species_name = sys.argv[1]
debug = True
min_coverage = 20
# Load subject and sample metadata
sys.stderr.write("Loading HMP metadata...\n")
subject_sample_map = parse_midas_data.parse_subject_sample_map()
sys.stderr.write("Done!\n")
###
# Load genomic coverage distributions
sample_coverage_histograms, samples = parse_midas_data.parse_coverage_distribution(
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))
}
# Load pi information for species_name
sys.stderr.write("Loading within-sample diversity for %s...\n" % species_name)
samples, total_pis, total_pi_opportunities = parse_midas_data.parse_within_sample_pi(
species_name, debug)
sys.stderr.write("Done!\n")
pis = total_pis / total_pi_opportunities
clipped_pis = (total_pis + 1) / (total_pi_opportunities + 1)
# Load subject and sample metadata
sys.stderr.write("Loading HMP metadata...\n")
subject_sample_map = parse_midas_data.parse_subject_sample_map()
sys.stderr.write("Done!\n")
species_idx = 0
for species_name in species_names:
species_name_items = species_name.split("_")
species_label = "_".join([species_name_items[0]]+species_name_items[1:])
# Load genomic coverage distributions
sample_coverage_histograms, samples = parse_midas_data.parse_coverage_distribution(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))}
# Load pi information for species_name
sys.stderr.write("Loading within-sample diversity for %s...\n" % species_name)
samples, total_pis, total_pi_opportunities = parse_midas_data.parse_within_sample_pi(species_name, debug=debug)
sys.stderr.write("Done!\n")
pis = total_pis/total_pi_opportunities
median_coverages = numpy.array([sample_coverage_map[samples[i]] for i in xrange(0,len(samples))])
# Only plot samples above a certain depth threshold that are "haploids"
desired_samples = samples[(median_coverages>=min_coverage)*(pis<=1e-03)]
desired_median_coverages = median_coverages[(median_coverages>=min_coverage)*(pis<=1e-03)]
if len(desired_samples) < 2:
