def get_core_gene_vector(species_name):
core_genes = core_gene_utils.parse_core_genes(species_name)
# sort the genes
all_genes = np.array(list(core_genes))
gene_indices = np.array(
list(map(lambda name: int(name.split('.')[-1]), all_genes)))
all_genes = all_genes[np.argsort(gene_indices)]
return all_genes
def main(between_host):
# Parse and save all the snps between QP hosts
t0 = time.time()
if between_host:
intermediate_file_path = os.path.join(config.analysis_directory,
'between_hosts_checkpoints')
else:
intermediate_file_path = os.path.join(config.analysis_directory,
'within_hosts_checkpoints')
for species_name in desired_species:
print("Start processing {}".format(species_name))
core_genes = core_gene_utils.parse_core_genes(species_name)
desired_samples = get_desired_samples(species_name,
between_host=between_host)
if desired_samples is None or len(desired_samples) == 0:
print("{} has no qualified samples".format(species_name))
continue
pickle_path = os.path.join(intermediate_file_path, species_name)
if not os.path.exists(pickle_path):
print('{} has not been processed'.format(species_name))
os.mkdir(pickle_path)
else:
print('{} already processed'.format(species_name))
continue
found_samples, allele_counts_map, passed_sites_map, final_line_number = parse_snps(
species_name,
allowed_samples=desired_samples,
allowed_genes=core_genes,
allowed_variant_types=['4D'])
pickle.dump(allele_counts_map,
open(pickle_path + '/allele_counts_map.pickle', 'wb'))
pickle.dump(found_samples,
open(pickle_path + '/found_samples.pickle', 'wb'))
pickle.dump(passed_sites_map,
open(pickle_path + '/passed_sites_map.pickle', 'wb'))
print("Done processing {} at {} min".format(species_name,
(time.time() - t0) / 60))
debug=debug)
# Only consider one sample per person
snp_samples = snp_samples[parse_midas_data.calculate_unique_samples(
subject_sample_map, sample_list=snp_samples)]
sys.stderr.write("Proceeding with %d haploid samples!\n" %
len(snp_samples))
if len(snp_samples) < min_sample_size:
sys.stderr.write("Not enough haploid samples!\n")
continue
sys.stderr.write("Proceeding with %d haploid samples!\n" %
len(snp_samples))
sys.stderr.write("Loading core genes...\n")
core_genes = core_gene_utils.parse_core_genes(species_name)
non_shared_genes = core_gene_utils.parse_non_shared_reference_genes(
species_name)
shared_pangenome_genes = core_gene_utils.parse_shared_genes(
species_name)
sys.stderr.write("Done! Core genome consists of %d genes\n" %
len(core_genes))
sys.stderr.write("%d shared genes and %d non-shared genes\n" %
(len(shared_pangenome_genes), len(non_shared_genes)))
sys.stderr.write(
"Loading pre-computed substitution rates for %s...\n" %
species_name)
substitution_rate_map = calculate_substitution_rates.load_substitution_rate_map(
species_name)
sys.stderr.write("Calculating matrix...\n")