def configure(self,
line,
sample_id_to_population,
dir_launch='..',
ancestral_check=False):
column_labels = line.split()
self.n_lineages = 2 * (len(column_labels) - 9)
print('\t{} columns'.format(len(column_labels)))
print('\tcolumn index to pop')
self.column_index_to_population = get_column_index_to_population(
column_labels, sample_id_to_population)
self.refseq = reference_sequence(self.chrom,
self.ref,
dir_launch=dir_launch)
print('len of reference seq: {}'.format(len(self.refseq)))
if ancestral_check:
print('\tdifferences to {}'.format(self.short))
self.human_chimp_differences = get_human_chimp_differences(
self.chrom, self.ref, self.short, dir_launch=dir_launch)
else:
self.human_chimp_differences = {}
print('\tconfigure regions')
for included_region in self.included_regions:
included_region.configure(column_labels, sample_id_to_population)
def configure(self, line):
column_labels = line.split()
self.n_lineages = 2 * (len(column_labels) - 9)
self.column_index_to_population = get_column_index_to_population(
column_labels)
self.refseq = reference_sequence(self.chrom)
self.human_chimp_differences = get_human_chimp_differences(self.chrom)
for included_region in self.included_regions:
included_region.configure(column_labels)
def process_chromosome(chrom,
ref,
short,
vcf_file,
suff='chr',
vcf_dir='vcfs',
dir_launch='..',
outfile_dir='..'):
'''
Platform function
read vcf file;
read fasta;
read reference to vcf differences;
dispatch each genotype line to process_line();
update mutation / individual library counts;
write
'''
# check args
refseq = reference_sequence(chrom, ref, dir_launch=dir_launch)
refseq = refseq.decode()
# check args
chimp_alleles = get_human_chimp_differences(chrom,
ref,
short,
dir_launch=dir_launch)
## mutations imported
# check args: chrom,vcf_file,suff='chr',vcf_dir= 'vcfs',dir_launch='..'
gzip_path = ''.join(
[dir_launch, '/data/', vcf_dir, '/', vcf_file, suff, chrom, '.vcf.gz'])
# gzip_path = '../data/vcfs/ALL.chr'+chrom+'.phase3_shapeit2_mvncall_integrated_v5a.20130502.genotypes.vcf.gz'
with gzip.open(gzip_path) as infile:
c = 0
d = 0
for line in infile:
line = line.decode()
c += 1
if line.split()[0] == '#CHROM':
sample_ids = line.split()[9:]
n_lineages = 2 * len(sample_ids)
mutation_counts = {(mutation, haplotype_index): 0
for haplotype_index in range(n_lineages)
for mutation in mutations}
d = 1
if d == 1:
try:
derived_allele, derived_count, this_mut, alleles = process_line(
line, refseq, chimp_alleles)
except BadDataQualityError:
continue
update_counts(alleles, mutation_counts, derived_count,
derived_allele, n_lineages, this_mut)
write_output(mutation_counts, sample_ids, mutations, n_lineages, chrom,
outfile_dir)