def vcf(infileList, outfile):
with open(outfile, 'w') as vcfout:
headerWritten = False
for file_i in infileList:
with genome.open_textfile(file_i) as vcfin:
line_i = vcfin.readline()
while line_i.startswith('#'):
if not headerWritten:
vcfout.write(line_i)
line_i = vcfin.readline()
# Turn off header writing from now on:
headerWritten = True
while line_i:
vcfout.write(line_i)
line_i = vcfin.readline()
def tsv(infileList, outfile):
with open(outfile, 'w') as tsvout:
headerWritten = False
for file_i in infileList:
with genome.open_textfile(file_i) as tsvin:
# First line is a header
line_i = tsvin.readline()
if not headerWritten:
tsvout.write(line_i)
# Turn off header writing from now on:
headerWritten = True
line_i = tsvin.readline()
while line_i:
tsvout.write(line_i)
line_i = tsvin.readline()
right_files = [i + '.vcf' + gz for i in chosen_chrom_sequence]
else:
right_files = (args.input_vcf)
# Open files:
if args.call_method == 'VarDict':
snpout = open(out_snp, 'w')
indelout = open(out_indel, 'w')
else:
vcfout = open(out_vcf, 'w')
### First, get the header. IF there are multiple VCF files (e.g., chromosome by chromosome), use the first file for this purpose:
vcf_header = []
with genome.open_textfile(right_files[0]) as vcf:
line_i = vcf.readline().rstrip()
# Save the headers and then sort them:
vcfheader_filter_info_filter = []
vcfheader_filter_info_filter.append(
'##INFO=<ID={0},Number=0,Type=Flag,Description="Indicates if record is a {0} called somatic mutation">'
.format(args.call_method))
vcfheader_misc = []
while line_i.startswith('#'):
if re.match(r'##fileformat=', line_i):
vcffileformat = line_i
header_append = []
format_append = []
if args.pileup_DP4:
header_append.append('##FORMAT=<ID=plDP4,Number=4,Type=Integer,Description="DP4 from pileup: ref forward, ref reverse, alt forward, alt reverse">')
format_append.append('plDP4')
if args.pileup_variant_allele_frequency:
header_append.append('##FORMAT=<ID=plVAF,Number=1,Type=Float,Description="Variant allele frequency calculated from pileup">')
format_append.append('plVAF')
# Start Working by opening files:
try:
my_vcf = genome.open_textfile(my_vcf)
Tpileup = genome.open_textfile(Tpileup)
outhandle = open(outfile, 'w')
Npileup = genome.open_textfile(Npileup)
except AttributeError:
pass
if Npileup:
npileup_line = Npileup.readline().rstrip('\n')
if Tpileup:
tpileup_line = Tpileup.readline().rstrip('\n')
# Add the extra headers:
out_vcf_headers = genome.vcf_header_modifier( my_vcf, addons=header_append )
'--snv-out',
type=str,
help='Output VCF file',
required=True)
# Parse the arguments:
args = parser.parse_args()
infile = args.input_vcf
indel_out = args.indel_out
snv_out = args.snv_out
info_to_split = 'NLOD', 'TLOD'
info_to_keep = 'STR', 'ECNT'
with genome.open_textfile(infile) as vcf_in, open(
snv_out, 'w') as snv_out, open(indel_out, 'w') as indel_out:
line_i = vcf_in.readline().rstrip()
while line_i.startswith('##'):
snv_out.write(line_i + '\n')
indel_out.write(line_i + '\n')
if line_i.startswith('##normal_sample='):
normal_name = line_i.split('=')[1]
if line_i.startswith('##tumor_sample='):
tumor_name = line_i.split('=')[1]
for combo_i in itertools.product( (True, False), repeat = len(tools) ):
# The four zeros represent [Total, dbsnp, COMMON, COSMIC]
MVJS_combinations[combo_i] = [0, 0, 0, 0]
# Keeping a tab on all those scores
bina_score_tally = {}
subscore_evidence_tally = {}
bonus_knowledge_tally = {}
penalty_knowledge_tally = {}
num_methods_tally = {}
with genome.open_textfile(args.input_vcf) as vcf, open(args.output_vcf, 'w') as vcf_out:
line_i = vcf.readline().rstrip()
while line_i.startswith('#'):
# Read thru the headers and metadata:
if line_i.startswith('#CHROM'):
header_item = line_i.split('\t')
if len(header_item) == 11:
paired_mode = True
idxN, idxT = 0,1
elif len(header_item) == 10:
paired_mode = False
# Open files:
if args.call_method == 'VarDict':
snpout = open(out_snp, 'w')
indelout = open(out_indel, 'w')
else:
vcfout = open(out_vcf, 'w')
# First, get the header. IF there are multiple VCF files (e.g., chromosome by
# chromosome), use the first file for this purpose:
vcf_header = []
with genome.open_textfile(right_files[0]) as vcf:
line_i = vcf.readline().rstrip()
# Save the headers and then sort them:
vcfheader_filter_info_filter = []
vcfheader_filter_info_filter.append('##INFO=<ID={0},Number=0,Type=Flag,Description="Indicates if record is a {0} called somatic mutation">'.format(args.call_method))
vcfheader_misc = []
while line_i.startswith('#'):
if re.match(r'##fileformat=', line_i):
vcffileformat = line_i
elif re.match(r'^##FORMAT=<ID=DP4,', line_i):
'--output-vcf',
type=str,
help='Output VCF file',
required=True,
default=None)
parser.add_argument('-tools',
'--individual-mutation-tools',
type=str,
help='A list tools to sub-sample',
nargs='*',
required=True)
args = parser.parse_args()
subtools = set(args.individual_mutation_tools)
with genome.open_textfile(args.input_vcf) as vcfin, open(args.output_vcf,
'w') as vcfout:
line_i = vcfin.readline().rstrip('\n')
while line_i.startswith('#'):
vcfout.write(line_i + '\n')
line_i = vcfin.readline().rstrip('\n')
while line_i:
vcf_i = genome.Vcf_line(line_i)
if 'FalseNegative' in vcf_i.identifier:
vcfout.write(line_i + '\n')
else:
tools = vcf_i.get_info_value('SOURCES')
parser.add_argument('-threshold',
'--phasing-threshold',
type=int,
help='How far apart do we try to phase',
required=False,
default=1)
args = parser.parse_args()
infile = args.input_vcf_file
bam = args.bam_file
ref_fa = args.genome_reference
outfile = args.output_vcf_file
threshold = args.phasing_threshold
with genome.open_textfile(infile) as infile, \
pysam.AlignmentFile(bam) as bam, \
open(outfile, 'w') as outfile, \
pysam.FastaFile(ref_fa) as ref_fa:
my_line = infile.readline().rstrip()
while my_line.startswith('##'):
outfile.write(my_line + '\n')
my_line = infile.readline().rstrip()
# This is to read through and copy the #CHROM line
assert my_line.startswith('#CHROM')
outfile.write(
'##INFO=<ID=COORDINATES,Number=.,Type=Integer,Description="Coordinates of the bases">\n'
)
# Variant Call Type, i.e., snp or indel
parser.add_argument('-infile', '--input-vcf', type=str, help='Input VCF file', required=True)
parser.add_argument('-indel', '--indel-out', type=str, help='Output VCF file', required=True)
parser.add_argument('-snv', '--snv-out', type=str, help='Output VCF file', required=True)
# Parse the arguments:
args = parser.parse_args()
infile = args.input_vcf
indel_out = args.indel_out
snv_out = args.snv_out
info_to_split = 'NLOD', 'TLOD'
info_to_keep = 'STR', 'ECNT'
with genome.open_textfile(infile) as vcf_in, open(snv_out, 'w') as snv_out, open(indel_out, 'w') as indel_out:
line_i = vcf_in.readline().rstrip()
while line_i.startswith('##'):
snv_out.write( line_i + '\n' )
indel_out.write( line_i + '\n' )
if line_i.startswith('##normal_sample='):
normal_name = line_i.split('=')[1]
if line_i.startswith('##tumor_sample='):
tumor_name = line_i.split('=')[1]
line_i = vcf_in.readline().rstrip()
args = parser.parse_args()
infile = args.input_vcf
outfile = args.output_vcf
# Seperate output into snv/snp and indel's:
out_snp_file = outfile.split(os.sep)
out_snp_file[-1] = 'snp.' + out_snp_file[-1]
out_indel_file = outfile.split(os.sep)
out_indel_file[-1] = 'indel.' + out_indel_file[-1]
out_snp = os.sep.join(out_snp_file)
out_indel = os.sep.join(out_indel_file)
with genome.open_textfile(infile) as vcf, \
open(out_snp, 'w') as snpout, \
open(out_indel, 'w') as indelout:
line_i = vcf.readline().rstrip()
while line_i.startswith('##'):
if re.match(r'^##INFO=<ID=(LSEQ|RSEQ),', line_i):
line_i = line_i.replace('Number=G', 'Number=1')
elif line_i.startswith('##FORMAT=<ID=BIAS,'):
line_i = line_i.replace('Number=1', 'Number=.')
elif line_i.startswith('##FORMAT=<ID=PSTD,') or \
line_i.startswith('##FORMAT=<ID=QSTD,') or \
import genomic_file_handlers as genome
parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
# Variant Call Type, i.e., snp or indel
parser.add_argument('-infile', '--input-vcf', type=str, help='Input VCF file', required=True)
parser.add_argument('-outfile', '--output-vcf', type=str, help='Output VCF file', required=True)
# Parse the arguments:
args = parser.parse_args()
infile = args.input_vcf
outfile = args.output_vcf
with genome.open_textfile(infile) as vcf_in, open(outfile, 'w') as vcf_out:
line_i = vcf_in.readline().rstrip()
while line_i.startswith('##'):
vcf_out.write( line_i + '\n' )
line_i = vcf_in.readline().rstrip()
# This is the #CHROM line:
headers = line_i.split('\t')
num_columns = len(headers)
vcf_out.write( line_i + '\n' )
line_i = vcf_in.readline().rstrip()
while line_i:
parser.add_argument('-snv', '--snv-out', type=str, help='Output VCF file', required=True)
parser.add_argument('-indel', '--indel-out', type=str, help='Output VCF file', required=True)
parser.add_argument('-tnscope', '--is-tnscope', action="store_true", help='Actually TNscope VCF', required=False, default=False)
# Parse the arguments:
args = parser.parse_args()
infile = args.input_vcf
indel_out = args.indel_out
snv_out = args.snv_out
info_to_split = 'NLOD', 'TLOD'
info_to_keep = 'STR', 'ECNT'
with genome.open_textfile(infile) as vcf_in, open(snv_out, 'w') as snv_out, open(indel_out, 'w') as indel_out:
line_i = vcf_in.readline().rstrip()
while line_i.startswith('##'):
if line_i.startswith('##normal_sample='):
normal_name = line_i.split('=')[1]
if line_i.startswith('##tumor_sample='):
tumor_name = line_i.split('=')[1]
if line_i.startswith('##INFO=<ID=SOR,'):
line_i = re.sub(r'Float', 'String', line_i)
snv_out.write( line_i + '\n' )
'--somaticseq-trained',
action='store_true',
help=
'If true, will use the QUAL as SomaticSeq score. Otherwise, SCORE will be .',
required=False,
default=False)
args = parser.parse_args()
vcf_in_fn = args.vcf_in
vcf_out_fn = args.vcf_out
caller_string = args.callers_classification_string
tumor = args.tumor_sample_name
somaticseq_trained = args.somaticseq_trained
with genome.open_textfile(vcf_in_fn) as vcfin, open(vcf_out_fn, 'w') as vcfout:
line_in = vcfin.readline().rstrip('\n')
while line_in.startswith('##'):
if line_in.startswith('##SomaticSeq='):
line_out = line_in + '-SEQC2'
elif line_in.startswith('##INFO=<ID=NUM_TOOLS') or line_in.startswith(
'##INFO=<ID={COMBO}'.format(COMBO=caller_string)):
line_out = re.sub('##INFO=', '##FORMAT=', line_in)
else:
line_out = line_in
header_append = []
format_append = []
if args.pileup_DP4:
header_append.append('##FORMAT=<ID=plDP4,Number=4,Type=Integer,Description="DP4 from pileup: ref forward, ref reverse, alt forward, alt reverse">')
format_append.append('plDP4')
if args.pileup_variant_allele_frequency:
header_append.append('##FORMAT=<ID=plVAF,Number=1,Type=Float,Description="Variant allele frequency calculated from pileup">')
format_append.append('plVAF')
# Start Working by opening files:
try:
my_vcf = genome.open_textfile(my_vcf)
Tpileup = genome.open_textfile(Tpileup)
outhandle = open(outfile, 'w')
Npileup = genome.open_textfile(Npileup)
except AttributeError:
pass
if Npileup:
npileup_line = Npileup.readline().rstrip('\n')
if Tpileup:
tpileup_line = Tpileup.readline().rstrip('\n')
# Add the extra headers:
out_vcf_headers = genome.vcf_header_modifier( my_vcf, addons=header_append )
{tBAM_ALT_Clipped_Reads}\t\
{tBAM_Clipping_FET}\t\
{tBAM_MQ0}\t\
{tBAM_Other_Reads}\t\
{tBAM_Poor_Reads}\t\
{tBAM_REF_InDel_3bp}\t\
{tBAM_REF_InDel_2bp}\t\
{tBAM_REF_InDel_1bp}\t\
{tBAM_ALT_InDel_3bp}\t\
{tBAM_ALT_InDel_2bp}\t\
{tBAM_ALT_InDel_1bp}\t\
{InDel_Length}\t\
{TrueVariant_or_False}'
## Running
with genome.open_textfile(mysites) as my_sites, open(outfile,
'w') as outhandle:
my_line = my_sites.readline().rstrip()
bam = pysam.AlignmentFile(bam_fn, reference_filename=ref_fa)
ref_fa = pysam.FastaFile(ref_fa)
if truth:
truth = genome.open_textfile(truth)
truth_line = truth.readline().rstrip()
while truth_line.startswith('#'):
truth_line = truth.readline().rstrip()
if cosmic:
cosmic = genome.open_textfile(cosmic)
min_altMQ = args.min_altMQ
min_refBQ = args.min_refBQ
min_altBQ = args.min_altBQ
max_refNM = args.max_refNM
max_altNM = args.max_altNM
max_fetSB = args.max_fetSB
max_fetCD = args.max_fetCD
max_zMQ = args.max_zMQ
max_zBQ = args.max_zBQ
max_MQ0 = args.max_MQ0
min_VAF = args.min_VAF
min_DP = args.min_DP
min_varDP = args.min_varDP
with genome.open_textfile(infile) as vcf_in, open(outfile, 'w') as vcf_out:
line_i = vcf_in.readline().rstrip()
while line_i.startswith('##'):
vcf_out.write( line_i + '\n' )
line_i = vcf_in.readline().rstrip()
vcf_out.write( line_i + '\n' )
# This line will be #CHROM:
header = line_i.split('\t')
sample_index = header.index(sample) - 9
# This will be the first variant line:
parser.add_argument('-infile', '--vcf-in', type=str, help='VCF in', required=True)
parser.add_argument('-outfile', '--vcf-out', type=str, help='VCF out', required=True)
parser.add_argument('-callers', '--callers-classification-string', type=str, help='MVJSD or whatever', required=True)
parser.add_argument('-tumor', '--tumor-sample-name', type=str, help='tumor sample name', required=False, default='TUMOR')
parser.add_argument('-trained', '--somaticseq-trained', action='store_true', help='If true, will use the QUAL as SomaticSeq score. Otherwise, SCORE will be .', required=False, default=False)
args = parser.parse_args()
vcf_in_fn = args.vcf_in
vcf_out_fn = args.vcf_out
caller_string = args.callers_classification_string
tumor = args.tumor_sample_name
somaticseq_trained = args.somaticseq_trained
with genome.open_textfile(vcf_in_fn) as vcfin, open(vcf_out_fn, 'w') as vcfout:
line_in = vcfin.readline().rstrip('\n')
while line_in.startswith('##'):
if line_in.startswith('##SomaticSeq='):
line_out = line_in + '-SEQC2'
elif line_in.startswith('##INFO=<ID=NUM_TOOLS') or line_in.startswith('##INFO=<ID={COMBO}'.format(COMBO=caller_string)):
line_out = re.sub('##INFO=', '##FORMAT=', line_in)
else:
line_out = line_in
vcfout.write( line_out + '\n' )
