def extract_vcf(gwas_file,gwas_id):
# Temporary output file:
tempDir=os.getenv('tmpDir',"/tmp/")
tempout = os.path.join(tempDir,gwas_id)+"."+str(uuid.uuid4())
print("Processing vcf to", tempout)
# Check if Sample size is available as a column
vcf_in = VariantFile(gwas_file)
sample = list(vcf_in.header.samples)[0]
availcols = next(vcf_in.fetch()).format.keys()
vcf_in.seek(0)
if 'SS' in availcols:
cmd = "bcftools query -f'%CHROM %POS %ID %ALT %REF[ %AF %ES %SE %LP %SS]\n' " + gwas_file + "| awk '{print $1, $2, $3, $4, $5, $6, $7, $8, 10^-$9, $10}' | grep -v inf | gzip -c > " + tempout
#print(cmd)
subprocess.call(cmd, shell=True)
print("Done")
return tempout
global_fields = [x for x in vcf_in.header.records if x.key == "SAMPLE"][0]
if 'TotalControls' in global_fields.keys() and 'TotalCases' in global_fields.keys():
SS = float(global_fields['TotalControls']) + float(global_fields['TotalCases'])
elif 'TotalControls' in global_fields.keys():
SS = float(global_fields['TotalControls'])
else:
SS = '.'
cmd = "bcftools query -f'%CHROM %POS %ID %ALT %REF[ %AF %ES %SE %LP]\n' " + gwas_file + "| awk '{print $1, $2, $3, $4, $5, $6, $7, $8, 10^-$9, \"" + str(SS) + "\"}' | grep -v inf | gzip -c > " + tempout
subprocess.call(cmd, shell=True)
print("Done")
return tempout
def read_vcf(fh, alleles, slh=None):
vcf_in = VariantFile(fh)
sample = list(vcf_in.header.samples)[0]
availcols = next(vcf_in.fetch()).format.keys()
vcf_in.seek(0)
# Check if sample size info is in header
global_fields = [x for x in vcf_in.header.records if x.key == "SAMPLE"][0]
if alleles:
dtype_dict = {'SNP': str, 'Z': float, 'N': float, 'A1': str, 'A2': str}
usecols = list(dtype_dict.keys())
# Read in data
if 'SS' in availcols:
o = [[
rec.id,
rec.samples[sample]['ES'][0] / rec.samples[sample]['SE'][0],
rec.samples[sample]['SS'][0], rec.alts[0], rec.ref
] for rec in vcf_in.fetch()]
N = pd.Series([x[2] for x in o], dtype='float')
else:
o = [[
rec.id,
rec.samples[sample]['ES'][0] / rec.samples[sample]['SE'][0],
rec.alts[0], rec.ref
] for rec in vcf_in.fetch()]
if 'TotalControls' in global_fields.keys(
) and 'TotalCases' in global_fields.keys():
N = pd.Series([
float(global_fields['TotalControls']) +
float(global_fields['TotalCases'])
] * len(o),
dtype='float')
elif 'TotalControls' in global_fields.keys():
N = pd.Series([float(global_fields['TotalControls'])] * len(o),
dtype='float')
else:
N = pd.Series([np.NaN] * len(o), dtype='float')
p = pd.DataFrame({
'SNP':
pd.Series([x[0] for x in o], dtype='str'),
'Z':
pd.Series([x[1] for x in o], dtype='float'),
'N':
N,
'A1':
pd.Series([x[2 + int('SS' in availcols)] for x in o], dtype='str'),
'A2':
pd.Series([x[3 + int('SS' in availcols)] for x in o], dtype='str')
})
else:
dtype_dict = {'SNP': str, 'Z': float, 'N': float}
usecols = list(dtype_dict.keys())
if 'SS' in availcols:
o = [[
rec.id,
rec.samples[sample]['ES'][0] / rec.samples[sample]['SE'][0],
rec.samples[sample]['SS'][0]
] for rec in vcf_in.fetch()]
N = pd.Series([x[2] for x in o], dtype='float')
else:
o = [[
rec.id,
rec.samples[sample]['ES'][0] / rec.samples[sample]['SE'][0]
] for rec in vcf_in.fetch()]
if 'TotalControls' in global_fields.keys(
) and 'TotalCases' in global_fields.keys():
N = pd.Series([
float(global_fields['TotalControls']) +
float(global_fields['TotalCases'])
] * len(o),
dtype='float')
elif 'TotalControls' in global_fields.keys():
N = pd.Series([float(global_fields['TotalControls'])] * len(o),
dtype='float')
else:
N = pd.Series([np.NaN] * len(o), dtype='float')
p = pd.DataFrame({
'SNP': pd.Series([x[0] for x in o], dtype='str'),
'Z': pd.Series([x[1] for x in o], dtype='float'),
'N': N
})
vcf_in.close()
if slh is not None:
compression = get_compression(slh)
sl = []
if compression == "gzip":
try:
with gzip.open(slh) as f:
for line in f:
sl.append(line.strip())
except (AttributeError, ValueError) as e:
raise ValueError('Improperly formatted snplist file: ' +
str(e.args))
else:
try:
with open(slh) as f:
for line in f:
sl.append(line.strip())
except (AttributeError, ValueError) as e:
raise ValueError('Improperly formatted snplist file: ' +
str(e.args))
f.close()
p = p.loc[p['SNP'].isin(sl)]
return (p)
