% (args['site_ratio'], 100 * args['site_prev']))
if args['max_sites'] != float('Inf'):
print(" keep <= %s sites" % (args['max_sites']))
print("Number of CPUs to use: %s" % args['threads'])
print("===============================")
print("")
def run_program(program, args):
""" Run program specified by user (species, genes, or snps) """
if program == 'species':
from midas.merge import species
species.run_pipeline(args)
elif program == 'genes':
from midas.merge import genes
genes.run_pipeline(args)
elif program == 'snps':
from midas.merge import snps
snps.run_pipeline(args)
else:
sys.exit("\nError: Unrecognized program: '%s'\n" % program)
if __name__ == '__main__':
program = get_program()
args = get_arguments(program)
check_arguments(program, args)
utility.print_copyright()
print_arguments(program, args)
run_program(program, args)
count_c: count of C allele
count_g: count of G allele
count_t: count of T allele
summary.txt
species_id: species id
genome_length: number of base pairs in representative genome
covered_bases: number of reference sites with at least 1 mapped read
fraction_covered: proportion of reference sites with at least 1 mapped read
mean_coverage: average read-depth across reference sites with at least 1 mapped read
aligned_reads: number of aligned reads BEFORE quality filtering
mapped_reads: number of aligned reads AFTER quality filtering
Additional information for each species can be found in the reference database:
%s/rep_genomes
""" % args['db'])
outfile.close()
if __name__ == '__main__':
program = get_program()
args = get_arguments(program)
check_arguments(program, args)
create_directories(program, args)
open_log(program, args)
utility.print_copyright(args['log'])
print_arguments(program, args)
run_program(program, args)
write_readme(program, args)
# keep/exclude sample
if sample.filter(args['sample_depth'], args['fract_cov']):
sample.pass_qc = False
if args['keep_samples'] and sample.id not in args['keep_samples']:
sample.pass_qc = False
if args['exclude_samples'] and sample.id in args['exclude_samples']:
sample.pass_qc = False
if sum([1 for s in samples if s.pass_qc]) >= args['max_samples']:
sample.pass_qc = False
# store sample
samples.append(sample)
# select random sample
if args['rand_samples']: resample_samples(samples)
return samples
if __name__ == '__main__':
args = parse_arguments()
check_args(args)
print_copyright()
print_args(args)
print("\nSelecting subset of samples...")
samples = fetch_samples(args)
print("Estimating diversity metrics...")
pi = compute_pi(args, samples)
print("Writing results to output file...")
write_pi(args, samples, pi)
'sites_NC', 'sites_1D', 'sites_2D', 'sites_3D', 'sites_4D',
'snps_NC', 'snps_1D', 'snps_2D', 'snps_3D', 'snps_4D',
'pi_NC', 'pi_1D', 'pi_2D', 'pi_3D', 'pi_4D']
outfile.write('\t'.join(fields)+'\n')
gene_ids = set([])
for sample in samples.values():
for gene_id in sample.genes:
gene_ids.add(gene_id)
for sample in samples.values():
for gene_id in gene_ids:
if gene_id not in sample.genes:
gene = Gene(gene_id)
else:
gene = sample.genes[gene_id]
record = gene.format_record(sample.id, fields)
outfile.write(record)
if __name__ == '__main__':
args = parse_arguments()
utility.print_copyright()
print("Loading samples...")
samples = st.init_samples(args)
print("Estimating diversity metrics...")
compute_diversity(args, samples)
print("Writing results...")
write_per_gene_results(args, samples)
