def test_format(self):
# This test exists mainly to assert that the single-file directory
# format is defined and functional. More extensive testing is performed
# on its underlying format (FastqGzFormat).
filepath = self.get_data_path('forward.fastq.gz')
shutil.copy(filepath,
os.path.join(self.temp_dir.name, 'forward.fastq.gz'))
format = MultiplexedSingleEndBarcodeInSequenceDirFmt(
self.temp_dir.name, mode='r')
# Should not error.
format.validate()
def setUp(self):
super().setUp()
self.fastq_fp = \
self.get_data_path('forward.fastq.gz')
self.fastq = FastqGzFormat(self.fastq_fp, mode='r')
self.seqs_dir_fmt = MultiplexedSingleEndBarcodeInSequenceDirFmt()
self.seqs_dir_fmt.file.write_data(self.fastq, FastqGzFormat)
self.barcode_series = pd.Series(['A', 'G'],
index=['sample_a', 'sample_b'])
self.per_sample_dir_fmt = SingleLanePerSampleSingleEndFastqDirFmt()
self.untrimmed_dir_fmt = MultiplexedSingleEndBarcodeInSequenceDirFmt()
def demux_single(seqs: MultiplexedSingleEndBarcodeInSequenceDirFmt,
barcodes: qiime2.MetadataCategory,
error_rate: float=0.1) -> \
(CasavaOneEightSingleLanePerSampleDirFmt,
MultiplexedSingleEndBarcodeInSequenceDirFmt):
untrimmed = MultiplexedSingleEndBarcodeInSequenceDirFmt()
return _demux(seqs, barcodes, error_rate, untrimmed)
def demux_single(seqs: MultiplexedSingleEndBarcodeInSequenceDirFmt,
barcodes: qiime2.MetadataCategory,
error_tolerance: float=0.1) -> \
(CasavaOneEightSingleLanePerSampleDirFmt,
MultiplexedSingleEndBarcodeInSequenceDirFmt):
barcodes = barcodes.to_series()
per_sample_sequences = CasavaOneEightSingleLanePerSampleDirFmt()
untrimmed = MultiplexedSingleEndBarcodeInSequenceDirFmt()
_write_empty_fastq_to_mux_barcode_in_seq_fmt(untrimmed)
with tempfile.NamedTemporaryFile() as barcode_fasta:
_write_barcode_fasta(barcodes, barcode_fasta)
cmd = _build_demux_command(seqs, barcode_fasta, per_sample_sequences,
untrimmed, error_tolerance)
run_command(cmd)
_rename_files(per_sample_sequences, barcodes)
muxed = len(list(per_sample_sequences.sequences.iter_views(FastqGzFormat)))
if muxed == 0:
raise ValueError('No samples were demultiplexed.')
return per_sample_sequences, untrimmed