def __init__(self,
contig,
cutout,
score=None,
cigar=None,
strand=1,
match=1,
mismatch=2,
gapopen=5,
gapextend=0):
if score is None:
score, cigar, strand = align_both_strands(cutout, contig, match,
mismatch, gapopen,
gapextend)
self.contig = contig
self.cutout = cutout
self.score = score
self.strand = strand
self.matedist = None
self.tok = AlignmentTokenizer(self.varseq, self.refrseq, cigar)
self.cigar = self.tok._cigar
self.vartype = None
snvpattern = r'^((\d+)([DI]))?(\d+)M((\d+)[DI])?$'
indelpattern = r'^((\d+)([DI]))?(\d+)M(\d+)([ID])(\d+)M((\d+)[DI])?$'
if re.search(snvpattern, self.cigar):
self.vartype = 'snv'
elif re.search(indelpattern, self.cigar):
self.vartype = 'indel'
def test_nomargin():
qfile = kevlar.open(data_file('nomargin-r-indel-contigs.augfasta'), 'r')
tfile = kevlar.open(data_file('nomargin-r-gdna.fa'), 'r')
query = next(kevlar.parse_augmented_fastx(qfile))
target = next(kevlar.parse_augmented_fastx(tfile))
cigar, score = kevlar.align(target.sequence, query.sequence)
tok = AlignmentTokenizer(query.sequence, target.sequence, cigar)
assert tok._cigar == tok._origcigar
def test_gap_center_aligned(contig, gdna, newcigar, origcigar, nblocks):
qfile = kevlar.open(data_file('cigar/' + contig), 'r')
tfile = kevlar.open(data_file('cigar/' + gdna), 'r')
query = next(kevlar.parse_augmented_fastx(qfile))
target = next(kevlar.parse_augmented_fastx(tfile))
cigar, score = kevlar.align(target.sequence, query.sequence)
tok = AlignmentTokenizer(query.sequence, target.sequence, cigar)
assert len(tok.blocks) == nblocks
assert tok._cigar == newcigar
assert tok._origcigar == origcigar
def test_gap_center_aligned():
query = next(
kevlar.parse_augmented_fastx(
kevlar.open(data_file('cigar/b.contig.fa'), 'r')))
target = next(
kevlar.parse_augmented_fastx(
kevlar.open(data_file('cigar/b.gdna.fa'), 'r')))
cigar, score = kevlar.align(target.sequence, query.sequence)
tok = AlignmentTokenizer(query.sequence, target.sequence, cigar)
assert len(tok.blocks) == 3
assert tok._cigar == '41D150M50D'
assert tok._origcigar == '41D144M50D6M'
def test_blocks(contig, gdna):
query = next(kevlar.parse_augmented_fastx(kevlar.open(contig, 'r')))
target = next(kevlar.parse_augmented_fastx(kevlar.open(gdna, 'r')))
cigar, score = kevlar.align(target.sequence, query.sequence)
tok = AlignmentTokenizer(query.sequence, target.sequence, cigar)
for block in tok.blocks:
assert block.type in ('M', 'D', 'I')
if block.type in ('M', 'D'):
assert len(block.target) == block.length
else:
assert block.target is None
if block.type in ('M', 'I'):
assert len(block.query) == block.length
else:
assert block.query is None
def __init__(self,
contig,
cutout,
score=None,
cigar=None,
strand=1,
match=1,
mismatch=2,
gapopen=5,
gapextend=0,
homopolyfilt=True,
nocall=False):
if score is None and not nocall:
score, cigar, strand = align_both_strands(cutout, contig, match,
mismatch, gapopen,
gapextend)
self.contig = contig
self.cutout = cutout
self.nocall = nocall
self.vartype = None
if nocall:
self.score = 0
return
self.score = score
self.strand = strand
self.do_homopolymer_filter = homopolyfilt
self.trimmed = 0
self.tok = AlignmentTokenizer(self.varseq, self.refrseq, cigar)
self.cigar = self.tok._cigar
snvpattern = r'^((\d+)([DI]))?(\d+)M((\d+)[DI])?$'
indelpattern = r'^((\d+)([DI]))?(\d+)M(\d+)([ID])(\d+)M((\d+)[DI])?$'
if re.search(snvpattern, self.cigar):
self.vartype = 'snv'
elif re.search(indelpattern, self.cigar):
self.vartype = 'indel'