def test_two_pairs_unordered(self):
self.fastq1 = StringIO("""\
@A:B:C X:Y
ACGT
+
QUAL
@A:B:E X:Y
AAGT
+
QUAL
""")
self.fastq2 = StringIO("""\
@A:B:E Q:R
TAGA
+
LAUQ
@A:B:C Q:R
TTGG
+
LAUQ
""")
expected_reads = [
("A:B:C", ("X:Y", "ACGT", "QUAL"), ("Q:R", "TTGG", "LAUQ")),
("A:B:E", ("X:Y", "AAGT", "QUAL"), ("Q:R", "TAGA", "LAUQ"))
]
reader = FastqReader(self.fastq1, self.fastq2)
reads = list(reader)
self.assertEqual(expected_reads, reads)
def align_untrimmed_reads(fastq):
v3loop_ref = extract_v3loop_ref()
score_counts = Counter()
for _, (_, nucs, _) in FastqReader.get_reads(fastq):
_, _, score = align_it(v3loop_ref, nucs, GAP_OPEN_COST,
GAP_EXTEND_COST, USE_TERMINAL_COST)
score_counts[score] += 1
return score_counts
def align_reads(fastq1, fastq2):
v3loop_ref = extract_v3loop_ref()
reader = FastqReader(fastq1, fastq2)
merged_reads = merge_reads(reader)
score_counts = Counter()
for _ in trim_reads(merged_reads, v3loop_ref, score_counts):
pass
return score_counts
def align_untrimmed_reads(fastq):
v3loop_ref = extract_v3loop_ref()
score_counts = Counter()
for _, (_, nucs, _) in FastqReader.get_reads(fastq):
_, _, score = align_it(v3loop_ref,
nucs,
GAP_OPEN_COST,
GAP_EXTEND_COST,
USE_TERMINAL_COST)
score_counts[score] += 1
return score_counts
def test_unmatched_pair(self):
self.fastq1 = StringIO("""\
@A:B:C X:Y
ACGT
+
QUAL
""")
self.fastq2 = StringIO("""\
@A:B:X Q:R
TTGG
+
LAUQ
""")
reader = FastqReader(self.fastq1, self.fastq2)
with self.assertRaisesRegex(FastqError, 'No match for read A:B:C.'):
list(reader)
def test_extra_description(self):
self.fastq1 = StringIO("""\
@A:B:C X:Y Z
ACGT
+
QUAL
""")
self.fastq2 = StringIO("""\
@A:B:C Q:R
TTGG
+
LAUQ
""")
expected_reads = [("A:B:C", ("X:Y Z", "ACGT", "QUAL"), ("Q:R", "TTGG",
"LAUQ"))]
reader = FastqReader(self.fastq1, self.fastq2)
reads = list(reader)
self.assertEqual(expected_reads, reads)