def main():
usage = """%prog <VCF file 1> <VCF file 2> ... <VCF file N>
l_sort
Author: Ryan Layer, Colby Chiang, & Ira Hall
Description: sort N VCF files into a single file
Version: 0.01
"""
if len(sys.argv) < 2:
exit(usage)
vcf_file_names = sys.argv[1:]
vcf_lines = []
vcf_headers = list()
for vcf_file_name in vcf_file_names:
samples = l_bp.parse_vcf(vcf_file_name, vcf_lines, vcf_headers)
for sample in samples:
vcf_headers.append("##SAMPLE=<ID=" + sample + ">\n")
vcf_headers.append("##INFO=<ID=SNAME,Number=.,Type=String," + \
"Description=\"Source sample name\">\n")
vcf_headers.append("##INFO=<ID=ALG,Number=1,Type=String," + \
"Description=\"Evidence PDF aggregation algorithm\">\n")
vcf_headers.append("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\t" + \
"VARIOUS\n")
vcf_headers = list(vcf_headers)
vcf_headers.sort(cmp=l_bp.header_line_cmp)
for h in vcf_headers:
print(h, end=' ')
vcf_lines.sort(cmp=l_bp.vcf_line_cmp)
for v in vcf_lines:
# if 'SVTYPE=BND' in v and (('--:' in v) != ('++' in v)):
# A = v.split('\t')
# neg_s = A[7].find('--:')
# pos_s = A[7].find('++:')
#
# if neg_s > 0:
# neg_e = neg_s + A[7][neg_s:].find(';')
# pre=A[7][:neg_s]
# mid=A[7][neg_s:neg_e]
# post=A[7][neg_e:]
# A[7] = pre + '++:0,' + mid + post
# else:
# pos_e = pos_s + A[7][pos_s:].find(';')
# pre=A[7][:pos_s]
# mid=A[7][pos_s:pos_e]
# post=A[7][pos_e:]
# A[7] = pre + mid + ',--:0' + post
# print '\t'.join(A)
# else:
print(v, end=' ')
def main():
usage ="""%prog <VCF file 1> <VCF file 2> ... <VCF file N>
l_sort
Author: Ryan Layer, Colby Chiang, & Ira Hall
Description: sort N VCF files into a single file
Version: 0.01
"""
if len(sys.argv) < 2:
exit(1)
vcf_file_names = sys.argv[1:]
vcf_lines = []
vcf_headers = list()
for vcf_file_name in vcf_file_names:
samples = l_bp.parse_vcf(vcf_file_name, vcf_lines, vcf_headers)
for sample in samples:
vcf_headers.append("##SAMPLE=<ID=" + sample + ">\n")
vcf_headers.append("##INFO=<ID=SNAME,Number=.,Type=String," + \
"Description=\"Source sample name\">\n")
vcf_headers.append("##INFO=<ID=ALG,Number=1,Type=String," + \
"Description=\"Evidence PDF aggregation algorithm\">\n")
vcf_headers.append("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\t" + \
"VARIOUS\n")
vcf_headers = list(vcf_headers)
vcf_headers.sort(cmp=l_bp.header_line_cmp)
for h in vcf_headers:
print h,
vcf_lines.sort(cmp=l_bp.vcf_line_cmp)
for v in vcf_lines:
# if 'SVTYPE=BND' in v and (('--:' in v) != ('++' in v)):
# A = v.split('\t')
# neg_s = A[7].find('--:')
# pos_s = A[7].find('++:')
#
# if neg_s > 0:
# neg_e = neg_s + A[7][neg_s:].find(';')
# pre=A[7][:neg_s]
# mid=A[7][neg_s:neg_e]
# post=A[7][neg_e:]
# A[7] = pre + '++:0,' + mid + post
# else:
# pos_e = pos_s + A[7][pos_s:].find(';')
# pre=A[7][:pos_s]
# mid=A[7][pos_s:pos_e]
# post=A[7][pos_e:]
# A[7] = pre + mid + ',--:0' + post
# print '\t'.join(A)
# else:
print v,
def l_cluster(file_name, percent_slop=0, fixed_slop=0):
v_id = 0
vcf_lines = []
vcf_headers = Set()
r = l_bp.parse_vcf(file_name, vcf_lines, vcf_headers, add_sname=False)
vcf_headers.add("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n")
sample_order = []
for header in vcf_headers:
if header[:8] == '##SAMPLE':
sample_order.append(header.rstrip()[13:-1])
#elif header[:8] == '##FORMAT':
#i,n,t=header[header.find('<')+1:header.find('>')].split(',')[0:3]
#print i,n,t
#exit(1)
vcf_headers = list(vcf_headers)
vcf_headers.sort(cmp=l_bp.header_line_cmp)
for h in vcf_headers:
print h,
BP_l = []
BP_sv_type = ''
BP_max_end_l = -1
BP_chr_l = ''
for l in vcf_lines:
b = l_bp.breakpoint(l,
percent_slop=percent_slop,
fixed_slop=fixed_slop)
if (len(BP_l) == 0) or \
((b.start_l <= BP_max_end_l) and \
(b.chr_l == BP_chr_l) and \
(b.sv_type == BP_sv_type)):
BP_l.append(b)
BP_max_end_l = max(BP_max_end_l, b.end_l)
BP_chr_l = b.chr_l
BP_sv_type = b.sv_type
else:
#print len(BP_l)
v_id = r_cluster(BP_l, sample_order, v_id)
BP_l = [b]
BP_max_end_l = b.end_l
BP_sv_type = b.sv_type
BP_chr_l = b.chr_l
if len(BP_l) > 0:
#print len(BP_l)
v_id = r_cluster(BP_l, sample_order, v_id)
def l_cluster(file_name, percent_slop=0, fixed_slop=0):
v_id = 0
vcf_lines = []
vcf_headers = Set()
r = l_bp.parse_vcf(file_name, vcf_lines, vcf_headers, add_sname=False)
vcf_headers.add("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\n")
sample_order = []
for header in vcf_headers:
if header[:8] == '##SAMPLE':
sample_order.append(header.rstrip()[13:-1])
#elif header[:8] == '##FORMAT':
#i,n,t=header[header.find('<')+1:header.find('>')].split(',')[0:3]
#print i,n,t
#exit(1)
vcf_headers = list(vcf_headers)
vcf_headers.sort(cmp=l_bp.header_line_cmp)
for h in vcf_headers:
print h,
BP_l = []
BP_sv_type = ''
BP_max_end_l = -1
BP_chr_l = ''
for l in vcf_lines:
b = l_bp.breakpoint(l,
percent_slop=percent_slop,
fixed_slop=fixed_slop)
if (len(BP_l) == 0) or \
((b.start_l <= BP_max_end_l) and \
(b.chr_l == BP_chr_l) and \
(b.sv_type == BP_sv_type)):
BP_l.append(b)
BP_max_end_l = max(BP_max_end_l, b.end_l)
BP_chr_l = b.chr_l
BP_sv_type = b.sv_type
else:
#print len(BP_l)
v_id = r_cluster(BP_l, sample_order, v_id)
BP_l = [b]
BP_max_end_l = b.end_l
BP_sv_type = b.sv_type
BP_chr_l = b.chr_l
if len(BP_l) > 0:
#print len(BP_l)
v_id = r_cluster(BP_l, sample_order, v_id)
def main():
usage ="""%prog <VCF file 1> <VCF file 2> ... <VCF file N>
l_sort
Author: Ryan Layer, Colby Chiang, & Ira Hall
Description: sort N VCF files into a single file
Version: 0.01
"""
if len(sys.argv) < 2:
exit(1)
vcf_file_names = sys.argv[1:]
vcf_lines = []
vcf_headers = Set()
vcf_headers.add("##INFO=<ID=SVNAME,Number=.,Type=String," + \
"Description=\"Source sample name\">\n")
vcf_headers.add("#CHROM\tPOS\tID\tREF\tALT\tQUAL\tFILTER\tINFO\t" + \
"VARIOUS\n")
for vcf_file_name in vcf_file_names:
samples = l_bp.parse_vcf(vcf_file_name, vcf_lines, vcf_headers)
for sample in samples:
vcf_headers.add("##SAMPLE=<ID=" + sample + ">\n")
vcf_headers = list(vcf_headers)
vcf_headers.sort(cmp=l_bp.header_line_cmp)
for h in vcf_headers:
print h,
vcf_lines.sort(cmp=l_bp.vcf_line_cmp)
for v in vcf_lines:
print v,