parser.add_argument("--species", help="Name of specific species to run code on", default="Bacteroides_vulgatus_57955")
args = parser.parse_args()
debug = args.debug
chunk_size = args.chunk_size
species_name=args.species
# Load subject and sample metadata
sys.stderr.write("Loading sample metadata...\n")
subject_sample_map = parse_HMP_data.parse_subject_sample_map()
sys.stderr.write("Done!\n")
# Only plot samples above a certain depth threshold that are "haploids"
snp_samples = diversity_utils.calculate_haploid_samples(species_name, 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")
sys.exit(1)
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("Done!\n")
sys.stderr.write("Loaded gene info for %d samples\n" % len(gene_samples))
gene_copynum_matrix = gene_depth_matrix * 1.0 / (marker_coverages +
(marker_coverages == 0))
clipped_gene_copynum_matrix = numpy.clip(gene_depth_matrix, 0.1,
1e09) / (marker_coverages + 0.1 *
(marker_coverages == 0))
low_copynum_matrix = (gene_copynum_matrix <= 3)
good_copynum_matrix = (gene_copynum_matrix >= 0.5) * (
gene_copynum_matrix <= 3) # why isn't this till 2? NRG
prevalence_idxs = (parse_midas_data.calculate_unique_samples(
subject_sample_map, gene_samples)) * (marker_coverages >= min_coverage)
prevalences = gene_diversity_utils.calculate_fractional_gene_prevalences(
gene_depth_matrix[:, prevalence_idxs], marker_coverages[prevalence_idxs])
pangenome_prevalences = numpy.array(prevalences, copy=True)
pangenome_prevalences.sort()
# Calculate matrix of number of genes that differ
sys.stderr.write("Calculating matrix of gene differences...\n")
gene_gain_matrix, gene_loss_matrix, gene_opportunity_matrix = gene_diversity_utils.calculate_coverage_based_gene_hamming_matrix_gain_loss(
gene_reads_matrix, gene_depth_matrix, marker_coverages)
gene_difference_matrix = gene_gain_matrix + gene_loss_matrix
# Now need to make the gene samples and snp samples match up
desired_samples = samples[(median_coverages >= min_coverage) * (pis <= 1e-03)]
###
# Load SNP information for species_name
sys.stderr.write("Loading %s...\n" % species_name)
samples, allele_counts_map, passed_sites_map, final_line_number = parse_midas_data.parse_snps(
species_name, debug=debug, allowed_samples=desired_samples)
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.
distance_bins[0] = 0.5 # made smallest bin 0.5 to avoid edge effects
distance_bins[
-1] = 1e09 # made largest bin very large to catch anything >10^4.
binned_rsquared_numerators = numpy.zeros_like(distance_bin_locations)
median_coverages = numpy.array(
[sample_coverage_map[samples[i]] for i in xrange(0, len(samples))])
###############################################################
# Indexes for SNP samples that have high coverage #
###############################################################
# Only plot samples above a certain depth threshold that are "haploids"
low_pi_snp_samples = samples[(median_coverages >= min_coverage) *
(pis <= 1e-03)]
high_pi_snp_samples = samples[(median_coverages >= min_coverage) *
(pis > 1e-03)]
# Calculate which pairs of idxs belong to unique samples. Remove any samples that are duplicates (i.e. multiple time pts)
unique_idxs = parse_midas_data.calculate_unique_samples(
subject_sample_map, low_pi_snp_samples)
low_pi_snp_samples = low_pi_snp_samples[unique_idxs]
unique_idxs = parse_midas_data.calculate_unique_samples(
subject_sample_map, high_pi_snp_samples)
high_pi_snp_samples = low_pi_snp_samples[unique_idxs]
####################################################
# Load gene coverage information for species_name
####################################################
sys.stderr.write("Loading pangenome data for %s...\n" % species_name)
low_pi_gene_samples, low_pi_gene_names, low_pi_gene_presence_matrix, low_pi_gene_depth_matrix, low_pi_marker_coverages, low_pi_gene_reads_matrix = parse_midas_data.parse_pangenome_data(
species_name, allowed_samples=low_pi_snp_samples)
high_pi_gene_samples, high_pi_gene_names, high_pi_gene_presence_matrix, high_pi_gene_depth_matrix, high_pi_marker_coverages, high_pi_gene_reads_matrix = parse_midas_data.parse_pangenome_data(
species_name, allowed_samples=high_pi_snp_samples)
