def test_count_fastq_sequences(self):
"""BarcodeCounter: count barcode sequences
"""
# Initialise counter object
bc = BarcodeCounter()
# Populate with sequences
for r, incr in (((1, "AGGCAGAATCTTACGC"),
102), ((1, "TCCTGAGCTCTTACGC"),
10), ((1, "ACAGTGATTCTTTCCC"),
3), ((1, "ATGCTCGTCTCGCATC"),
1), ((2, "CGTACTAGTCTTACGC"), 95),
((2, "ATGTCAGATCTTTCCC"),
29), ((2, "AGGCAGAATCTTACGC"),
12), ((2, "CAGATCATTCTTTCCC"),
6), ((3, "GGACTCCTTCTTACGC"),
75), ((3, "ACCGATTCGCGCGTAG"), 74),
((3, "CCAGCAATATCGCGAG"), 2), ((3, "CCGCGTAAGCAATAGA"),
1)):
lane, seq = r
for i in xrange(incr):
bc.count_barcode(seq, lane=lane)
# Check contents
self.assertEqual(bc.barcodes(), [
"AGGCAGAATCTTACGC", "CGTACTAGTCTTACGC", "GGACTCCTTCTTACGC",
"ACCGATTCGCGCGTAG", "ATGTCAGATCTTTCCC", "TCCTGAGCTCTTACGC",
"CAGATCATTCTTTCCC", "ACAGTGATTCTTTCCC", "CCAGCAATATCGCGAG",
"ATGCTCGTCTCGCATC", "CCGCGTAAGCAATAGA"
])
# Lanes
self.assertEqual(bc.lanes, [1, 2, 3])
# Counts for individual barcodes
self.assertEqual(bc.counts("AGGCAGAATCTTACGC"), 114)
self.assertEqual(bc.counts("AGGCAGAATCTTACGC", lane=1), 102)
self.assertEqual(bc.counts("AGGCAGAATCTTACGC", lane=2), 12)
self.assertEqual(bc.counts("AGGCAGAATCTTACGC", lane=3), 0)
self.assertEqual(bc.counts_all("AGGCAGAATCTTACGC"), 114)
self.assertEqual(bc.counts("CCGCGTAAGCAATAGA"), 1)
self.assertEqual(bc.counts("CCGCGTAAGCAATAGA", lane=1), 0)
self.assertEqual(bc.counts("CCGCGTAAGCAATAGA", lane=2), 0)
self.assertEqual(bc.counts("CCGCGTAAGCAATAGA", lane=3), 1)
self.assertEqual(bc.counts_all("CCGCGTAAGCAATAGA"), 1)
# Read counts
self.assertEqual(bc.nreads(), 410)
self.assertEqual(bc.nreads(1), 116)
self.assertEqual(bc.nreads(2), 142)
self.assertEqual(bc.nreads(3), 152)
# Lengths
self.assertEqual(bc.barcode_lengths(), [16])
self.assertEqual(bc.barcode_lengths(1), [16])
self.assertEqual(bc.barcode_lengths(2), [16])
self.assertEqual(bc.barcode_lengths(3), [16])
elif length != barcode_length:
logging.error("Lane %s has a mixture of "
"barcode lengths" % lane)
barcode_length = min(barcode_length, length)
if barcode_length >= 6:
mismatches = 1
else:
mismatches = 0
# Check for collisions
while mismatches and check_barcode_collisions(
fp.name, mismatches):
mismatches = mismatches - 1
# Check mismatches
if mismatches is None:
# Set according to barcode lengths found in counts
barcode_length = min(counts.barcode_lengths(lane=lane))
if barcode_length >= 6:
mismatches = 1
else:
mismatches = 0
# Report the analysis
report_barcodes(counts,
lane=lane,
cutoff=cutoff,
sample_sheet=sample_sheet,
mismatches=mismatches,
reporter=reporter)
if opts.report_file is not None:
print "Writing report to %s" % opts.report_file
reporter.write(filen=opts.report_file, title=opts.title)
else: