def maker_clinvar() -> pandas.DataFrame:
from idiva.db import clinvar_open
from idiva.io import ReadVCF
from idiva.db.clinvar import clinvar_to_df
with clinvar_open(which=which) as fd:
return clinvar_to_df(ReadVCF(fd))
def test_open_read_vcf_meta(self):
from idiva.db import clinvar_open
from idiva.io import ReadVCF
with clinvar_open(which='vcf_37') as fd:
vcf = ReadVCF(fd)
assert not hasattr(vcf, "sample_ids")
print(vcf.header)
raise NotImplementedError
def test_howto(self):
from idiva.db import clinvar_open
from idiva.io.vcf import ReadVCF
with clinvar_open() as fd:
vcf = ReadVCF(fd)
vcf.meta
for dataline in vcf:
dataline
def test_open_read_manual(self):
from idiva.db import clinvar_open
with clinvar_open() as fd:
self.assertIsInstance(fd, io.TextIOBase)
reference = [
'##fileformat=VCFv4.1', '##fileDate=2020-11-07',
'##source=ClinVar'
]
candidate = [fd.readline().strip() for __ in range(3)]
self.assertListEqual(reference, candidate)
def maker_clinvar() -> pd.DataFrame:
"""
creates the clinvar dataframe
"""
from idiva.db import clinvar_open
from idiva.io import ReadVCF
from idiva.db.clinvar import clinvar_to_df
log.info('Making clinvar df.')
with clinvar_open(which=clinvar_file) as fd:
return clinvar_to_df(ReadVCF(fd))
def test_clinvar_df(self):
from idiva.db import clinvar_open
from idiva.io import ReadVCF
from idiva.db.clinvar import clinvar_to_df
with clinvar_open(which='vcf_37') as fd:
df = clinvar_to_df(ReadVCF(fd))
self.assertEqual(len(df), REF_LENGTHS['clinvar_df'])
self.assertTrue(all(
df.loc[df['CLNVC'] == 'single_nucleotide_variant']))
self.assertFalse(df['CLNVC'].isnull().values.any())
self.assertTrue('OMIM_id' in df.columns)
def test_length_clinvar(self):
from idiva.db import clinvar_open
from idiva.io import ReadVCF
from tqdm import tqdm
with clinvar_open(which='vcf_37') as fd:
vcf = ReadVCF(fd)
for idx, line in tqdm(enumerate(vcf.datalines),
postfix='reading clinvar file'):
pass
self.assertEqual(idx, REF_LENGTHS['clinvar_csv'])
def test_open_read_vcf_datalines(self):
from idiva.db import clinvar_open
from idiva.io import ReadVCF
with clinvar_open(which='vcf_37') as fd:
vcf = ReadVCF(fd)
reference = [
"1 865568 846933 G A . . ALLELEID=824438;CLNDISDB=MedGen:CN517202;CLNDN=not_provided;CLNHGVS=NC_000001.10:g.865568G>A;CLNREVSTAT=criteria_provided,_single_submitter;CLNSIG=Uncertain_significance;CLNVC=single_nucleotide_variant;CLNVCSO=SO:0001483;GENEINFO=SAMD11:148398;MC=SO:0001583|missense_variant;ORIGIN=1",
"1 865583 972363 C T . . ALLELEID=959431;CLNDISDB=MedGen:CN517202;CLNDN=not_provided;CLNHGVS=NC_000001.10:g.865583C>T;CLNREVSTAT=criteria_provided,_single_submitter;CLNSIG=Uncertain_significance;CLNVC=single_nucleotide_variant;CLNVCSO=SO:0001483;GENEINFO=SAMD11:148398;MC=SO:0001583|missense_variant;ORIGIN=1",
"1 865628 789256 G A . . AF_ESP=0.00347;AF_EXAC=0.00622;AF_TGP=0.00280;ALLELEID=707587;CLNDISDB=MedGen:CN517202;CLNDN=not_provided;CLNHGVS=NC_000001.10:g.865628G>A;CLNREVSTAT=criteria_provided,_single_submitter;CLNSIG=Likely_benign;CLNVC=single_nucleotide_variant;CLNVCSO=SO:0001483;GENEINFO=SAMD11:148398;MC=SO:0001583|missense_variant;ORIGIN=1;RS=41285790",
]
from idiva.io.vcf import RawDataline
datalines: typing.List[RawDataline]
datalines = list(at_most_n(vcf, n=len(reference)))
self.assertIsInstance(datalines[0], RawDataline)
candidate = list(map(str, datalines))
self.assertListEqual(reference, candidate)
self.assertEqual(datalines[0].ref, 'G')
self.assertEqual(datalines[1].ref, 'C')
self.assertEqual(datalines[2].ref, 'G')
def test_open(self):
from idiva.db import clinvar_open
with clinvar_open() as fd:
self.assertIsInstance(fd, io.TextIOBase)