def check_path():
if not isdir(my_parser().filePath):
return bomb(f'No files found at path = {my_parser().filePath}\n')
elif isdir(my_parser().filePath) and \
not [item for item in flatten(file_list) if item.endswith(('vcf', 'vcf.gz', 'ped', 'map'))]:
return bomb(
f'No vcf or plink files found at path = {abspath(my_parser().filePath)}\n'
)
genotypes.append(row)
elif toto == 2:
for n, a in enumerate(geno):
try:
geno_tot.append(plink_ACGT[plink_info[n][0]][int(a)])
except KeyError:
pass
geno_out.write(
'%s %s \n' %
(' '.join([sample_id, sample_id, '0', '0', '2', '-9'
]), ' '.join(geno_tot)))
# continue writing VCF
if toto == 1:
for row in zip(vcfsnps, [*zip(*genotypes)]):
line = [list(flatten(i)) for i in list(row)]
geno_out.write('\t'.join(flatten(line)) + '\n')
# Map file for Ped
if toto == 2:
map_out = open(fo + ".map", "w")
map_ped = []
for marker in snps: # snps is a list need to ammend this
try:
ms = vcf_a1a2[marker][0:3]
ms.insert(0, '0')
ms = [ms[i] for i in [1, 3, 0, 2]]
map_ped.append(ms)
except KeyError:
ms = snps[marker]
ms.insert(0, '0')
within_file_sample_dups = {} # key=file, v = duplicated sample
between_file_sample_dups = {} # key=file, v = file_samples
between_file_chroms = {} # key=file, v = set(file_chroms)
for index, file_ in enumerate(file_list):
if str(file_list[index]).endswith("vcf.gz"):
command0 = "zcat< " + file_list[index] + "|grep -m 1 '#CHR' |cut -f10-"
command1 = "zcat< " + file_list[index] + "| grep -v '#'|cut -f1-2"
chroms = [i[0] for i in std_capture(command1)]
snps = [':'.join(i) for i in std_capture(command1)]
within_file_snps_dups[file_list[index]] = snps
between_file_chroms[file_list[index]] = set(chroms)
samples = list(flatten(std_capture(command0)))
if len(samples) > len(set(samples)):
within_file_sample_dups[file_list[index]] = set([
x for x in samples if samples.count(x) > 1
]) # multimode(samples)
between_file_sample_dups[file_list[index]] = set(samples)
if str(file_list[index]).endswith("vcf"):
command0 = "cat " + file_list[index] + "|grep -m 1 '#CHR' |cut -f10-"
command1 = "cat " + file_list[index] + "| grep -v '#'|cut -f1-2"
chroms = [i[0] for i in std_capture(command1)]
snps = [':'.join(i) for i in std_capture(command1)]
within_file_snps_dups[file_list[index]] = snps
between_file_chroms[file_list[index]] = set(chroms)
except ValueError:
chrom, snpname, cm, pos = line.strip().split()
key = chrom + ":" + pos
if key not in markers:
markers[key] = [snpname] + mark_chip
if key in markers:
value = list(markers[key])
value[chip + 1] = snp_number + 1
markers[key] = value
# Create a comprehensive snps file
# Sort the snps by chrom then pos and write index
mark = []
for row in [list(flatten(i)) for i in list(markers.items())]:
row.insert(0, row[1])
row.insert(1, row[1].split(":")[0])
row.insert(2, row[2].split(":")[1])
row.pop(3)
row.pop(3)
mark.append(row)
'''
for row in mark:
print(row)
'''
mark = sorted(mark, key=lambda x: (int(x[1]), int(x[2])))
f_out = "snpinfo.txt"
mark_out = open(f_out, "w")
mark_out.write('marker bta pos chips...\n')
geno = []
chip = index + 1
snp_number = 0
with open_by_suffix(file_list[index]) as f:
for line in f:
if "##" in line: continue
# CHROM,POS,ID,REF,ALT,QUAL,FILTER,INFO,FORMAT,samples...
bta, pos, snp, ref, alt, qual, filter_, info, format_, genotype = line.strip(
).split("\t", 9)
bta = bta.replace('Chr', '')
geno.append(
list(
flatten([
vcf_2_fimpute.get(i, i) for i in [
ii.split(':')[0].replace("|", "/")
for ii in genotype.split('\t')
]
])))
if bta != '#CHROM ' and pos != 'POS':
if bta + ":" + pos not in snps_list:
snps_list[bta + ":" +
pos] = [bta, snp, "0", pos, ref, alt]
elif bta + ":" + pos in snps_list and snps_list[
bta + ":" + pos][4].lower() != ref.lower():
print(
'Some REF/ALT may be flipped \n'
'Normalize VCF files e.g. `bcftools norm -f [REF_GENOME] ... `\n'
)
raise SystemExit