richard
/
geinf
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

add comments

master
tforest 2021-10-19 11:32:30 +02:00
parent a7490aed15
commit 110ba26f7e
1 changed files with 12 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
vcf_to_sfs.py
View File

@ -3,6 +3,10 @@
""" """
Caution : At the moment for gzipped files only. Caution : At the moment for gzipped files only.
ARGS
--------
usage : vcf_to_sfs.py VCF.gz nb_indiv
""" """
@ -12,22 +16,23 @@ import sys
# default folded SFS # default folded SFS
folded = True folded = True
diploid = True diploid = True
phased = False
# PARAM : Nb of indiv # PARAM : Nb of indiv
n = int(sys.argv[2]) n = int(sys.argv[2])
if diploid and not folded: if diploid and not folded:
n *= 2 n *= 2
# initiate SFS_values with a zeros dict
SFS_values = dict.fromkeys(range(n),0) SFS_values = dict.fromkeys(range(n),0)
with gzip.open(sys.argv[1], "rb") as inputgz: with gzip.open(sys.argv[1], "rb") as inputgz:
line = inputgz.readline() line = inputgz.readline()
genotypes = [] genotypes = []
#SFS_values = {}
while line: while line:
# decode gzipped binary lines
line = line.decode('utf-8').strip() line = line.decode('utf-8').strip()
# every snp line, not comment or header
if not line.startswith("##") and not line.startswith("#"): if not line.startswith("##") and not line.startswith("#"):
FORMAT = line.split("\t")[8:9] FORMAT = line.split("\t")[8:9]
SAMPLES = line.split("\t")[9:] SAMPLES = line.split("\t")[9:]
@ -36,27 +41,16 @@ with gzip.open(sys.argv[1], "rb") as inputgz:
for sample in SAMPLES: for sample in SAMPLES:
# for UNPHASED data # for UNPHASED data
smpl_genotype = [int(a) for a in sample.split(':')[0].split('/') if a != '.'] smpl_genotype = [int(a) for a in sample.split(':')[0].split('/') if a != '.']
nb_alleles = set(smpl_genotype) nb_alleles = set(smpl_genotype)
snp_genotypes += smpl_genotype snp_genotypes += smpl_genotype
# skip if all individuals have the same genotype
if len(set(snp_genotypes)) == 1: if len(set(snp_genotypes)) == 1:
line = inputgz.readline() line = inputgz.readline()
continue continue
#print(snp_genotypes)
for k in set(snp_genotypes): for k in set(snp_genotypes):
allele_counts[snp_genotypes.count(k)] = k allele_counts[snp_genotypes.count(k)] = k
if 7 in allele_counts.keys():
print(allele_counts)
#print(allele_counts)
if folded : if folded :
#for count in allele_counts.keys():
# for count in allele_counts.keys():
# if count <= len(snp_genotypes)/2 :
# SFS_values[count-1] += 1
# else:
# SFS_values[len(snp_genotypes)-count-1] += 1
SFS_values[min(allele_counts.keys())-1] += 1 SFS_values[min(allele_counts.keys())-1] += 1
line = inputgz.readline() line = inputgz.readline()
#print(SFS_values) print(SFS_values)
# Note : tout est doublé là