def test_calc_obs_het_sample(self):
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
snps = VariationsArrays()
snps.put_chunks(hdf5.iterate_chunks(kept_fields=['/calls/GT']))
het_h5 = calc_obs_het_by_sample(hdf5)
het_array = calc_obs_het_by_sample(snps)
assert numpy.all(het_array == het_h5)
gts = numpy.array([[[0, 0], [0, 1], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, 0], [-1, -1]]])
varis = {'/calls/GT': gts}
het = calc_obs_het_by_sample(varis, chunk_size=None)
assert numpy.allclose(het, [0, 1 / 3, 0, numpy.NaN], equal_nan=True)
gts = numpy.array([])
varis = {'/calls/GT': gts}
het = calc_obs_het_by_sample(varis, chunk_size=None)
assert het.shape[0] == 0
snps = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
calc_obs_het_by_sample(snps, min_call_dp=3)
calc_obs_het_by_sample(snps, min_call_dp=3, max_call_dp=20)
het_0 = calc_obs_het_by_sample(snps)
het = calc_obs_het_by_sample(snps, chunk_size=None)
assert numpy.allclose(het_0, het)
def test_calc_obs_het_sample(self):
hdf5 = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
snps = VariationsArrays()
snps.put_chunks(hdf5.iterate_chunks(kept_fields=['/calls/GT']))
het_h5 = calc_obs_het_by_sample(hdf5)
het_array = calc_obs_het_by_sample(snps)
assert numpy.all(het_array == het_h5)
gts = numpy.array([[[0, 0], [0, 1], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, -1], [-1, -1]],
[[0, 0], [0, 0], [0, 0], [-1, -1]]])
varis = {'/calls/GT': gts}
het = calc_obs_het_by_sample(varis, chunk_size=None)
assert numpy.allclose(het, [0, 1 / 3, 0, numpy.NaN], equal_nan=True)
gts = numpy.array([])
varis = {'/calls/GT': gts}
het = calc_obs_het_by_sample(varis, chunk_size=None)
assert het.shape[0] == 0
snps = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
calc_obs_het_by_sample(snps, min_call_dp=3)
calc_obs_het_by_sample(snps, min_call_dp=3, max_call_dp=20)
het_0 = calc_obs_het_by_sample(snps)
het = calc_obs_het_by_sample(snps, chunk_size=None)
assert numpy.allclose(het_0, het)
def plot_obs_het(variations, data_dir, chunk_size=SNPS_PER_CHUNK,
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT):
# Calculate observed heterozygosity distribution by snp
_calc_obs_het_by_var = partial(calc_obs_het,
min_num_genotypes=min_num_genotypes)
distrib = histogram_for_chunks(variations, calc_funct=_calc_obs_het_by_var,
n_bins=25, range_=(0, 1),
chunk_size=chunk_size)
obs_het_var_distrib, bins1 = distrib
# Calculate observed heterozygosity distribution by sample
obs_het_by_sample = calc_obs_het_by_sample(variations,
chunk_size=chunk_size)
obs_het_sample_distrib, bins2 = histogram(obs_het_by_sample, n_bins=25,
range_=(0, 1))
# Plot distributions
fpath = join(data_dir, 'obs_het.png')
fhand = open(fpath, 'w')
fig = Figure(figsize=(10, 10))
canvas = FigureCanvas(fig)
axes = fig.add_subplot(211)
title = 'SNP observed Heterozygosity distribution'
plot_distrib(obs_het_var_distrib, bins=bins1, fhand=open(fpath, 'w'),
mpl_params={'set_xlabel': {'args': ['Heterozygosity'],
'kwargs': {}},
'set_ylabel': {'args': ['SNP number'], 'kwargs': {}},
'set_title': {'args': [title], 'kwargs': {}},
'set_yscale': {'args': ['log'], 'kwargs': {}}},
axes=axes, color='c')
axes = fig.add_subplot(212)
title = 'Sample observed Heterozygosity distribution'
plot_distrib(obs_het_sample_distrib, bins=bins2, fhand=open(fpath, 'w'),
mpl_params={'set_xlabel': {'args': ['Heterozygosity'],
'kwargs': {}},
'set_ylabel': {'args': ['Sample number'],
'kwargs': {}},
'set_title': {'args': [title], 'kwargs': {}}},
axes=axes, color='c')
canvas.print_figure(fhand)
def plot_obs_het(variations,
data_dir,
chunk_size=SNPS_PER_CHUNK,
min_num_genotypes=MIN_NUM_GENOTYPES_FOR_POP_STAT):
# Calculate observed heterozygosity distribution by snp
_calc_obs_het_by_var = partial(calc_obs_het,
min_num_genotypes=min_num_genotypes)
distrib = histogram_for_chunks(variations,
calc_funct=_calc_obs_het_by_var,
n_bins=25,
range_=(0, 1),
chunk_size=chunk_size)
obs_het_var_distrib, bins1 = distrib
# Calculate observed heterozygosity distribution by sample
obs_het_by_sample = calc_obs_het_by_sample(variations,
chunk_size=chunk_size)
obs_het_sample_distrib, bins2 = histogram(obs_het_by_sample,
n_bins=25,
range_=(0, 1))
# Plot distributions
fpath = join(data_dir, 'obs_het.png')
fhand = open(fpath, 'w')
fig = Figure(figsize=(10, 10))
canvas = FigureCanvas(fig)
axes = fig.add_subplot(211)
title = 'SNP observed Heterozygosity distribution'
plot_distrib(obs_het_var_distrib,
bins=bins1,
fhand=open(fpath, 'w'),
mpl_params={
'set_xlabel': {
'args': ['Heterozygosity'],
'kwargs': {}
},
'set_ylabel': {
'args': ['SNP number'],
'kwargs': {}
},
'set_title': {
'args': [title],
'kwargs': {}
},
'set_yscale': {
'args': ['log'],
'kwargs': {}
}
},
axes=axes,
color='c')
axes = fig.add_subplot(212)
title = 'Sample observed Heterozygosity distribution'
plot_distrib(obs_het_sample_distrib,
bins=bins2,
fhand=open(fpath, 'w'),
mpl_params={
'set_xlabel': {
'args': ['Heterozygosity'],
'kwargs': {}
},
'set_ylabel': {
'args': ['Sample number'],
'kwargs': {}
},
'set_title': {
'args': [title],
'kwargs': {}
}
},
axes=axes,
color='c')
canvas.print_figure(fhand)
