def varpileup_line2vcf_line(pileupfields):
""" Converts Variant Pileup format to VCF format """
t = '\t'
chr = str(pileupfields[0])
pos = str(pileupfields[1])
ref = str(pileupfields[2])
alt = str(pileupfields[3])
consqual = str(pileupfields[4])
snpqual = str(pileupfields[5])
mapqual = str(pileupfields[6])
depth = str(pileupfields[7])
alt_count = str(count_alt(depth, pileupfields[8]))
GT = '1/1'
if fu.isOnTheList(HETERO.keys(), alt):
GT = '0/1'
alt = hetero2homo(ref, alt)
# 4 - Phred-scaled likelihood that the genotype is wrong, which is also called `consensus quality'.
# 5 - Phred-scaled likelihood that the genotype is identical to the reference, which is also called `SNP quality'.
# Suppose the reference base is A and in alignment we see 17 G and 3 A. We will get a low consensus quality because
# it is difficult to distinguish an A/G heterozygote from a G/G homozygote. We will get a high SNP quality, though,
# because the evidence of a SNP is very strong.
# 6 - root mean square (RMS) mapping quality
return chr + t + pos + t + '.' + t + ref + t + alt + t + mapqual + t + 'PASS' + t + '.' + t + 'GT:GQ:DP:AD' + t + GT + ':' + consqual + ':' + depth + ':' + alt_count
def varpileup_line2vcf_line(pileupfields):
""" Converts Variant Pileup format to VCF format """
t='\t'
chr=str(pileupfields[0])
pos=str(pileupfields[1])
ref=str(pileupfields[2])
alt=str(pileupfields[3])
consqual=str(pileupfields[4])
snpqual=str(pileupfields[5])
mapqual=str(pileupfields[6])
depth=str(pileupfields[7])
alt_count=str(count_alt(depth, pileupfields[8]))
GT='1/1'
if fu.isOnTheList(HETERO.keys(), alt):
GT='0/1'
alt=hetero2homo(ref,alt)
# 4 - Phred-scaled likelihood that the genotype is wrong, which is also called `consensus quality'.
# 5 - Phred-scaled likelihood that the genotype is identical to the reference, which is also called `SNP quality'.
# Suppose the reference base is A and in alignment we see 17 G and 3 A. We will get a low consensus quality because
# it is difficult to distinguish an A/G heterozygote from a G/G homozygote. We will get a high SNP quality, though,
# because the evidence of a SNP is very strong.
# 6 - root mean square (RMS) mapping quality
return chr+t+pos+t+'.' +t+ ref +t+ alt +t+ mapqual +t+ 'PASS' +t+ '.' + t + 'GT:GQ:DP:AD'+t+GT+':'+consqual+':'+depth+':'+alt_count
def hetero2homo(ref, alt):
""" Converts heterozygous symbols from Samtools pileup to A, G, T, C """
if fu.isOnTheList(HETERO.keys(), alt) == False:
return alt
else:
alt_x=HETERO[alt]
if str(ref)==str(alt_x)[0]:
return str(alt_x)[1]
else:
return str(alt_x)[0]
def hetero2homo(ref, alt):
""" Converts heterozygous symbols from Samtools pileup to A, G, T, C """
if fu.isOnTheList(HETERO.keys(), alt) == False:
return alt
else:
alt_x = HETERO[alt]
if str(ref) == str(alt_x)[0]:
return str(alt_x)[1]
else:
return str(alt_x)[0]
def varpileup_line2vcf_line(pileupfields):
""" Converts Variant Pileup format to VCF format """
t = '\t'
chr = str(pileupfields[0])
pos = str(pileupfields[1])
ref = str(pileupfields[2])
alt = str(pileupfields[3])
consqual = str(pileupfields[4])
snpqual = str(pileupfields[5])
mapqual = str(pileupfields[6])
depth = str(pileupfields[7])
alt_count = str(count_alt(depth, pileupfields[8]))
GT = '1/1'
if fu.isOnTheList(HETERO.keys(), alt):
GT = '0/1'
alt = hetero2homo(ref, alt)
return chr + t + pos + t + '.' + t + ref + t + alt + t + mapqual + \
t + 'PASS' + t + '.' + t + 'GT:GQ:DP:AD' + t + GT + ':' + \
consqual + ':' + depth + ':' + alt_count
def addOverlapWithGadAll(vcf,
format='vcf',
table='gadAll',
tmpextin='',
tmpextout='.1',
sep='\t'):
basefile = vcf
vcf = basefile + tmpextin
outfile = basefile + tmpextout
fh_out = open(outfile, "w")
fh = open(vcf)
logcountfile = basefile + '.count.log'
fh_log = open(logcountfile, 'a')
var_count = 0
line_count = 0
inds = getFormatSpecificIndices(format=format)
conn = u.db_connect()
cursor = conn.cursor()
linenum = 1
for line in fh:
line = line.strip()
## not comments
if not line.startswith("##"):
#header line
if (line.startswith('CHROM') or line.startswith('#CHROM')):
fh_out.write(line + '\n')
else:
fields = line.split(sep)
chr = fields[inds[0]].strip()
# For some reason this table has no "chr" preceeding number
if chr.startswith("chr"):
chr = str(chr).replace("chr", "")
pos = fields[inds[1]].strip()
isOverlap = False
sql = 'select * from ' + table + ' where chromosome="' + \
str(chr) + '" AND (chromStart <= ' + str(pos) + \
' AND ' + str(pos) + ' <= chromEnd);'
cursor.execute(sql)
rows = cursor.fetchall()
records = []
if (len(rows) > 0):
records_count = 1
line_count = line_count + 1
r_tmp = []
for row in rows:
var_count = var_count + 1
if not fu.isOnTheList(r_tmp, str(row[3])):
r_tmp.append(str(row[3]))
records.append(str(table) + '=' + str(row[3]))
records_count = records_count + 1
if str(fields[7]).endswith(';'):
fields[7] = fields[7] + ';'.join(records)
else:
fields[7] = fields[7] + ';' + ';'.join(records)
fh_out.write('\t '.join(fields) + '\n')
else:
fh_out.write(line + '\n')
linenum = linenum + 1
else:
fh_out.write(line + '\n')
fh_log.write(f"In {str(table)}: {str(var_count)} in " + \
f"{str(line_count)} variants\n")
fh_log.close()
conn.close()
fh.close()
fh_out.close()
def addOverlapWitHUGOGeneNomenclature(vcf,
format='vcf',
table='hugo',
tmpextin='',
tmpextout='.1',
sep='\t'):
basefile = vcf
vcf = basefile + tmpextin
outfile = basefile + tmpextout
fh_out = open(outfile, "w")
fh = open(vcf)
logcountfile = basefile + '.count.log'
fh_log = open(logcountfile, 'a')
var_count = 0
line_count = 0
inds = getFormatSpecificIndices(format=format)
conn = u.db_connect()
cursor = conn.cursor()
linenum = 1
for line in fh:
line = line.strip()
## not comments
if not line.startswith("##"):
#header line
if (line.startswith('CHROM') or line.startswith('#CHROM')):
fh_out.write(line + '\n')
else:
fields = line.split(sep)
chr = fields[inds[0]].strip()
if not chr.startswith("chr"):
chr = "chr" + chr
pos = fields[inds[1]].strip()
isOverlap = False
sql = 'select * from ' + table + ' where chrom="' + \
str(chr) + '" AND (chromStart <= ' + str(pos) + \
' AND ' + str(pos) + ' <= chromEnd);'
cursor.execute(sql)
rows = cursor.fetchall()
records = []
if (len(rows) > 0):
line_count = line_count + 1
records_count = 1
r_tmp = []
for row in rows:
var_count = var_count + 1
t = str(str(row[5]) + ',' + str(row[6])).strip()
if not fu.isOnTheList(r_tmp, t):
r_tmp.append(t)
records.append('HGNC_GeneAnnotation' + '=' + t)
records_count = records_count + 1
records_str = ','.join(records).replace(';', ',')
if str(fields[7]).endswith(';'):
fields[7] = fields[7] + records_str
else:
fields[7] = fields[7] + ';' + records_str
fh_out.write('\t'.join(fields) + '\n')
else:
fh_out.write(line + '\n')
linenum = linenum + 1
else:
fh_out.write(line + '\n')
fh_log.write(f"In {str(table)}: {str(var_count)} in " + \
f"{str(line_count)} variants\n")
fh_log.close()
conn.close()
fh.close()
fh_out.close()