def test_figure(self):
from idiva.stat.vcf_to_fisher import figure_pvalues
for kind in ["head", "full"]:
workdir = basepath / kind
vcf = unlist1(workdir.glob("*.vcf.gz"))
with ReadVCF.open(vcf) as vcf:
for px in figure_pvalues(vcf):
px.f.savefig(
(workdir /
px.info['name proposal']).with_suffix(".png"))
def post(vcf_file: Path):
log.info("=> Entering the postprocessing stage.")
from idiva.stat.vcf_to_fisher import figure_pvalues
from idiva.io.vcf import SEP
with ReadVCF.open(vcf_file) as vcf:
for px in figure_pvalues(vcf):
file = vcf_file.parent / px.info['name proposal']
log.info(F"Saving figure and data to {file}.* .")
px.f.savefig(file.with_suffix(".png"))
df: pandas.DataFrame = px.info['df']
df.to_csv(file.with_suffix(".csv"), sep=SEP)
def translate_vcf(self, vcf) -> pd.DataFrame:
"""
Returns a dataframe that contains the following features from a vcf file
CHROM, POS, ID, VAR
"""
cache = (Path(__file__).parent.parent.parent.parent /
"input/download_cache").resolve()
assert cache.is_dir()
with ReadVCF.open(vcf) as reader:
with seek_then_rewind(reader.fd,
seek=reader.dataline_start_pos) as fd:
dataframe = pd.read_csv(fd,
sep='\t',
usecols=range(
len(DataHandler.INIT_COLS)),
header=None,
names=DataHandler.INIT_COLS,
dtype={
'CHROM': np.int,
'POS': np.int,
'ID': np.str,
'REF': np.str,
'ALT': np.str
})
# Check if ALT contains only one value or several values seperated by ','
assert (len([
uni for uni in dataframe['ALT'].unique().tolist()
if ',' in uni
]) == 0)
# store only SNP variants
dataframe = dataframe[dataframe['REF'].apply(
lambda x: {x}.issubset({'A', 'C', 'G', 'T'}))]
dataframe = dataframe[dataframe['ALT'].apply(
lambda x: {x}.issubset({'A', 'C', 'G', 'T'}))]
# Check if only SNP
for ref in dataframe['REF']:
assert (len(ref) == 1)
for alt in dataframe['ALT']:
assert (len(alt) == 1)
assert (set(dataframe['REF'].unique().tolist()).issubset(
{'A', 'C', 'G', 'T'}))
assert (set(dataframe['ALT'].unique().tolist()).issubset(
{'A', 'C', 'G', 'T'}))
dataframe['CHROM'] = pd.to_numeric(dataframe[['CHROM']].apply(
self.translate_chrom, axis=1))
dataframe = self.encode_ref_alt(dataframe)
dataframe.drop_duplicates()
# TODO: same CHROM POS and rsID but not same REF & ALT
# consequence of real world data (Kjong Nov 30)
# => identify samples by CHROM, POS and VAR
# same CHROM rsID REF ALT but not same POS
# => rsIDs are not completely unique !
# Ignore rsID (Kjong Nov 23)
"""
print(len(dataframe['ID'].unique().tolist()))
print(len(dataframe['ID'].tolist()))
CHROM POS ID REF ALT VAR
56638 17 1649616 rs544719440 A G 2
576511 17 19159733 rs540831825 A G 2
717227 17 27196477 rs202111951 T C 10
919995 17 34642425 rs568794696 C A 3
2105598 17 77663493 rs148485780 C T 5
CHROM POS ID REF ALT VAR
56637 17 1649616 rs544719440 A C 1
576510 17 19159733 rs540831825 A C 1
717226 17 27196477 rs202111951 T A 9
919587 17 34540858 rs568794696 C A 3
2105592 17 77663435 rs148485780 C T 5
"""
return dataframe
dataframe.to_csv(file_path, sep='\t', index=False)
return dataframe
if __name__ == '__main__':
dh = DataHandler()
print(dh.preprocess_clinvar())
cache = (Path(__file__).parent.parent.parent.parent /
"input/download_cache").resolve()
assert cache.is_dir()
with ReadVCF.open(cache / 'control_v2.vcf') as ctrl_vcf:
with ReadVCF.open(cache / 'case_processed_v2.vcf') as case_vcf:
test_set = dh.create_test_set_v2(
case_vcf=case_vcf,
ctrl_vcf=ctrl_vcf,
)
print(test_set)
"""
print(dataframe)
cache = (Path(__file__).parent.parent.parent.parent / "input/download_cache").resolve()
assert cache.is_dir()
file_path = str(cache) + "/cadd_full.vcf"
dataframe = dataframe.fillna(value=".")