def test_write_counts_file(self):
"""BarcodeCounter: write counts to a file
"""
# Write a file
self._make_working_dir()
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("TATGCGCGGTG", lane=1, incr=532)
bc.count_barcode("ACCTACCGGTA", lane=1, incr=315)
bc.count_barcode("CCCTTATGCGA", lane=1, incr=22)
bc.count_barcode("ACCTAGCGGTA", lane=2, incr=477)
bc.count_barcode("ACCTCTATGCT", lane=2, incr=368)
bc.count_barcode("ACCCTNCGGTA", lane=3, incr=312)
bc.count_barcode("ACCTTATGCGC", lane=3, incr=248)
counts_file = os.path.join(self.wd, "out.counts")
bc.write(counts_file)
expected_contents = """#Lane Rank Sequence Count
1 1 TATGCGCGGTA 285302
1 2 TATGCGCGGTG 532
1 3 ACCTACCGGTA 315
1 4 CCCTTATGCGA 22
2 1 ACCTAGCGGTA 477
2 2 ACCTCTATGCT 368
3 1 ACCCTNCGGTA 312
3 2 ACCTTATGCGC 248
"""
self.assertTrue(os.path.exists(counts_file))
self.assertEqual(open(counts_file, 'r').read(), expected_contents)
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])
def test_analyse_groups_with_sample_sheet(self):
"""BarcodeCounter: perform analysis with grouping and samplesheet
"""
# Create sample sheet
sample_sheet_file = self._make_file(
"SampleSheet.csv", """[Data]
Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,Sample_Project,Description
1,SMPL1,,,,A006,CATGCGCGGTA,,
1,SMPL2,,,,A012,GCTGCGCGGTC,,
2,SMPL3,,,,A005,ACAGTGCGGTA,,
2,SMPL4,,,,A019,GTGAAACGGTC,,
""")
# Set up barcode counts
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("CATGCGCGGTA", lane=1, incr=8532)
bc.count_barcode("GATGCGCGGTA", lane=1, incr=5321)
bc.count_barcode("GCTGCGCGGTA", lane=1, incr=7853)
bc.count_barcode("GCTGCGCGGTC", lane=1, incr=325394)
analysis = bc.analyse(lane=1,
mismatches=2,
sample_sheet=sample_sheet_file)
##"CATGCGCGGTA","TATGCGCGGTA","GATGCGCGGTA","GCTGCGCGGTA" = 307008
##"GCTGCGCGGTC" = 325394
self.assertEqual(analysis.cutoff, None)
self.assertEqual(analysis.mismatches, 2)
self.assertEqual(analysis.total_reads, 632402)
self.assertEqual(analysis.coverage, 632402)
self.assertEqual(analysis.barcodes, ["GCTGCGCGGTC", "CATGCGCGGTA"])
self.assertEqual(analysis.counts["GCTGCGCGGTC"].reads, 325394)
self.assertEqual(analysis.counts["CATGCGCGGTA"].reads, 307008)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sample, "SMPL2")
self.assertEqual(analysis.counts["CATGCGCGGTA"].sample, "SMPL1")
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sequences, 1)
self.assertEqual(analysis.counts["CATGCGCGGTA"].sequences, 4)
def test_analyse_with_cutoff(self):
"""BarcodeCounter: perform analysis with cutoff
"""
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("CATGCGCGGTA", lane=1, incr=8532)
bc.count_barcode("GATGCGCGGTA", lane=1, incr=5321)
bc.count_barcode("GCTGCGCGGTA", lane=1, incr=7853)
bc.count_barcode("GCTGCGCGGTC", lane=1, incr=325394)
analysis = bc.analyse(lane=1, cutoff=0.013)
self.assertEqual(analysis.cutoff, 0.013)
self.assertEqual(analysis.mismatches, 0)
self.assertEqual(analysis.total_reads, 632402)
self.assertEqual(analysis.coverage, 619228)
self.assertEqual(analysis.barcodes,
["GCTGCGCGGTC", "TATGCGCGGTA", "CATGCGCGGTA"])
self.assertEqual(analysis.counts["GCTGCGCGGTC"].reads, 325394)
self.assertEqual(analysis.counts["TATGCGCGGTA"].reads, 285302)
self.assertEqual(analysis.counts["CATGCGCGGTA"].reads, 8532)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sample, None)
self.assertEqual(analysis.counts["TATGCGCGGTA"].sample, None)
self.assertEqual(analysis.counts["CATGCGCGGTA"].sample, None)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sequences, 1)
self.assertEqual(analysis.counts["TATGCGCGGTA"].sequences, 1)
self.assertEqual(analysis.counts["CATGCGCGGTA"].sequences, 1)
def test_filter_barcodes(self):
"""BarcodeCounter: check filtering by lane and cutoff
"""
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("TATGCGCGGTG", lane=1, incr=532)
bc.count_barcode("ACCTACCGGTA", lane=1, incr=315)
bc.count_barcode("CCCTTATGCGA", lane=1, incr=22)
bc.count_barcode("ACCTAGCGGTA", lane=2, incr=477)
bc.count_barcode("ACCTCTATGCT", lane=2, incr=368)
self.assertEqual(bc.barcodes(), [
"TATGCGCGGTA", "TATGCGCGGTG", "ACCTAGCGGTA", "ACCTCTATGCT",
"ACCTACCGGTA", "CCCTTATGCGA"
])
# No filtering
self.assertEqual(bc.filter_barcodes(), [
"TATGCGCGGTA", "TATGCGCGGTG", "ACCTAGCGGTA", "ACCTCTATGCT",
"ACCTACCGGTA", "CCCTTATGCGA"
])
# Filter by lane
self.assertEqual(
bc.filter_barcodes(lane=1),
["TATGCGCGGTA", "TATGCGCGGTG", "ACCTACCGGTA", "CCCTTATGCGA"]),
self.assertEqual(bc.filter_barcodes(lane=2),
["ACCTAGCGGTA", "ACCTCTATGCT"])
# Filter by cutoff
self.assertEqual(bc.filter_barcodes(cutoff=0.5), [
"TATGCGCGGTA",
])
self.assertEqual(bc.filter_barcodes(cutoff=0.0015, lane=1),
["TATGCGCGGTA", "TATGCGCGGTG"])
self.assertEqual(bc.filter_barcodes(cutoff=0.5, lane=2), [
"ACCTAGCGGTA",
])
def count_barcodes(fastqs):
"""
Count the barcodes from multiple fastqs
"""
print "Reading in %s fastq%s" % (len(fastqs),
('' if len(fastqs) == 1 else 's'))
counts = BarcodeCounter()
for fq in fastqs:
print "%s" % os.path.basename(fq)
for r in FastqIterator(fq):
seq = r.seqid.index_sequence
lane = int(r.seqid.flowcell_lane)
counts.count_barcode(seq, lane)
return counts
def test_report_barcodes(self):
"""report_barcodes: check output for mismatches and sample sheet
"""
# Create sample sheet
sample_sheet_file = self._make_file(
"SampleSheet.csv", """[Data]
Lane,Sample_ID,Sample_Name,Sample_Plate,Sample_Well,I7_Index_ID,index,Sample_Project,Description
1,SMPL1,,,,A006,CATGCGCGGTA,,
1,SMPL2,,,,A012,GCTGCGCGGTC,,
""")
# Set up barcode counts
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("CATGCGCGGTA", lane=1, incr=8532)
bc.count_barcode("GATGCGCGGTA", lane=1, incr=5321)
bc.count_barcode("GCTGCGCGGTA", lane=1, incr=7853)
bc.count_barcode("GCTGCGCGGTC", lane=1, incr=325394)
analysis = bc.analyse(lane=1,
mismatches=2,
sample_sheet=sample_sheet_file)
##"CATGCGCGGTA","TATGCGCGGTA","GATGCGCGGTA","GCTGCGCGGTA" = 307008
##"GCTGCGCGGTC" = 325394
self.assertEqual(analysis.cutoff, None)
self.assertEqual(analysis.mismatches, 2)
self.assertEqual(analysis.total_reads, 632402)
self.assertEqual(analysis.coverage, 632402)
self.assertEqual(analysis.barcodes, ["GCTGCGCGGTC", "CATGCGCGGTA"])
self.assertEqual(analysis.counts["GCTGCGCGGTC"].reads, 325394)
self.assertEqual(analysis.counts["CATGCGCGGTA"].reads, 307008)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sample, "SMPL2")
self.assertEqual(analysis.counts["CATGCGCGGTA"].sample, "SMPL1")
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sequences, 1)
self.assertEqual(analysis.counts["CATGCGCGGTA"].sequences, 4)
# Create report
reporter = report_barcodes(bc,
lane=1,
mismatches=2,
sample_sheet=sample_sheet_file)
# Check content
self.assertEqual(
str(reporter), """Barcode analysis for lane #1
============================
* Barcodes have been grouped by allowing 2 mismatches
#Rank Index Sample N_seqs N_reads %reads (%Total_reads)
1 GCTGCGCGGTC SMPL2 1 325394 51.5% (51.5%)
2 CATGCGCGGTA SMPL1 4 307008 48.5% (100.0%)""")
def test_analyse_groups(self):
"""BarcodeCounter: perform analysis with grouping
"""
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("CATGCGCGGTA", lane=1, incr=8532)
bc.count_barcode("GATGCGCGGTA", lane=1, incr=5321)
bc.count_barcode("GCTGCGCGGTA", lane=1, incr=7853)
bc.count_barcode("GCTGCGCGGTC", lane=1, incr=325394)
analysis = bc.analyse(lane=1, mismatches=1)
##"TATGCGCGGTA","CATGCGCGGTA","GATGCGCGGTA" = 299155
##"GCTGCGCGGTC","GCTGCGCGGTA" = 333247
self.assertEqual(analysis.cutoff, None)
self.assertEqual(analysis.mismatches, 1)
self.assertEqual(analysis.total_reads, 632402)
self.assertEqual(analysis.coverage, 632402)
self.assertEqual(analysis.barcodes, ["GCTGCGCGGTC", "TATGCGCGGTA"])
self.assertEqual(analysis.counts["GCTGCGCGGTC"].reads, 333247)
self.assertEqual(analysis.counts["TATGCGCGGTA"].reads, 299155)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sample, None)
self.assertEqual(analysis.counts["TATGCGCGGTA"].sample, None)
self.assertEqual(analysis.counts["GCTGCGCGGTC"].sequences, 2)
self.assertEqual(analysis.counts["TATGCGCGGTA"].sequences, 3)
def test_group(self):
"""BarcodeCounter: check grouping of barcode sequences
"""
bc = BarcodeCounter()
bc.count_barcode("TATGCGCGGTA", lane=1, incr=285302)
bc.count_barcode("CATGCGCGGTA", lane=1, incr=8532)
bc.count_barcode("GATGCGCGGTA", lane=1, incr=5321)
bc.count_barcode("GCTGCGCGGTA", lane=1, incr=7853)
bc.count_barcode("GCTGCGCGGTC", lane=1, incr=325394)
bc.count_barcode("GTCACGCGGTA", lane=2, incr=296201)
bc.count_barcode("GTCACGCGGTT", lane=2, incr=2853)
bc.count_barcode("GTCACGCTGTT", lane=2, incr=278539)
## 2 mismatches across all lanes
groups = bc.group(None, mismatches=2)
##"GCTGCGCGGTC","GCTGCGCGGTA","GATGCGCGGTA" = 338568
##"TATGCGCGGTA","CATGCGCGGTA" = 293834
##"GTCACGCGGTA","GTCACGCTGTT","GTCACGCGGTT" = 577593
self.assertEqual(len(groups), 3)
self.assertEqual(groups[0].reference, "GTCACGCGGTA")
self.assertEqual(groups[0].sequences,
["GTCACGCGGTA", "GTCACGCTGTT", "GTCACGCGGTT"])
self.assertEqual(groups[0].counts, 577593)
self.assertEqual(groups[1].reference, "GCTGCGCGGTC")
self.assertEqual(groups[1].sequences,
["GCTGCGCGGTC", "GCTGCGCGGTA", "GATGCGCGGTA"])
self.assertEqual(groups[1].counts, 338568)
self.assertEqual(groups[2].reference, "TATGCGCGGTA")
self.assertEqual(groups[2].sequences, ["TATGCGCGGTA", "CATGCGCGGTA"])
self.assertEqual(groups[2].counts, 293834)
## 1 mismatch across all lanes
groups = bc.group(None, mismatches=1)
##"TATGCGCGGTA","CATGCGCGGTA","GATGCGCGGTA" = 299155
##"GCTGCGCGGTC","GCTGCGCGGTA" = 333247
##"GTCACGCGGTA","GTCACGCGGTT" = 299054
##"GTCACGCTGTT" = 278539
self.assertEqual(len(groups), 4)
self.assertEqual(groups[0].reference, "GCTGCGCGGTC")
self.assertEqual(groups[0].sequences, ["GCTGCGCGGTC", "GCTGCGCGGTA"])
self.assertEqual(groups[0].counts, 333247)
self.assertEqual(groups[1].reference, "TATGCGCGGTA")
self.assertEqual(groups[1].sequences,
["TATGCGCGGTA", "CATGCGCGGTA", "GATGCGCGGTA"])
self.assertEqual(groups[1].counts, 299155)
self.assertEqual(groups[2].reference, "GTCACGCGGTA")
self.assertEqual(groups[2].sequences, ["GTCACGCGGTA", "GTCACGCGGTT"])
self.assertEqual(groups[2].counts, 299054)
self.assertEqual(groups[3].reference, "GTCACGCTGTT")
self.assertEqual(groups[3].sequences, [
"GTCACGCTGTT",
])
self.assertEqual(groups[3].counts, 278539)
## 1 mismatch in lane 1
groups = bc.group(1, mismatches=1)
##"TATGCGCGGTA","CATGCGCGGTA","GATGCGCGGTA" = 299155
##"GCTGCGCGGTC","GCTGCGCGGTA" = 333247
self.assertEqual(len(groups), 2)
self.assertEqual(groups[0].reference, "GCTGCGCGGTC")
self.assertEqual(groups[0].sequences, ["GCTGCGCGGTC", "GCTGCGCGGTA"])
self.assertEqual(groups[0].counts, 333247)
self.assertEqual(groups[1].reference, "TATGCGCGGTA")
self.assertEqual(groups[1].sequences,
["TATGCGCGGTA", "CATGCGCGGTA", "GATGCGCGGTA"])
self.assertEqual(groups[1].counts, 299155)
## 2 mismatches across all lanes
groups = bc.group(None, mismatches=2)
##"GCTGCGCGGTC","GCTGCGCGGTA","GATGCGCGGTA" = 338568
##"TATGCGCGGTA","CATGCGCGGTA" = 293834
##"GTCACGCGGTA","GTCACGCTGTT","GTCACGCGGTT" = 577593
self.assertEqual(len(groups), 3)
self.assertEqual(groups[0].reference, "GTCACGCGGTA")
self.assertEqual(groups[0].sequences,
["GTCACGCGGTA", "GTCACGCTGTT", "GTCACGCGGTT"])
self.assertEqual(groups[0].counts, 577593)
self.assertEqual(groups[1].reference, "GCTGCGCGGTC")
self.assertEqual(groups[1].sequences,
["GCTGCGCGGTC", "GCTGCGCGGTA", "GATGCGCGGTA"])
self.assertEqual(groups[1].counts, 338568)
self.assertEqual(groups[2].reference, "TATGCGCGGTA")
self.assertEqual(groups[2].sequences, ["TATGCGCGGTA", "CATGCGCGGTA"])
self.assertEqual(groups[2].counts, 293834)