divergence_matrices[species_name] = snp_substitution_matrix
between_divergences[species_name] = []
for i in xrange(0, divergence_matrices[species_name].shape[0]):
for j in xrange(i + 1, divergence_matrices[species_name].shape[0]):
if divergence_matrices[species_name][i, j] >= 0:
between_divergences[species_name].append(
divergence_matrices[species_name][i, j])
between_divergences[species_name] = numpy.array(
between_divergences[species_name])
# Load SNP information for species_name
sys.stderr.write("Loading SFSs for %s...\t" % species_name)
sfs_samples, sfs_map = parse_midas_data.parse_within_sample_sfs(
species_name)
sys.stderr.write("Done!\n")
highcoverage_samples = diversity_utils.calculate_highcoverage_samples(
species_name)
desired_samples = snp_samples
within_polymorphisms[species_name] = []
for sample in desired_samples:
within_sites, between_sites, total_sites = sfs_utils.calculate_polymorphism_rates_from_sfs_map(
sfs_map[sample])
within_polymorphisms[species_name].append(within_sites * 1.0 /
total_sites)
species_names = []
sample_sizes = []
subject_sample_map = parse_HMP_data.parse_subject_sample_map()
sample_order_map = parse_HMP_data.parse_sample_order_map()
sys.stderr.write("Done!\n")
if other_species_str == "":
good_species_list = parse_midas_data.parse_good_species_list()
else:
good_species_list = [species_name]
# store all the species' data in a dictionary:
all_data = {}
#key=species
#value={}, key=gene, valuee=num times gene shows up
for species_name in good_species_list:
dummy_samples, sfs_map = parse_midas_data.parse_within_sample_sfs(
species_name, allowed_variant_types=set(['1D', '2D', '3D', '4D']))
#
# data structures for storing information for pickling later on
all_species_gene_changes = {}
#all_species_gene_changes_category={}
all_species_null = {}
all_data[species_name] = {}
#
####################
# Analyze the data #
####################
#
# Only plot samples above a certain depth threshold that are "haploids"
haploid_samples = diversity_utils.calculate_haploid_samples(species_name,
debug=debug)
#
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, site_map = parse_midas_data.parse_within_sample_sfs(
species_name,
allowed_variant_types=set(['4D']),
allowed_genes=core_genes,
debug=debug)
sys.stderr.write("Done!\n")
median_coverages = numpy.array(
[sample_coverage_map[samples[i]] for i in xrange(0, len(samples))])
print[len(site_map[i].keys()) for i in xrange(0, len(site_map))]
sys.exit(0)
# Only plot samples above a certain depth threshold that are "haploids"
snp_samples = samples[(median_coverages >= min_coverage) * (pis <= 1e-03)]
num_haploids = len(snp_samples)
