def test_variable_length_barcodes(self):
barcodes = pd.Series(['AAA', 'AACC'],
name='bc',
index=pd.Index(['sample1', 'sample2'], name='id'))
barcodes = qiime2.CategoricalMetadataColumn(barcodes)
with self.assertRaises(ValueError):
emp_single(self.bsi, barcodes)
def test_no_matched_barcodes(self):
barcodes = pd.Series(['CCCC', 'GGCC'],
name='bc',
index=pd.Index(['sample1', 'sample2'], name='id'))
barcodes = qiime2.CategoricalMetadataColumn(barcodes)
with self.assertRaises(ValueError):
emp_single(self.bsi, barcodes)
def test_sequence_length_uses_subsample_single(self):
random.seed(6) # Will select s1 and s2 which aren't the shortest ones
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)
with tempfile.TemporaryDirectory() as output_dir:
summarize(output_dir, _PlotQualView(demux_data, paired=False), 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"], 5)
self.assertEqual(payload["minSeqLen"]["reverse"], None)
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_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_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_barcode_trimming(self):
# these barcodes are longer then the ones in the mapping file, so
# only the first barcode_length bases should be read
barcodes = [('@s1/2 abc/2', 'AAAAG', '+', 'YYYY'),
('@s2/2 abc/2', 'TTAAG', '+', 'PPPP'),
('@s3/2 abc/2', 'AACCG', '+', 'PPPP'),
('@s4/2 abc/2', 'TTAAG', '+', 'PPPP'),
('@s5/2 abc/2', 'AACCG', '+', 'PPPP'),
('@s6/2 abc/2', 'AAAAG', '+', 'PPPP'),
('@s7/2 abc/2', 'CGGCG', '+', 'PPPP'),
('@s8/2 abc/2', 'GGAAG', '+', 'PPPP'),
('@s9/2 abc/2', 'CGGCG', '+', 'PPPP'),
('@s10/2 abc/2', 'CGGCG', '+', 'PPPP'),
('@s11/2 abc/2', 'GGAAG', '+', 'PPPP')]
bsi = BarcodeSequenceFastqIterator(barcodes, self.sequences)
actual = emp_single(bsi, self.barcode_map)
output_fastq = list(actual.sequences.iter_views(FastqGzFormat))
# five per-sample files were written
self.assertEqual(len(output_fastq), 5)
# sequences in sample1 are correct
self._validate_sample_fastq(output_fastq[0][1].open(), self.sequences,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(output_fastq[1][1].open(), self.sequences,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(output_fastq[2][1].open(), self.sequences,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(output_fastq[3][1].open(), self.sequences,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(output_fastq[4][1].open(), self.sequences,
[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',
'sample3,sample3_2_L001_R1_001.fastq.gz,forward\n',
'sample2,sample2_3_L001_R1_001.fastq.gz,forward\n',
'sample5,sample5_4_L001_R1_001.fastq.gz,forward\n',
'sample4,sample4_5_L001_R1_001.fastq.gz,forward\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_rev_comp_mapping_barcodes(self):
barcodes = pd.Series(
['TTTT', 'GGTT', 'TTAA', 'TTCC', 'GCCG'],
name='bc',
index=pd.Index(
['sample1', 'sample2', 'sample3', 'sample4', 'sample5'],
name='id'))
barcodes = qiime2.CategoricalMetadataColumn(barcodes)
actual = emp_single(self.bsi, barcodes, rev_comp_mapping_barcodes=True)
output_fastq = list(actual.sequences.iter_views(FastqGzFormat))
# five per-sample files were written
self.assertEqual(len(output_fastq), 5)
# sequences in sample1 are correct
self._validate_sample_fastq(output_fastq[0][1].open(), self.sequences,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(output_fastq[1][1].open(), self.sequences,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(output_fastq[2][1].open(), self.sequences,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(output_fastq[3][1].open(), self.sequences,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(output_fastq[4][1].open(), self.sequences,
[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',
'sample3,sample3_2_L001_R1_001.fastq.gz,forward\n',
'sample2,sample2_3_L001_R1_001.fastq.gz,forward\n',
'sample5,sample5_4_L001_R1_001.fastq.gz,forward\n',
'sample4,sample4_5_L001_R1_001.fastq.gz,forward\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_rev_comp_barcodes(self):
barcodes = [('@s1/2 abc/2', 'TTTT', '+', 'YYYY'),
('@s2/2 abc/2', 'TTAA', '+', 'PPPP'),
('@s3/2 abc/2', 'GGTT', '+', 'PPPP'),
('@s4/2 abc/2', 'TTAA', '+', 'PPPP'),
('@s5/2 abc/2', 'GGTT', '+', 'PPPP'),
('@s6/2 abc/2', 'TTTT', '+', 'PPPP'),
('@s7/2 abc/2', 'GCCG', '+', 'PPPP'),
('@s8/2 abc/2', 'TTCC', '+', 'PPPP'),
('@s9/2 abc/2', 'GCCG', '+', 'PPPP'),
('@s10/2 abc/2', 'GCCG', '+', 'PPPP'),
('@s11/2 abc/2', 'TTCC', '+', 'PPPP')]
bsi = BarcodeSequenceFastqIterator(barcodes, self.sequences)
actual = emp_single(bsi, self.barcode_map, rev_comp_barcodes=True)
output_fastq = list(actual.sequences.iter_views(FastqGzFormat))
# five per-sample files were written
self.assertEqual(len(output_fastq), 5)
# sequences in sample1 are correct
self._validate_sample_fastq(output_fastq[0][1].open(), self.sequences,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(output_fastq[1][1].open(), self.sequences,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(output_fastq[2][1].open(), self.sequences,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(output_fastq[3][1].open(), self.sequences,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(output_fastq[4][1].open(), self.sequences,
[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',
'sample3,sample3_2_L001_R1_001.fastq.gz,forward\n',
'sample2,sample2_3_L001_R1_001.fastq.gz,forward\n',
'sample5,sample5_4_L001_R1_001.fastq.gz,forward\n',
'sample4,sample4_5_L001_R1_001.fastq.gz,forward\n'
]
self._compare_manifests(act_manifest, exp_manifest)
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_valid(self):
actual = emp_single(self.bsi, self.barcode_map)
output_fastq = list(actual.sequences.iter_views(FastqGzFormat))
# five per-sample files were written
self.assertEqual(len(output_fastq), 5)
# sequences in sample1 are correct
self._validate_sample_fastq(output_fastq[0][1].open(), self.sequences,
[0, 5])
# sequences in sample2 are correct
self._validate_sample_fastq(output_fastq[1][1].open(), self.sequences,
[2, 4])
# sequences in sample3 are correct
self._validate_sample_fastq(output_fastq[2][1].open(), self.sequences,
[1, 3])
# sequences in sample4 are correct
self._validate_sample_fastq(output_fastq[3][1].open(), self.sequences,
[7, 10])
# sequences in sample5 are correct
self._validate_sample_fastq(output_fastq[4][1].open(), self.sequences,
[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',
'sample3,sample3_2_L001_R1_001.fastq.gz,forward\n',
'sample2,sample2_3_L001_R1_001.fastq.gz,forward\n',
'sample5,sample5_4_L001_R1_001.fastq.gz,forward\n',
'sample4,sample4_5_L001_R1_001.fastq.gz,forward\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_single(self.bsi, barcodes)
def test_variable_length_barcodes(self):
barcodes = pd.Series(['AAA', 'AACC'], index=['sample1', 'sample2'])
barcodes = qiime2.MetadataCategory(barcodes)
with self.assertRaises(ValueError):
emp_single(self.bsi, barcodes)
