replacement_map = {}
for species_name in good_species_list:
if not species_name.startswith('Bacteroides_fragilis'):
continue
# Only plot samples above a certain depth threshold that are "haploids"
haploid_samples = diversity_utils.calculate_haploid_samples(species_name,
debug=debug)
if len(haploid_samples) < min_sample_size:
continue
same_sample_idxs, same_subject_idxs, diff_subject_idxs = parse_midas_data.calculate_ordered_subject_pairs(
sample_order_map, haploid_samples)
snp_samples = set()
sample_size = 0
for sample_pair_idx in xrange(0, len(same_subject_idxs[0])):
i = same_subject_idxs[0][sample_pair_idx]
j = same_subject_idxs[1][sample_pair_idx]
snp_samples.add(haploid_samples[i])
snp_samples.add(haploid_samples[j])
sample_size += 1
snp_samples = list(snp_samples)
include_high_copynum=include_high_copynum)
gene_difference_matrix = gene_gain_matrix + gene_loss_matrix
# Now need to make the gene samples and snp samples match up
desired_samples = gene_samples
num_haploids = len(desired_samples)
# Calculate which pairs of idxs belong to the same sample, which to the same subject
# and which to different subjects
#desired_same_sample_idxs, desired_same_subject_idxs, desired_diff_subject_idxs = parse_midas_data.calculate_subject_pairs(subject_sample_map, desired_samples)
# Calculate which pairs of idxs belong to the same sample, which to the same subject
# and which to different subjects
desired_same_sample_idxs, desired_same_subject_idxs, desired_diff_subject_idxs = parse_midas_data.calculate_ordered_subject_pairs(
sample_order_map, desired_samples)
snp_sample_idx_map = parse_midas_data.calculate_sample_idx_map(
desired_samples, snp_samples)
gene_sample_idx_map = parse_midas_data.calculate_sample_idx_map(
desired_samples, gene_samples)
same_sample_snp_idxs = parse_midas_data.apply_sample_index_map_to_indices(
snp_sample_idx_map, desired_same_sample_idxs)
same_sample_gene_idxs = parse_midas_data.apply_sample_index_map_to_indices(
gene_sample_idx_map, desired_same_sample_idxs)
same_subject_snp_idxs = parse_midas_data.apply_sample_index_map_to_indices(
snp_sample_idx_map, desired_same_subject_idxs)
same_subject_gene_idxs = parse_midas_data.apply_sample_index_map_to_indices(
gene_sample_idx_map, desired_same_subject_idxs)
debug=debug)
if len(haploid_samples) < min_sample_size:
continue
# all samples
temporal_samples = diversity_utils.calculate_temporal_samples(species_name)
# temporal changes
sys.stderr.write("Loading pre-computed temporal changes for %s...\n" %
species_name)
temporal_change_map = calculate_temporal_changes.load_temporal_change_map(
species_name)
sys.stderr.write("Done!\n")
same_sample_idxs, same_subject_idxs, diff_subject_idxs = parse_midas_data.calculate_ordered_subject_pairs(
sample_order_map, temporal_samples)
snp_samples = set()
sample_size = 0
for sample_pair_idx in xrange(0, len(same_subject_idxs[0])):
i = same_subject_idxs[0][sample_pair_idx]
j = same_subject_idxs[1][sample_pair_idx]
sample_i = temporal_samples[i]
sample_j = temporal_samples[j]
# Don't look at haploids here!
if sample_i in haploid_samples:
continue