def Variants(self, chromosome, start, end):
"""
Generator funtion. Yields variants in order of
genomic co-ordinate.
"""
vcfLines = None
varList = []
maxSize = self.options.maxSize
for vcfFile in self.vcfFiles:
try:
vcfLines = vcfFile.fetch(chromosome,
start,
end,
parser=ctabix.asVCF())
except Exception as e:
logger.warning(
"Could not retrieve variants from source file in region %s:%s-%s. Error was %s"
% (chromosome, start, end, e))
continue
for line in vcfLines:
if not isValidVcfLine(line):
continue
# Get the components of the VCF line
chrom = line.contig
pos = line.pos
ref = line.ref
altCol = line.alt
alts = altCol.split(",")
lenRef = len(ref)
for alt in alts:
lenAlt = len(alt)
varSize = abs(lenAlt - lenRef)
if varSize > maxSize:
logger.debug(
"Skipping large variant of size %s in source file. Maximum allowed variant size is %s"
% (varSize, maxSize))
continue
# SNP
if lenRef == 1 and lenAlt == 1:
var = Variant(chromosome, pos, ref, alt, 0, FILE_VAR)
varList.append(var)
# MNP
elif lenRef == lenAlt:
# MNPs may leading and/or trailing bases trimming
#var = Variant(chromosome, pos, ref, alt, 0, FILE_VAR)
#varList.append(var)
tempRef = ref
tempAlt = alt
tempPos = pos
removed = tempRef
added = tempAlt
# Trim leading bases
while len(tempRef) > 0 and len(
tempAlt) > 0 and tempRef[0] == tempAlt[0]:
tempRef = tempRef[1:]
tempAlt = tempAlt[1:]
removed = tempRef
added = tempAlt
tempPos += 1
# Trim trailing bases
while len(tempRef) > 0 and len(
tempAlt) > 0 and tempRef[-1] == tempAlt[-1]:
tempRef = tempRef[:-1]
tempAlt = tempAlt[:-1]
removed = tempRef
added = tempAlt
var = Variant(chromosome, tempPos, removed, added, 0,
FILE_VAR)
varList.append(var)
# Anything else
else:
if self.options.longHaps == 1:
var = Variant(chromosome, pos, ref, alt, 0,
FILE_VAR)
varList.append(var)
continue
# VCF4 is -1 indexed for indels, so trim off first base
tempRef = ref[1:]
tempAlt = alt[1:]
tempPos = pos
removed = tempRef
added = tempAlt
# Trim the matching bits off and shift position. This will decompose
# multi-variant sites into individual alleles at different positions.
while len(tempRef) > 0 and len(
tempAlt) > 0 and tempRef[0] == tempAlt[0]:
tempRef = tempRef[1:]
tempAlt = tempAlt[1:]
removed = tempRef
added = tempAlt
tempPos += 1
# Skip weird cases for now
#if len(removed) != 0 and len(added) != 0:
# continue
#logger.error("Dodgy variant found at %s:%s, with ref=%s, alt = %s" %(chrom,pos,ref,alt))
#logger.error("This will probably break something later on...")
var = Variant(chromosome, tempPos, removed, added, 0,
FILE_VAR)
varList.append(var)
varList = sorted(list(set(varList)))
logger.debug("Found %s variants in region %s in source file" %
(len(varList), "%s:%s-%s" % (chromosome, start, end)))
return varList
def Variants(self, chromosome, start, end):
"""
Generator funtion. Yields variants in order of
genomic co-ordinate.
"""
vcfLines = None
varList = []
maxSize = self.options.maxSize
for vcfFile in self.vcfFiles:
try:
vcfLines = vcfFile.fetch(chromosome, start, end, parser=ctabix.asVCF())
except Exception, e:
logger.warning("Could not retrieve variants from source file in region %s:%s-%s. Error was %s" %(chromosome,start,end,e))
continue
for line in vcfLines:
if not isValidVcfLine(line):
continue
# Get the components of the VCF line
chrom = line.contig
pos = line.pos
ref = line.ref
altCol = line.alt
alts = altCol.split(",")
lenRef = len(ref)
for alt in alts:
lenAlt = len(alt)
varSize = abs(lenAlt - lenRef)
if varSize > maxSize:
logger.debug("Skipping large variant of size %s in source file. Maximum allowed variant size is %s" %(varSize, maxSize))
continue
# SNP
if lenRef == 1 and lenAlt == 1:
var = Variant(chromosome, pos, ref, alt, 0, FILE_VAR)
varList.append(var)
# MNP
elif lenRef == lenAlt:
# MNPs may leading and/or trailing bases trimming
#var = Variant(chromosome, pos, ref, alt, 0, FILE_VAR)
#varList.append(var)
tempRef = ref
tempAlt = alt
tempPos = pos
removed = tempRef
added = tempAlt
# Trim leading bases
while len(tempRef) > 0 and len(tempAlt) > 0 and tempRef[0] == tempAlt[0]:
tempRef = tempRef[1:]
tempAlt = tempAlt[1:]
removed = tempRef
added = tempAlt
tempPos +=1
# Trim trailing bases
while len(tempRef) > 0 and len(tempAlt) > 0 and tempRef[-1] == tempAlt[-1]:
tempRef = tempRef[:-1]
tempAlt = tempAlt[:-1]
removed = tempRef
added = tempAlt
var = Variant(chromosome, tempPos, removed, added, 0, FILE_VAR)
varList.append(var)
# Anything else
else:
# VCF4 is -1 indexed for indels, so trim off first base
tempRef = ref[1:]
tempAlt = alt[1:]
tempPos = pos
removed = tempRef
added = tempAlt
# Trim the matching bits off and shift position. This will decompose
# multi-variant sites into individual alleles at different positions.
while len(tempRef) > 0 and len(tempAlt) > 0 and tempRef[0] == tempAlt[0]:
tempRef = tempRef[1:]
tempAlt = tempAlt[1:]
removed = tempRef
added = tempAlt
tempPos +=1
# Skip weird cases for now
#if len(removed) != 0 and len(added) != 0:
# continue
#logger.error("Dodgy variant found at %s:%s, with ref=%s, alt = %s" %(chrom,pos,ref,alt))
#logger.error("This will probably break something later on...")
var = Variant(chromosome, tempPos, removed, added, 0, FILE_VAR)
varList.append(var)