}
# Load SNP information for species_name
sys.stderr.write("Loading %s...\n" % species_name)
samples, allele_counts_map, passed_sites_map = parse_midas_data.parse_snps(
species_name, combination_type="sample", debug=False)
sys.stderr.write("Done!\n")
median_coverages = numpy.array(
[sample_coverage_map[samples[i]] for i in xrange(0, len(samples))])
# Calculate full matrix of synonymous pairwise differences
sys.stderr.write("Calculate synonymous pi matrix...\n")
pi_matrix_syn, avg_pi_matrix_syn = diversity_utils.calculate_pi_matrix(
allele_counts_map,
passed_sites_map,
variant_type='4D',
allowed_genes=metaphlan2_genes)
# Calculate fixation matrix
fixation_matrix_syn = diversity_utils.calculate_fixation_matrix(
allele_counts_map,
passed_sites_map,
variant_type='4D',
min_change=min_change,
allowed_genes=metaphlan2_genes)
sys.stderr.write("Done!\n")
# Calculate full matrix of nonsynonymous pairwise differences
sys.stderr.write("Calculate nonsynonymous pi matrix...\n")
from parsers import parse_midas_data
from numpy.random import choice
species_name = sys.argv[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")
# Load SNP information for species_name
sys.stderr.write("Loading %s...\n" % species_name)
samples, allele_counts_map, passed_sites_map = parse_midas_data.parse_snps(
species_name, combination_type="sample", debug=False)
sys.stderr.write("Done!\n")
pi_matrix_syn, avg_pi_matrix_syn = diversity_utils.calculate_pi_matrix(
allele_counts_map, passed_sites_map, variant_type='4D')
low_diversity_samples = (numpy.diag(avg_pi_matrix_syn) < 1e-03)
unique_samples = parse_midas_data.calculate_unique_samples(
subject_sample_map, samples)
desired_samples = unique_samples * low_diversity_samples
# initialize distance bins for LD computations
distance_bins = numpy.logspace(
0, 4, 20
) # bins start from 1 to 10^4 and there are 20 evenly spaced bins log(1)=0, log(10^4)-4
distance_bin_locations = numpy.array(
distance_bins[:-1],
copy=True) # shifted one to avoid edge effects for plotting.
sys.stderr.write("Loading %s...\n" % species_name)
samples, allele_counts_map, passed_sites_map = parse_midas_data.parse_snps(
species_name, combination_type="sample", debug=False)
sys.stderr.write("Done!\n")
locations = []
pi_syns = []
pi_nons = []
for gene_name in passed_sites_map.keys():
passed_sites = passed_sites_map[gene_name]['4D']['sites']
passed_pairs = (passed_sites > 0.5)
passed_pairs[numpy.diag_indices_from(passed_pairs)] = False
pi_matrix, avg_pi_matrix = diversity_utils.calculate_pi_matrix(
allele_counts_map,
passed_sites_map,
variant_type='4D',
allowed_genes=set([gene_name]))
total_pairs = passed_pairs.sum()
if total_pairs < 0.5:
continue
avg_pi = (pi_matrix * passed_pairs).sum() / (total_pairs +
(total_pairs < 0.5))
pi_syns.append(avg_pi)
locations.append(passed_sites_map[gene_name]['4D']['location'])
passed_sites = passed_sites_map[gene_name]['1D']['sites']
passed_pairs = (passed_sites > 0.5)