inconsistency_axis.get_xaxis().tick_bottom()
inconsistency_axis.get_yaxis().tick_left()
inconsistency_axis.set_xlabel('Maximum divergence age of SNV, $d_B^*$')
inconsistency_axis.set_ylabel('Phylogenetic inconsistency between\nSNVs & core-genome divergence')
inconsistency_axis.set_xlim([2e-05,2e-02])
inconsistency_axis.set_ylim([0,1.05])
passed_species = []
sample_sizes = []
for species_name in good_species_list:
sys.stderr.write("Loading haploid samples...\n")
# Only plot samples above a certain depth threshold that are "haploids"
snp_samples = diversity_utils.calculate_haploid_samples(species_name, debug=debug)
if len(snp_samples) < min_sample_size:
sys.stderr.write("Not enough haploid samples!\n")
continue
sys.stderr.write("Calculating unique samples...\n")
# Only consider one sample per person
snp_samples = snp_samples[sample_utils.calculate_unique_samples(subject_sample_map, sample_list=snp_samples)]
if len(snp_samples) < min_sample_size:
sys.stderr.write("Not enough unique samples!\n")
continue
# Load inconsistency data
species_name)
median_coverages = numpy.array([
stats_utils.calculate_nonzero_median_from_histogram(
sample_coverage_histogram)
for sample_coverage_histogram in sample_coverage_histograms
])
sample_coverage_map = {
samples[i]: median_coverages[i]
for i in xrange(0, len(samples))
}
samples = numpy.array(samples)
highcoverage_samples = set(
diversity_utils.calculate_highcoverage_samples(species_name))
qp_samples = set(
diversity_utils.calculate_haploid_samples(species_name))
non_qp_samples = list(highcoverage_samples - qp_samples)
num_samples = 6
replace = False
if len(non_qp_samples) < num_samples:
replace = True
target_samples = choice(non_qp_samples, num_samples, replace)
sample_sfs_grid = gridspec.GridSpecFromSubplotSpec(
1,
num_samples,
width_ratios=[1] * 6,
subplot_spec=species_sfs_grid[species_idx],
wspace=0.1)
