def test_condition():
V = variants('fixture/sample.vcf')
eq_(9, len(V))
C = calldata('fixture/sample.vcf', condition=V['FILTER']['PASS'])
eq_(5, len(C))
Vf = variants('fixture/sample.vcf', condition=V['FILTER']['PASS'])
eq_(5, len(Vf))
def readVcf(inFile, logDebug):
log.info("reading the VCF file")
if logDebug:
vcf = vcfnp.variants(inFile, cache=False).view(np.recarray)
vcfD = vcfnp.calldata_2d(inFile, cache=False).view(np.recarray)
else:
sys.stderr = StringIO.StringIO()
vcf = vcfnp.variants(inFile, cache=False).view(np.recarray)
vcfD = vcfnp.calldata_2d(inFile, cache=False).view(np.recarray)
sys.stderr = sys.__stderr__
DPthres = np.mean(vcfD.DP[np.where(vcfD.DP > 0)[0]]) * 4
DPmean = DPthres / 4
snpCHROM = np.char.replace(np.core.defchararray.lower(
vcf.CHROM), "chr", "") ## Should take care of all possible chr names
snpsREQ = np.where((vcfD.is_called[:, 0]) & (vcf.QUAL > 30) & (vcf.DP > 0)
& (vcf.DP < DPthres) & (np.char.isdigit(snpCHROM)))[0]
snpCHR = np.array(snpCHROM[snpsREQ]).astype("int8")
snpPOS = np.array(vcf.POS[snpsREQ])
try:
snpGT = np.array(vcfD.GT[snpsREQ, 0])
except AttributeError:
die("input VCF file doesnt have required GT field")
try:
snpPL = vcfD.PL[snpsREQ, 0]
snpWEI = np.copy(snpPL)
snpWEI = snpWEI.astype(float)
snpWEI = snpWEI / (-10)
snpWEI = np.exp(snpWEI)
except AttributeError:
snpBinary = parseGT(snpGT)
snpWEI = np.ones((len(snpsREQ), 3)) ## for h**o and het
snpWEI[np.where(snpBinary != 0), 0] = 0
snpWEI[np.where(snpBinary != 1), 2] = 0
snpWEI[np.where(snpBinary != 2), 1] = 0
return (DPmean, snpCHR, snpPOS, snpGT, snpWEI)
def test_condition():
V = variants("fixture/sample.vcf")
eq_(9, len(V))
C = calldata("fixture/sample.vcf", condition=V["FILTER"]["PASS"])
eq_(5, len(C))
Vf = variants("fixture/sample.vcf", condition=V["FILTER"]["PASS"])
eq_(5, len(Vf))
def test_missing_info_definition():
# INFO field DP not declared in VCF header
V = variants('fixture/test14.vcf', fields=['DP'])
eq_('14', V[2]['DP']) # default is string
V = variants('fixture/test14.vcf', fields=['DP'], vcf_types={'DP':'Integer'})
eq_(14, V[2]['DP'])
# what about a field which isn't present at all?
V = variants('fixture/test14.vcf', fields=['FOO'])
eq_('.', V[2]['FOO']) # default missing value for string field
def test_condition():
v = variants('fixture/sample.vcf')
eq_(9, len(v))
c = calldata('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(c))
i = info('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(i))
vf = variants('fixture/sample.vcf', condition=v['FILTER']['PASS'])
eq_(5, len(vf))
def test_missing_info_definition():
# INFO field DP not declared in VCF header
V = variants("fixture/test14.vcf", fields=["DP"])
eq_("14", V[2]["DP"]) # default is string
V = variants("fixture/test14.vcf", fields=["DP"], vcf_types={"DP": "Integer"})
eq_(14, V[2]["DP"])
# what about a field which isn't present at all?
V = variants("fixture/test14.vcf", fields=["FOO"])
eq_("", V[2]["FOO"]) # default missing value for string field
def test_variants_transformers():
def _test(V):
eq_("STOP_GAINED", V["EFF"]["Effect"][0])
eq_("HIGH", V["EFF"]["Effect_Impact"][0])
eq_("NONSENSE", V["EFF"]["Functional_Class"][0])
eq_("Cag/Tag", V["EFF"]["Codon_Change"][0])
eq_("Q236*", V["EFF"]["Amino_Acid_Change"][0])
eq_(749, V["EFF"]["Amino_Acid_Length"][0])
eq_("NOC2L", V["EFF"]["Gene_Name"][0])
eq_(".", V["EFF"]["Transcript_BioType"][0])
eq_(1, V["EFF"]["Gene_Coding"][0])
eq_("NM_015658", V["EFF"]["Transcript_ID"][0])
eq_(-1, V["EFF"]["Exon"][0])
eq_("NON_SYNONYMOUS_CODING", V["EFF"]["Effect"][1])
eq_("MODERATE", V["EFF"]["Effect_Impact"][1])
eq_("MISSENSE", V["EFF"]["Functional_Class"][1])
eq_("gTt/gGt", V["EFF"]["Codon_Change"][1])
eq_("V155G", V["EFF"]["Amino_Acid_Change"][1])
eq_(-1, V["EFF"]["Amino_Acid_Length"][1])
eq_("PF3D7_0108900", V["EFF"]["Gene_Name"][1])
eq_(".", V["EFF"]["Transcript_BioType"][1])
eq_(-1, V["EFF"]["Gene_Coding"][1])
eq_("rna_PF3D7_0108900-1", V["EFF"]["Transcript_ID"][1])
eq_(1, V["EFF"]["Exon"][1])
eq_(".", V["EFF"]["Effect"][2])
eq_(".", V["EFF"]["Effect_Impact"][2])
eq_(".", V["EFF"]["Functional_Class"][2])
eq_(".", V["EFF"]["Codon_Change"][2])
eq_(".", V["EFF"]["Amino_Acid_Change"][2])
eq_(-1, V["EFF"]["Amino_Acid_Length"][2])
eq_(".", V["EFF"]["Gene_Name"][2])
eq_(".", V["EFF"]["Transcript_BioType"][2])
eq_(-1, V["EFF"]["Gene_Coding"][2])
eq_(".", V["EFF"]["Transcript_ID"][2])
eq_(-1, V["EFF"]["Exon"][2])
V = variants(
"fixture/test12.vcf",
dtypes={"EFF": EFF_DEFAULT_DTYPE},
arities={"EFF": 1},
transformers={"EFF": eff_default_transformer()},
)
_test(V)
# test EFF is included in defaults
V = variants("fixture/test12.vcf")
_test(V)
def test_error_handling():
# try to open a directory
vcf_fn = '.'
with assert_raises(ValueError):
a = vcfnp.variants(vcf_fn)
# try to open a file that doesn't exist
vcf_fn = 'doesnotexist'
with assert_raises(ValueError):
a = vcfnp.variants(vcf_fn)
# file is nothing like a VCF (has no header etc.)
vcf_fn = 'fixture/test48a.vcf'
with assert_raises(RuntimeError):
a = vcfnp.variants(vcf_fn)
def test_svlen():
# V = variants('fixture/test13.vcf').view(np.recarray)
# assert hasattr(V, 'svlen')
# eq_(0, V.svlen[0])
# eq_(1, V.svlen[1])
# eq_(-1, V.svlen[2])
# eq_(3, V.svlen[3])
# eq_(3, V.svlen[4])
V = variants("fixture/test13.vcf", arities={"svlen": 2}).view(np.recarray)
def test_variants():
a = variants('fixture/sample.vcf', arities={'ALT': 2})
print repr(a)
eq_(9, len(a))
eq_('19', a[0]['CHROM'])
eq_(111, a[0]['POS'])
eq_('rs6054257', a[2]['ID'])
eq_('A', a[0]['REF'])
eq_('ATG', a[8]['ALT'][1])
eq_(10.0, a[1]['QUAL'])
eq_(True, a[2]['FILTER']['PASS'])
eq_(False, a[3]['FILTER']['PASS'])
eq_(True, a[3]['FILTER']['q10'])
eq_(2, a[0]['num_alleles'])
eq_(False, a[5]['is_snp'])
def build_arrays(vcf_fn, region, samples=None, force=False):
variants_array_fn = vcf_fn + '.' + region.replace('-:', '_') + '.variants.npy'
if force or not os.path.exists(variants_array_fn):
print >>sys.stderr, 'building', variants_array_fn
V = vcfnp.variants(vcf_fn, region=region, progress=20000)
np.save(variants_array_fn, V)
else:
print >>sys.stderr, 'skipping', variants_array_fn
info_array_fn = vcf_fn + '.' + region.replace('-:', '_') + '.info.npy'
if force or not os.path.exists(info_array_fn):
print >>sys.stderr, 'building', info_array_fn
I = vcfnp.info(vcf_fn, region=region, progress=20000, fields=['NS', 'UQ', 'CODING', 'DP', 'AD'], vcf_types={'DP': 'Integer', 'AD': 'Integer'}, arities={'AD': 2})
np.save(info_array_fn, I)
else:
print >>sys.stderr, 'skipping', info_array_fn
def run_vcfnp(sample='7G8', file_prefix='WG'):
vcf_fn = INDIVIDAL_VALIDATION_SAMPLES_VCF_FORMAT % (file_prefix, sample)
v = vcfnp.variants(
vcf_fn=vcf_fn,
progress=10000,
arities={
'ALT': 2,
'AF': 2,
'AC': 2,
'MLEAF': 2,
'MLEAC': 2,
'RPA': 3
},
dtypes={
'REF': 'a400',
'ALT': 'a400',
'RegionType': 'a25',
'VariantType': 'a40',
'RU': 'a40',
'set': 'a40',
'SNPEFF_AMINO_ACID_CHANGE':'a20',
'SNPEFF_CODON_CHANGE':'a20',
'SNPEFF_EFFECT':'a33',
'SNPEFF_EXON_ID':'a2',
'SNPEFF_FUNCTIONAL_CLASS':'a8',
'SNPEFF_GENE_BIOTYPE':'a14',
'SNPEFF_GENE_NAME':'a20',
'SNPEFF_IMPACT':'a8',
'SNPEFF_TRANSCRIPT_ID':'a20',
'VariantType':'a60',
'culprit':'a14',
},
cache=True
)
c = vcfnp.calldata_2d(
vcf_fn=vcf_fn,
progress=10000,
fields=['GT', 'AD'],
arities={'AD': 3},
cache=True,
)
print(sample, max(v['num_alleles']), max([len(x) for x in v['REF']]))
return(v, c)
def test_variants_transformers():
V = variants('fixture/test12.vcf',
dtypes={'EFF': EFF_DEFAULT_DTYPE},
arities={'EFF': 1},
transformers={'EFF': eff_default_transformer()})
eq_('STOP_GAINED', V['EFF']['Effect'][0])
eq_('HIGH', V['EFF']['Effect_Impact'][0])
eq_('NONSENSE', V['EFF']['Functional_Class'][0])
eq_('Cag/Tag', V['EFF']['Codon_Change'][0])
eq_('Q236*', V['EFF']['Amino_Acid_Change'][0])
eq_(749, V['EFF']['Amino_Acid_Length'][0])
eq_('NOC2L', V['EFF']['Gene_Name'][0])
eq_('.', V['EFF']['Transcript_BioType'][0])
eq_(1, V['EFF']['Gene_Coding'][0])
eq_('NM_015658', V['EFF']['Transcript_ID'][0])
eq_(-1, V['EFF']['Exon'][0])
eq_('NON_SYNONYMOUS_CODING', V['EFF']['Effect'][1])
eq_('MODERATE', V['EFF']['Effect_Impact'][1])
eq_('MISSENSE', V['EFF']['Functional_Class'][1])
eq_('gTt/gGt', V['EFF']['Codon_Change'][1])
eq_('V155G', V['EFF']['Amino_Acid_Change'][1])
eq_(-1, V['EFF']['Amino_Acid_Length'][1])
eq_('PF3D7_0108900', V['EFF']['Gene_Name'][1])
eq_('.', V['EFF']['Transcript_BioType'][1])
eq_(-1, V['EFF']['Gene_Coding'][1])
eq_('rna_PF3D7_0108900-1', V['EFF']['Transcript_ID'][1])
eq_(1, V['EFF']['Exon'][1])
eq_('.', V['EFF']['Effect'][2])
eq_('.', V['EFF']['Effect_Impact'][2])
eq_('.', V['EFF']['Functional_Class'][2])
eq_('.', V['EFF']['Codon_Change'][2])
eq_('.', V['EFF']['Amino_Acid_Change'][2])
eq_(-1, V['EFF']['Amino_Acid_Length'][2])
eq_('.', V['EFF']['Gene_Name'][2])
eq_('.', V['EFF']['Transcript_BioType'][2])
eq_(-1, V['EFF']['Gene_Coding'][2])
eq_('.', V['EFF']['Transcript_ID'][2])
eq_(-1, V['EFF']['Exon'][2])
def test_variants():
a = variants("fixture/sample.vcf", arities={"ALT": 2, "AC": 2})
print repr(a)
eq_(9, len(a))
eq_("19", a[0]["CHROM"])
eq_(111, a[0]["POS"])
eq_("rs6054257", a[2]["ID"])
eq_("A", a[0]["REF"])
eq_("ATG", a[8]["ALT"][1])
eq_(10.0, a[1]["QUAL"])
eq_(True, a[2]["FILTER"]["PASS"])
eq_(False, a[3]["FILTER"]["PASS"])
eq_(True, a[3]["FILTER"]["q10"])
eq_(2, a[0]["num_alleles"])
eq_(False, a[5]["is_snp"])
# INFO fields
eq_(3, a[2]["NS"])
eq_(0.5, a[2]["AF"])
eq_(True, a[2]["DB"])
eq_((3, 1), tuple(a[6]["AC"]))
def work(self):
import vcfnp
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
variants = vcfnp.variants(self.input().path)
calldata_2d = vcfnp.calldata_2d(self.input().path)
var = np.logical_and(variants['ALT'] != b'<NON_REF>',
variants['DP'] > self.DP_thresh)
counts = np.sort(calldata_2d['AD'][var][:, 0, :], axis=1)[:, ::-1]
freqs = counts / calldata_2d['DP'][var]
third = 1 - np.sum(freqs, axis=1)
df = pd.DataFrame(np.hstack((freqs, third.reshape((-1, 1)))))
df[df == 0] = float('nan')
df.hist(sharex=True, sharey=True, range=(0, 1), bins=20)
plt.gcf().suptitle(self.library, fontsize=20)
plt.gcf().text(0.5, 0.04, 'Allele frequency', ha='center')
plt.gcf().text(0.02, 0.5, 'Counts', va='center', rotation='vertical')
plt.gcf().savefig(self.output().path)
def test_caching():
vcf_fn = "fixture/sample.vcf.gz"
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="variants")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = variants(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="calldata")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = calldata(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
cache_fn = vcfnp._mk_cache_fn(vcf_fn, array_type="calldata_2d")
if os.path.exists(cache_fn):
os.remove(cache_fn)
A = calldata_2d(vcf_fn, cache=True, verbose=True)
A2 = np.load(cache_fn)
assert np.all(A == A2)
def run_vcfnp_all(chrom='Pf3D7_01_v3'):
vcf_fn = OUTGROUP_VCF_FORMAT % chrom
v = vcfnp.variants(
vcf_fn=vcf_fn,
progress=10000,
arities={
'ALT': 6,
'AF': 6,
'AC': 6,
'MLEAF': 6,
'MLEAC': 6,
'RPA': 7
},
dtypes={
# 'REF': 'a100',
# 'ALT': 'a100',
'RegionType': 'a25',
'VariantType': 'a40',
'RU': 'a40',
'set': 'a40',
'SNPEFF_AMINO_ACID_CHANGE':'a20',
'SNPEFF_CODON_CHANGE':'a20',
'SNPEFF_EFFECT':'a33',
'SNPEFF_EXON_ID':'a2',
'SNPEFF_FUNCTIONAL_CLASS':'a8',
'SNPEFF_GENE_BIOTYPE':'a14',
'SNPEFF_GENE_NAME':'a20',
'SNPEFF_IMPACT':'a8',
'SNPEFF_TRANSCRIPT_ID':'a20',
'VariantType':'a60',
'culprit':'a14',
},
cache=True,
cachedir=FULL_NPY_FORMAT % chrom
)
return(0)
def run_vcfnp(
annotated_vcf_fn = '/lustre/scratch110/malaria/rp7/Pf3k/release4_candidate/consensus_alignment/nucmer/7G8.3d7coordinates.annoatated.vcf'
):
v = vcfnp.variants(
vcf_fn=annotated_vcf_fn,
progress=10000,
arities={
'ALT': 2,
'AF': 2,
'AC': 2,
'MLEAF': 2,
'MLEAC': 2,
'RPA': 3
},
dtypes={
'REF': 'a400',
'ALT': 'a400',
'RegionType': 'a25',
'VariantType': 'a40',
'RU': 'a40',
'set': 'a40',
'SNPEFF_AMINO_ACID_CHANGE':'a20',
'SNPEFF_CODON_CHANGE':'a20',
'SNPEFF_EFFECT':'a33',
'SNPEFF_EXON_ID':'a2',
'SNPEFF_FUNCTIONAL_CLASS':'a8',
'SNPEFF_GENE_BIOTYPE':'a14',
'SNPEFF_GENE_NAME':'a20',
'SNPEFF_IMPACT':'a8',
'SNPEFF_TRANSCRIPT_ID':'a20',
'VariantType':'a60',
'culprit':'a14',
},
cache=True
)
return(v)
def test_error_handling():
# try to open a directory
vcf_fn = '.'
with assert_raises(ValueError):
vcfnp.variants(vcf_fn)
# try to open a file that doesn't exist
vcf_fn = 'doesnotexist'
with assert_raises(ValueError):
vcfnp.variants(vcf_fn)
# file is nothing like a VCF (has no header etc.)
vcf_fn = 'fixture/test48a.vcf'
with assert_raises(RuntimeError):
vcfnp.variants(vcf_fn)
# file has mode sample columns than in header row
vcf_fn = 'fixture/test48b.vcf'
with assert_raises(RuntimeError):
vcfnp.calldata(vcf_fn)
from __future__ import print_function, division
import numpy as np
import matplotlib.pyplot as plt
import vcfnp
vcfnp.__version__
filename = 'fixture/sample.vcf'
# load data from fixed fields (including INFO)
v = vcfnp.variants(filename, cache=True).view(np.recarray)
# print some simple variant metrics
print('found %s variants (%s SNPs)' % (v.size, np.count_nonzero(v.is_snp)))
print('QUAL mean (std): %s (%s)' % (np.mean(v.QUAL), np.std(v.QUAL)))
# plot a histogram of variant depth
fig = plt.figure(1)
ax = fig.add_subplot(111)
ax.hist(v.DP)
ax.set_title('DP histogram')
ax.set_xlabel('DP')
plt.show()
# load data from sample columns
c = vcfnp.calldata_2d(filename, cache=True).view(np.recarray)
# print some simple genotype metrics
count_phased = np.count_nonzero(c.is_phased)
count_variant = np.count_nonzero(np.any(c.genotype > 0, axis=2))
count_missing = np.count_nonzero(~c.is_called)
print('calls (phased, variant, missing): %s (%s, %s, %s)'
def readVcf(inFile): bvcf = vcfnp.variants(inFile, cache=True).view(np.recarray) bvcfD = vcfnp.calldata_2d(inFile, cache=True).view(np.recarray) return(bvcf, bvcfD)
def test_override_vcf_types():
V = variants("fixture/test4.vcf")
eq_(0, V["MQ0FractionTest"][2])
V = variants("fixture/test4.vcf", vcf_types={"MQ0FractionTest": "Float"})
assert_almost_equal(0.03, V["MQ0FractionTest"][2])
def test_variants_slice():
a = variants("fixture/sample.vcf.gz")
eq_("rs6054257", a["ID"][2])
a = variants("fixture/sample.vcf.gz", slice=(0, None, 2))
eq_("rs6054257", a["ID"][1])
def test_variants_exclude_fields():
a = variants("fixture/sample.vcf", exclude_fields=["ID", "FILTER"])
assert "CHROM" in a.dtype.names
assert "ID" not in a.dtype.names
assert "FILTER" not in a.dtype.names
def test_variants_count():
a = variants("fixture/sample.vcf", count=3)
eq_(3, len(a))
from compiler.ast import flatten
import numpy
def mkdir_p(path):
try:
os.makedirs(path)
except OSError as exc: # Python >2.5
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else: raise
vcf_file = "ag1000g.phase1.AR1.Y_unplaced.PASS.vcf.gz"
print 'Parsing variants'
variants = vcfnp.variants(vcf_file)
#Recursivly get the names of the columns
def names_from_dtype(dtype, path=''):
if dtype.names:
#dtypes don't support iter.... yes. I know.
dtype_as_list = [dtype[i] for i in xrange(len(dtype))]
return [names_from_dtype(inner_dtype, path+'.'+name if path else name)
for name, inner_dtype in zip(dtype.names, dtype_as_list)]
elif dtype.kind == 'V': #a vector with no names! We will have to just number them...
return [path+'.'+str(i) if path else str(i) for i in range(dtype.shape[0])]
else:
return path
def flatten_numpy_line(line):
for entry in line:
def profile():
a = vcfnp.variants(sys.argv[1], count=int(sys.argv[2]))
def test_variants_slice():
a = variants('fixture/sample.vcf.gz')
eq_('rs6054257', a['ID'][2])
a = variants('fixture/sample.vcf.gz', slice=(0, None, 2))
eq_('rs6054257', a['ID'][1])
def test_explicit_pass_definition():
# explicit PASS FILTER definition
V = variants("fixture/test16.vcf")
def profile():
a = vcfnp.variants(sys.argv[1], count=int(sys.argv[2]))
def test_duplicate_field_definitions():
V = variants("fixture/test10.vcf")
# should not raise, but print useful message to stderr
C = calldata("fixture/test10.vcf")
def profile():
v = vcfnp.variants(sys.argv[1], count=int(sys.argv[2]))
c = vcfnp.calldata(sys.argv[1], condition=v['FILTER']['PASS'])
def test_variants_flatten_filter():
a = variants("fixture/sample.vcf", flatten_filter=True)
eq_(True, a[2]["FILTER_PASS"])
eq_(False, a[3]["FILTER_PASS"])
eq_(True, a[3]["FILTER_q10"])
from compiler.ast import flatten
import numpy
def mkdir_p(path):
try:
os.makedirs(path)
except OSError as exc: # Python >2.5
if exc.errno == errno.EEXIST and os.path.isdir(path):
pass
else: raise
vcf_file = "ag1000g.phase1.AR1.Y_unplaced.PASS.vcf.gz"
print 'Parsing variants'
variants = vcfnp.variants(vcf_file)
#Recursivly get the names of the columns
def names_from_dtype(dtype, path=''):
if dtype.names:
#dtypes don't support iter.... yes. I know.
dtype_as_list = [dtype[i] for i in xrange(len(dtype))]
return [names_from_dtype(inner_dtype, path+'.'+name if path else name)
for name, inner_dtype in zip(dtype.names, dtype_as_list)]
elif dtype.kind == 'V': #a vector with no names! We will have to just number them...
return [path+'.'+str(i) if path else str(i) for i in range(dtype.shape[0])]
else:
return path
def flatten_numpy_line(line):
for entry in line:
def test_variants_region():
a = variants("fixture/sample.vcf.gz", region="20")
eq_(6, len(a))
inOptions.add_option("-d", "--hdf5_file", dest="hdf5File", help="Path to SNP matrix given in binary hdf5 file", type="string")
inOptions.add_option("-e", "--hdf5_acc_file", dest="hdf5accFile", help="Path to SNP matrix given in binary hdf5 file", type="string")
inOptions.add_option("-o", "--output", dest="outFile", help="Output file with the probability scores", type="string")
inOptions.add_option("-r", "--refScore", dest="refScore", help="Output for refined score", type="string")
(options, args) = inOptions.parse_args()
logging.basicConfig(format='%(levelname)s:%(asctime)s: %(message)s', level=logging.DEBUG)
GenotypeData = genotype.load_hdf5_genotype_data(options.hdf5File)
#GenotypeData_acc = genotype.load_hdf5_genotype_data(options.hdf5accFile)
#num_lines = len(GenotypeData.accessions)
logging.info("Reading the VCF file")
vcf = vcfnp.variants(options.vcfFile, cache=True).view(numpy.recarray)
vcfD = vcfnp.calldata_2d(options.vcfFile, cache=True).view(numpy.recarray)
## Doubtful .... whether there should be a threshold based on just mean of std
#DPthres = numpy.mean(vcf.DP[numpy.where(vcf.DP > 0)[0]]) + numpy.std(vcf.DP[numpy.where(vcf.DP > 0)[0]])
DPthres = numpy.mean(vcf.DP[numpy.where(vcf.DP > 0)[0]]) * 4
print "Threshold for depth is set at: ", DPthres
#snpsREQ = numpy.where((vcfD.is_called[:,0]) & (vcf.QUAL > 30) & (vcf.DP > 0))[0]
snpsREQ = numpy.where((vcfD.is_called[:,0]) & (vcf.QUAL > 30) & (vcf.DP > 0) & (vcf.DP < DPthres))[0]
snpCHR = numpy.array(numpy.chararray.replace(vcf.CHROM[snpsREQ], "Chr", "")).astype("int8")
snpPOS = numpy.array(vcf.POS[snpsREQ])
snpGT = vcfD.GT[snpsREQ, 0] ## since one sample
snpPL = vcfD.PL[snpsREQ, 0]
snpDP = vcf.DP[snpsREQ]
def test_variants_region_empty():
a = variants("fixture/sample.vcf.gz", region="18")
eq_(0, len(a))
a = variants("fixture/sample.vcf.gz", region="19:113-200")
eq_(0, len(a))