def test_shift_overaligned(self):
# qwertyuiopas---kkkkk------dfghjklzxcvbnm
# .......... ................
gene = Gene('1', 1, 1000, strand='+')
transcript = PreTranscript(exons=[(1, 12), (20, 28)], gene=gene, strand='+')
for spl_patt in transcript.generate_splicing_patterns():
transcript.transcripts.append(Transcript(transcript, spl_patt))
gene.transcripts.append(transcript)
read = SamRead(
reference_name='1',
reference_start=0,
cigar=_cigar.convert_string_to_cigar('14=7D12='),
query_sequence='qwertyuiopasdfghjklzxcvbnm',
)
evidence = TranscriptomeEvidence(
annotations={},
reference_genome={'1': MockObject(seq='qwertyuiopasdfkkkkkdfghjklzxcvbnm')},
bam_cache=MockObject(get_read_reference_name=lambda r: r.reference_name),
break1=Breakpoint('1', 1, orient='L', strand='+'),
break2=Breakpoint('1', 10, orient='R', strand='+'),
read_length=75,
stdev_fragment_size=75,
median_fragment_size=220,
)
evidence.overlapping_transcripts.add(transcript)
new_read = evidence.standardize_read(read)
assert new_read.cigar == _cigar.convert_string_to_cigar('12=7N14=')
def setUp(self):
b1 = Breakpoint('1', 1051, 1051, 'L')
b2 = Breakpoint('1', 1551, 1551, 'R')
self.read_length = 50
self.trans_ev = TranscriptomeEvidence(
{}, # fake the annotations
b1,
b2,
None,
None, # bam_cache and reference_genome
opposing_strands=False,
read_length=self.read_length,
stdev_fragment_size=100,
median_fragment_size=100,
stdev_count_abnormal=1,
)
self.genomic_ev = GenomeEvidence(
b1,
b2,
None,
None, # bam_cache and reference_genome
opposing_strands=False,
read_length=self.read_length,
stdev_fragment_size=100,
median_fragment_size=100,
stdev_count_abnormal=1,
)
def trans_evidence(read_length):
return TranscriptomeEvidence(
{}, # fake the annotations
Breakpoint('1', 1051, 1051, 'L'),
Breakpoint('1', 1551, 1551, 'R'),
None,
None, # bam_cache and reference_genome
opposing_strands=False,
read_length=read_length,
stdev_fragment_size=100,
median_fragment_size=100,
config={'validate.stdev_count_abnormal': 1},
)
def test_shift_no_transcripts(self):
read = SamRead(reference_name='1',
reference_start=0,
cigar=_cigar.convert_string_to_cigar('14=7D18='),
query_sequence='qwertyuiopasdfdfghjklzxcvbnm')
evidence = TranscriptomeEvidence(
annotations={},
reference_genome={
'1': MockObject(seq='qwertyuiopasdfkkkkkdfghjklzxcvbnm')
},
bam_cache=None,
break1=Breakpoint('1', 1, orient='L', strand='+'),
break2=Breakpoint('1', 10, orient='R', strand='+'),
read_length=75,
stdev_fragment_size=75,
median_fragment_size=220)
new_cigar = evidence.exon_boundary_shift_cigar(read)
self.assertEqual(_cigar.convert_string_to_cigar('14=7D18='), new_cigar)