def test_inconsistent_sequence_length_single(self):
sequences = [('@s1/1 abc/1', 'GGGGGGG', '+', 'YYYYYYY'),
('@s2/1 abc/1', 'CCCCC', '+', 'PPPPP'),
('@s3/1 abc/1', 'AAA', '+', 'PPP'),
('@s4/1 abc/1', 'T', '+', 'P')]
bsi = BarcodeSequenceFastqIterator(self.barcodes, sequences)
barcode_map = pd.Series(['AAAA', 'AACC'],
name='bc',
index=pd.Index(['sample1', 'sample2'],
name='id'))
barcode_map = qiime2.CategoricalMetadataColumn(barcode_map)
demux_data = emp_single(bsi, 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=False),
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.assertEqual(payload["minSeqLen"]["reverse"], None)
self.assertEqual(payload["n"], min(n, 4))
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_phred_score_out_of_range(self):
barcodes = self.barcodes[:3]
sequences = [('@s1/1 abc/1', 'GGG', '+', 'jjj'),
('@s2/1 abc/1', 'CCC', '+', 'iii'),
('@s3/1 abc/1', 'AAA', '+', 'hhh')]
bsi = BarcodeSequenceFastqIterator(barcodes, sequences)
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_single(bsi, barcode_map)
with tempfile.TemporaryDirectory() as output_dir:
result = summarize(output_dir,
_PlotQualView(demux_data, paired=False),
n=50)
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('<strong>Danger:</strong>', html)
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_single_sample(self):
bsi = BarcodeSequenceFastqIterator(self.barcodes[:1],
self.sequences[:1])
barcode_map = pd.Series(['AAAA'],
name='bc',
index=pd.Index(['sample1'], name='id'))
barcode_map = qiime2.CategoricalMetadataColumn(barcode_map)
demux_data = emp_single(bsi, barcode_map)
# test that an index.html file is created and that it has size > 0
with tempfile.TemporaryDirectory() as output_dir:
# TODO: Remove _PlotQualView wrapper
result = summarize(output_dir,
_PlotQualView(demux_data, paired=False),
n=1)
self.assertTrue(result is None)
index_fp = os.path.join(output_dir, 'overview.html')
self.assertTrue(os.path.exists(index_fp))
self.assertTrue(os.path.getsize(index_fp) > 0)
csv_fp = os.path.join(output_dir, 'per-sample-fastq-counts.csv')
self.assertTrue(os.path.exists(csv_fp))
self.assertTrue(os.path.getsize(csv_fp) > 0)
pdf_fp = os.path.join(output_dir, 'demultiplex-summary.pdf')
self.assertFalse(os.path.exists(pdf_fp))
png_fp = os.path.join(output_dir, 'demultiplex-summary.png')
self.assertFalse(os.path.exists(png_fp))
with open(index_fp, 'r') as fh:
html = fh.read()
self.assertIn('<td>Minimum:</td><td>1</td>', html)
self.assertIn('<td>Maximum:</td><td>1</td>', html)
def test_subsample_higher_than_seqs_count(self):
barcodes = self.barcodes[:1]
sequences = self.sequences[:1]
bsi = BarcodeSequenceFastqIterator(barcodes, sequences)
barcode_map = pd.Series(['AAAA'], index=['sample1'])
barcode_map = qiime2.MetadataCategory(barcode_map)
demux_data = emp_single(bsi, barcode_map)
with tempfile.TemporaryDirectory() as output_dir:
result = summarize(output_dir, _PlotQualView(demux_data,
paired=False), n=50)
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('<strong>Warning:</strong>', html)
def test_single_sample_multiple_files(self):
# Note, this case came up on the QIIME 2 Forum, due to a user running
# `summarize` with demuxed sequences that all had the same Sample ID
# in the internal MANIFEST file. With versions of seaborn greater than
# 0.8.0 this is no longer a problem, but on prior versions, the user
# would see the following error:
# TypeError: len() of unsized object
files = [
'sample1_S0_L001_R1_001.fastq.gz',
'sample2_S0_L001_R1_001.fastq.gz',
'sample3_S0_L001_R1_001.fastq.gz', 'MANIFEST', 'metadata.yml'
]
for f in files:
shutil.copy(
self.get_data_path('single_sample_multiple_files/%s' % f),
self.temp_dir.name)
demux_data = SingleLanePerSampleSingleEndFastqDirFmt(
self.temp_dir.name, mode='r')
with tempfile.TemporaryDirectory() as output_dir:
# TODO: Remove _PlotQualView wrapper
result = summarize(output_dir,
_PlotQualView(demux_data, paired=False),
n=1)
self.assertTrue(result is None)
index_fp = os.path.join(output_dir, 'overview.html')
self.assertTrue(os.path.exists(index_fp))
self.assertTrue(os.path.getsize(index_fp) > 0)
csv_fp = os.path.join(output_dir, 'per-sample-fastq-counts.csv')
self.assertTrue(os.path.exists(csv_fp))
self.assertTrue(os.path.getsize(csv_fp) > 0)
pdf_fp = os.path.join(output_dir, 'demultiplex-summary.pdf')
self.assertTrue(os.path.exists(pdf_fp))
png_fp = os.path.join(output_dir, 'demultiplex-summary.png')
self.assertTrue(os.path.exists(png_fp))
with open(index_fp, 'r') as fh:
html = fh.read()
self.assertIn('<td>Minimum:</td><td>1</td>', html)
self.assertIn('<td>Maximum:</td><td>1</td>', html)
