def plot_missing_gt_rate_per_snp(variations,
data_dir,
chunk_size=SNPS_PER_CHUNK):
_calc_missing_gt = partial(calc_missing_gt, rates=True, axis=1)
distrib, bins = histogram_for_chunks(variations,
calc_funct=_calc_missing_gt,
range_=(0, 1),
n_bins=20,
chunk_size=chunk_size)
fpath = join(data_dir, 'missing_gt_rate.png')
title = 'Missing Genotype rates per SNP distribution'
plot_distrib(distrib,
bins,
fhand=open(fpath, 'w'),
color='c',
mpl_params={
'set_xlabel': {
'args': ['Missing GT rate'],
'kwargs': {}
},
'set_ylabel': {
'args': ['SNP number'],
'kwargs': {}
},
'set_title': {
'args': [title],
'kwargs': {}
}
})
def test_calc_maf_distrib_by_chunk(self):
varis = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
calc_maf_for_chunk = partial(calc_maf, min_num_genotypes=1,
chunk_size=None)
distrib, bins = histogram_for_chunks(varis, calc_maf_for_chunk,
n_bins=10)
dist_expected = [53, 75, 74, 70, 69, 129, 73, 74, 49, 277]
bins_expected = [0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95,
1.]
assert numpy.allclose(bins, bins_expected)
assert numpy.allclose(distrib, dist_expected)
def test_calc_maf_distrib_by_chunk(self):
varis = VariationsH5(join(TEST_DATA_DIR, 'ril.hdf5'), mode='r')
calc_maf_for_chunk = partial(calc_maf, min_num_genotypes=1,
chunk_size=None)
distrib, bins = histogram_for_chunks(varis, calc_maf_for_chunk,
n_bins=10)
dist_expected = [53, 72, 77, 66, 73, 129, 74, 73, 49, 277]
bins_expected = [0.5, 0.55, 0.6, 0.65, 0.7, 0.75, 0.8, 0.85, 0.9, 0.95,
1.]
assert numpy.allclose(bins, bins_expected)
assert numpy.allclose(distrib, dist_expected)
def plot_missing_gt_rate_per_snp(variations, data_dir,
chunk_size=SNPS_PER_CHUNK):
_calc_missing_gt = partial(calc_missing_gt, rates=True, axis=1)
distrib, bins = histogram_for_chunks(variations,
calc_funct=_calc_missing_gt,
range_=(0, 1), n_bins=20,
chunk_size=chunk_size)
fpath = join(data_dir, 'missing_gt_rate.png')
title = 'Missing Genotype rates per SNP distribution'
plot_distrib(distrib, bins, fhand=open(fpath, 'w'), color='c',
mpl_params={'set_xlabel': {'args': ['Missing GT rate'],
'kwargs': {}},
'set_ylabel': {'args': ['SNP number'],
'kwargs': {}},
'set_title': {'args': [title], 'kwargs': {}}})
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)
