def test_duplicate_barcodes(self):
barcodes = pd.Series(['AACC', 'AACC'],
name='bc',
index=pd.Index(['sample1', 'sample2'], name='id'))
barcodes = qiime2.CategoricalMetadataColumn(barcodes)
with self.assertRaises(ValueError):
emp_paired(self.bpsi, barcodes)
def test_sequence_length_uses_subsample_paired(self):
random.seed(6) # Will select s1 and s2 which aren't the shortest pairs
forward = [('@s1/1 abc/1', 'GGG', '+', 'YYY'),
('@s2/1 abc/1', 'CCCCC', '+', 'PPPPP'),
('@s3/1 abc/1', 'A', '+', 'P'),
('@s4/1 abc/1', 'TTTTTTT', '+', 'PPPPPPP')]
reverse = [('@s1/1 abc/1', 'AAAAA', '+', 'YYYYY'),
('@s2/1 abc/1', 'TTTTTTT', '+', 'PPPPPPP'),
('@s3/1 abc/1', 'GGG', '+', 'PPP'),
('@s4/1 abc/1', 'C', '+', 'P')]
bpsi = BarcodePairedSequenceFastqIterator(self.barcodes, forward,
reverse)
barcode_map = pd.Series(['AAAA', 'AACC'],
name='bc',
index=pd.Index(['sample1', 'sample2'],
name='id'))
barcode_map = qiime2.CategoricalMetadataColumn(barcode_map)
demux_data = emp_paired(bpsi, barcode_map)
with tempfile.TemporaryDirectory() as output_dir:
summarize(output_dir, _PlotQualView(demux_data, paired=True), n=2)
plot_fp = os.path.join(output_dir, 'data.jsonp')
with open(plot_fp, 'r') as fh:
jsonp = fh.read()
json_ = jsonp.replace('app.init(', '[').replace(');', ']')
payload = json.loads(json_)[0]
self.assertEqual(payload["minSeqLen"]["forward"], 3)
self.assertEqual(payload["minSeqLen"]["reverse"], 5)
def test_paired_end(self):
barcodes = self.barcodes[:3]
forward = self.sequences[:3]
reverse = [('@s1/1 abc/1', 'CCC', '+', 'YYY'),
('@s2/1 abc/1', 'GGG', '+', 'PPP'),
('@s3/1 abc/1', 'TTT', '+', 'PPP')]
bpsi = BarcodePairedSequenceFastqIterator(barcodes, forward, reverse)
barcode_map = pd.Series(['AAAA', 'AACC', 'TTAA'],
name='bc',
index=pd.Index(
['sample1', 'sample2', 'sample3'],
name='id'))
barcode_map = qiime2.CategoricalMetadataColumn(barcode_map)
demux_data = emp_paired(bpsi, barcode_map)
with tempfile.TemporaryDirectory() as output_dir:
result = summarize(output_dir,
_PlotQualView(demux_data, paired=True),
n=2)
self.assertTrue(result is None)
plot_fp = os.path.join(output_dir, 'quality-plot.html')
with open(plot_fp, 'r') as fh:
html = fh.read()
self.assertIn('<h5 class="text-center">Forward Reads</h5>',
html)
self.assertIn('<h5 class="text-center">Reverse Reads</h5>',
html)
def test_inconsistent_sequence_length_paired(self):
forward = [('@s1/1 abc/1', 'G', '+', 'Y'),
('@s2/1 abc/1', 'CCC', '+', 'PPP'),
('@s3/1 abc/1', 'AAAAA', '+', 'PPPPP'),
('@s4/1 abc/1', 'TTTTTTT', '+', 'PPPPPPP')]
reverse = [('@s1/1 abc/1', 'AAAAAAA', '+', 'YYYYYYY'),
('@s2/1 abc/1', 'TTTTT', '+', 'PPPPP'),
('@s3/1 abc/1', 'GGG', '+', 'PPP'),
('@s4/1 abc/1', 'C', '+', 'P')]
bpsi = BarcodePairedSequenceFastqIterator(self.barcodes, forward,
reverse)
barcode_map = pd.Series(['AAAA', 'AACC'],
name='bc',
index=pd.Index(['sample1', 'sample2'],
name='id'))
barcode_map = qiime2.CategoricalMetadataColumn(barcode_map)
demux_data = emp_paired(bpsi, barcode_map)
lengths = [1, 3, 5, 7]
for n in range(1, 6):
with tempfile.TemporaryDirectory() as output_dir:
lengths_ = lengths[0:5 - n] if n < 4 else [1]
# TODO: Remove _PlotQualView wrapper
summarize(output_dir,
_PlotQualView(demux_data, paired=True),
n=n)
plot_fp = os.path.join(output_dir, 'data.jsonp')
with open(plot_fp, 'r') as fh:
jsonp = fh.read()
json_ = jsonp.replace('app.init(', '[').replace(');', ']')
payload = json.loads(json_)[0]
self.assertEqual(payload["totalSeqCount"], 4)
self.assertIn(payload["minSeqLen"]["forward"], lengths_)
self.assertIn(payload["minSeqLen"]["reverse"], lengths_)
self.assertEqual(payload["n"], min(n, 4))
def check_valid(self, *args, **kwargs):
actual = emp_paired(*args, **kwargs)
# five forward sample files
forward_fastq = [
view for path, view in actual.sequences.iter_views(FastqGzFormat)
if 'R1_001.fastq' in path.name
]
self.assertEqual(len(forward_fastq), 5)
# five reverse sample files
reverse_fastq = [
view for path, view in actual.sequences.iter_views(FastqGzFormat)
if 'R2_001.fastq' in path.name
]
self.assertEqual(len(reverse_fastq), 5)
# FORWARD:
# sequences in sample1 are correct
self._validate_sample_fastq(forward_fastq[0].open(), self.forward,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(forward_fastq[1].open(), self.forward,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(forward_fastq[2].open(), self.forward,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(forward_fastq[3].open(), self.forward,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(forward_fastq[4].open(), self.forward,
[6, 8, 9])
# REVERSE:
# sequences in sample1 are correct
self._validate_sample_fastq(reverse_fastq[0].open(), self.reverse,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(reverse_fastq[1].open(), self.reverse,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(reverse_fastq[2].open(), self.reverse,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(reverse_fastq[3].open(), self.reverse,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(reverse_fastq[4].open(), self.reverse,
[6, 8, 9])
# manifest is correct
act_manifest = list(actual.manifest.view(FastqManifestFormat).open())
exp_manifest = [
'sample-id,filename,direction\n',
'sample1,sample1_1_L001_R1_001.fastq.gz,forward\n',
'sample1,sample1_1_L001_R2_001.fastq.gz,reverse\n',
'sample3,sample3_2_L001_R1_001.fastq.gz,forward\n',
'sample3,sample3_2_L001_R2_001.fastq.gz,reverse\n',
'sample2,sample2_3_L001_R1_001.fastq.gz,forward\n',
'sample2,sample2_3_L001_R2_001.fastq.gz,reverse\n',
'sample5,sample5_4_L001_R1_001.fastq.gz,forward\n',
'sample5,sample5_4_L001_R2_001.fastq.gz,reverse\n',
'sample4,sample4_5_L001_R1_001.fastq.gz,forward\n',
'sample4,sample4_5_L001_R2_001.fastq.gz,reverse\n'
]
self._compare_manifests(act_manifest, exp_manifest)
# metadata is correct
act_metadata = list(actual.metadata.view(YamlFormat).open())
exp_metadata = ["{phred-offset: 33}\n"]
self.assertEqual(act_metadata, exp_metadata)
def test_no_matched_barcodes(self):
barcodes = pd.Series(['CCCC', 'GGCC'], index=['sample1', 'sample2'])
barcodes = qiime2.MetadataCategory(barcodes)
with self.assertRaises(ValueError):
emp_paired(self.bpsi, barcodes)
def test_variable_length_barcodes(self):
barcodes = pd.Series(['AAA', 'AACC'], index=['sample1', 'sample2'])
barcodes = qiime2.MetadataCategory(barcodes)
with self.assertRaises(ValueError):
emp_paired(self.bpsi, barcodes)
