zygosity=[VariantZygosity.HOMOZYGOUS],
type=VariantType.INSERTION, vcf='null.vcf', bams=[bam])
return variant
def deletion_variant():
bam = os.path.join(get_data_folder(), "some_indels.bam")
variant = Variant(chrom="1", pos=10163457, id=None, ref='CTTTA', allele='C',
quality=50, filter=[], info={}, format=['GT', 'PS', 'DP', 'ADALL', 'AD', 'GQ'],
samples=[['1/0', None, 177, [0, 0, 0], [0, 0, 0], 160]], zygosity=[VariantZygosity.HETEROZYGOUS],
type=VariantType.DELETION, vcf='null.vcf', bams=[bam])
return variant
def snp_variant():
bam = os.path.join(get_data_folder(), "small_bam.bam")
variant = Variant(chrom="1", pos=240000, id="GL000235", ref='T', allele='A',
quality=60, filter=None, info={'DP': 35, 'AF': 0.0185714}, format=['GT', 'GQ'],
samples=[['1/1', '50']], zygosity=[VariantZygosity.HOMOZYGOUS],
type=VariantType.SNP, vcf='null.vcf', bams=[bam])
return variant
def _df_row_to_variant(dataframe, idx, format_vcf_key_counts, sample_names,
filter_vcf_keys, info_vcf_key_counts, header_type, vcf,
bams):
# Convert row Series into dict to improve access performance.
row = dataframe.iloc[idx].to_dict()
# Build sample data by iterating through FORMAT columns.
samples = []
zygosities = []
format_keys = sorted(format_vcf_key_counts.keys())
for call in sample_names:
call_data = []
for k in format_keys:
count = format_vcf_key_counts[k]
if count == 1:
call_data.append(header_type[k](row["{}_{}".format(call, k)]))
else:
vals = []
for i in range(count):
vals.append(header_type[k](row["{}_{}-{}".format(
call, k, i)]))
call_data.append(vals)
samples.append(call_data)
zyg_col = "{}_GT".format(call)
if zyg_col in row:
zygosities.append(VariantZygosity(row[zyg_col]))
# Build filter data by iterating over all saved FILTER keys.
var_filter = []
for k in filter_vcf_keys:
if row["FILTER_{}".format(k)]:
var_filter.append(k)
# Build info data by iterating over all saved INFO keys.
info = {}
for k, count in info_vcf_key_counts.items():
if count == 1:
val = header_type[k](row["{}".format(k)])
info[k] = val
else:
vals = []
for i in range(count):
vals.append(header_type[k](row["{}-{}".format(k, i)]))
info[k] = vals
variant = Variant(chrom=row["chrom"],
pos=row["start_pos"],
id=row["id"] if "id" in row else ".",
ref=row["ref"],
allele=row["alt"],
quality=row["quality"] if "quality" in row else ".",
filter=(var_filter if var_filter else None),
info=info,
format=format_keys,
type=VariantType(row["variant_type"]),
samples=samples,
zygosity=zygosities,
vcf=vcf,
bams=bams)
return variant
def _create_variant_tuple_from_record(self, record, vcf_file, bam, is_fp):
"""Create a variant record from pyVCF record.
Args:
record : pyVCF record
vcf_file : Path to VCF file
bam : Path to corresponding BAM file
is_fp : Boolean indicating whether entry is a false positive variant or not.
Returns:
Variant dataclass record.
"""
var_zyg = self._get_variant_zygosity(record, is_fp)
var_type = self._get_variant_type(record)
# Split multi alleles into multiple entries
for alt in record.ALT:
var_allele = alt.sequence
try:
var_format = record.FORMAT.split(':')
except AttributeError:
if is_fp:
var_format = []
else:
raise RuntimeError(
"Could not parse format field for entry - {}".format(
record))
try:
yield Variant(
chrom=record.CHROM,
pos=record.POS,
id=record.ID,
ref=record.REF,
allele=var_allele,
quality=record.QUAL,
filter=record.FILTER,
info=record.INFO,
format=var_format,
samples=[[field_value for field_value in sample.data]
for sample in record.samples],
zygosity=var_zyg,
type=var_type,
vcf=vcf_file,
bam=bam)
except Exception:
raise RuntimeError(
"Could not parse variant from entry - {}".format(record))
def test_zygosity_encoder():
encoder = ZygosityLabelEncoder()
bam = os.path.join(get_data_folder(), "small_bam.bam")
variant = Variant(chrom="1",
pos=240000,
id="GL000235",
ref='T',
allele='A',
quality=60,
filter=None,
info={
'DP': 35,
'AF': 0.0185714
},
format=['GT', 'GQ'],
samples=[['1/1', '50']],
zygosity=[VariantZygosity.HOMOZYGOUS],
type=VariantType.SNP,
vcf='null.vcf',
bams=[bam])
encoding = encoder(variant)
# Since it should return a scalar
assert (encoding.size() == torch.Size([]))
assert (encoding == 1)
variant = Variant(chrom="1",
pos=240000,
id="GL000235",
ref='T',
allele='A',
quality=60,
filter=None,
info={
'DP': 35,
'AF': 0.0185714
},
format=['GT', 'GQ'],
samples=[['0/0', '50']],
zygosity=[VariantZygosity.NO_VARIANT],
type=VariantType.SNP,
vcf='null.vcf',
bams=[bam])
encoding = encoder(variant)
assert (encoding == 0)
variant = Variant(chrom="1",
pos=240000,
id="GL000235",
ref='T',
allele='A',
quality=60,
filter=None,
info={
'DP': 35,
'AF': 0.0185714
},
format=['GT', 'GQ'],
samples=[['0/1', '50']],
zygosity=[VariantZygosity.HETEROZYGOUS],
type=VariantType.SNP,
vcf='null.vcf',
bams=[bam])
encoding = encoder(variant)
assert (encoding == 2)
def __getitem__(self, idx):
"""Get Variant instance in location.
Args:
idx: Variant index
Returns:
Variant instance
"""
row = self._dataframe.iloc[idx]
# Build sample data by iterating through FORMAT columns.
samples = []
zygosities = []
format_keys = sorted(self._format_vcf_key_counts.keys())
for call in self._sample_names:
call_data = []
for k in format_keys:
count = self._format_vcf_key_counts[k]
if count == 1:
call_data.append(row["{}_{}".format(call, k)])
else:
for i in range(count):
call_data.append(row["{}_{}_{}".format(call, k, i)])
samples.append(call_data)
zyg_col = "{}_zyg".format(call)
if zyg_col in row:
zygosities.append(VariantZygosity(row[zyg_col]))
# Build filter data by iterating over all saved FILTER keys.
var_filter = []
for k in self._filter_vcf_keys:
if row["FILTER_{}".format(k)]:
var_filter.append(k)
# Build info data by iterating over all saved INFO keys.
info = {}
for k, count in self._info_vcf_key_counts.items():
if count == 1:
info[k] = row["{}".format(k)]
else:
vals = []
for i in range(count):
vals.append(row["{}_{}".format(k, i)])
info[k] = vals
variant = Variant(chrom=row["chrom"],
pos=row["start_pos"],
id=row["id"],
ref=row["ref"],
allele=row["alt"],
quality=row["quality"],
filter=(var_filter if var_filter else None),
info=info,
format=format_keys,
type=VariantType(row["variant_type"]),
samples=samples,
zygosity=zygosities,
vcf=self._vcf,
bams=self._bams)
return variant