if not ((snp_samples[snp_i] in haploid_samples) and (snp_samples[snp_j] in haploid_samples)):
# both have to be haploids
continue
plower = snp_difference_matrix[snp_i,snp_j]
pupper = plower*1.1
#plower,pupper = stats_utils.calculate_poisson_rate_interval(snp_difference_matrix[snp_i,snp_j], snp_opportunity_matrix[snp_i, snp_j])
diff_subject_snp_plowers.append(plower)
diff_subject_snp_puppers.append(pupper)
i = diff_subject_gene_idxs[0][sample_pair_idx]
j = diff_subject_gene_idxs[1][sample_pair_idx]
gene_differences = gene_diversity_utils.calculate_gene_differences_between(i, j, gene_depth_matrix, marker_coverages,include_high_copynum=False)
if snp_substitution_rate[snp_i,snp_j] < clade_divergence_threshold:
for gene_idx, depth_tuple_1, depth_tuple_2 in gene_differences:
if gene_idx not in between_host_gene_idx_map:
between_host_gene_idx_map[gene_idx]=0
between_host_gene_idxs.append(gene_idx)
between_host_gene_idx_map[gene_idx]+=1
if snp_substitution_rate[snp_i,snp_j] < modification_divergence_threshold:
# A modification, not a replacement!
for gene_idx, depth_tuple_1, depth_tuple_2 in gene_differences:
label='CN>0.01')
pylab.semilogy([10, 10], [1, 1e04], 'k:')
pylab.xlim([-1, prevalences[-1] + 1])
pylab.legend(loc='lower right', frameon=False, fontsize=8)
pylab.savefig('%s/%s_reference_gene_presence_sfs.pdf' %
(parse_midas_data.analysis_directory, species_name),
bbox_inches='tight')
pylab.savefig('%s/%s_reference_gene_presence_sfs.png' %
(parse_midas_data.analysis_directory, species_name),
bbox_inches='tight',
dpi=300)
sys.exit(0)
within_subject_gene_change_prevalences = []
# Calculate gene content differences
for i, j in zip(same_subject_idxs[0], same_subject_idxs[1]):
gene_differences = gene_diversity_utils.calculate_gene_differences_between(
i,
j,
gene_names,
gene_depth_matrix,
marker_coverages,
min_log2_fold_change=4)
if len(gene_differences) > 0:
print "Differences between", i, j
for idx in xrange(0, len(gene_differences)):
print gene_differences[idx], gene_prevalence_map[
gene_differences[idx][0]]
#
snp_i = same_subject_snp_idxs[0][sample_pair_idx]
snp_j = same_subject_snp_idxs[1][sample_pair_idx]
#
plower, pupper = stats_utils.calculate_poisson_rate_interval(
snp_difference_matrix[snp_i, snp_j],
snp_opportunity_matrix[snp_i, snp_j], alpha)
#
same_subject_snp_plowers.append(plower)
same_subject_snp_puppers.append(pupper)
#
#snp_differences = diversity_utils.calculate_snp_differences_between(i,j,allele_counts_map, passed_sites_map, min_change=min_change)
#
i = same_subject_gene_idxs[0][sample_pair_idx]
j = same_subject_gene_idxs[1][sample_pair_idx]
gene_differences = gene_diversity_utils.calculate_gene_differences_between(
i, j, gene_depth_matrix, marker_coverages)
if snp_substitution_rate[snp_i, snp_j] < low_divergence_threshold:
for gene_idx, depth_tuple_1, depth_tuple_2 in gene_differences:
if gene_idx not in within_host_gene_idx_map:
within_host_gene_idx_map[gene_idx] = 0
#
within_host_gene_idx_map[gene_idx] += 1
#
plower, pupper = stats_utils.calculate_poisson_rate_interval(
gene_difference_matrix[i, j], gene_opportunity_matrix[i, j])
#
same_subject_gene_plowers.append(plower)
same_subject_gene_puppers.append(pupper)
#