def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_illumina_run_")
# Create a fcdir
self.exp_fcid = td.generate_fc_barcode()
self.exp_fcdir = os.path.join(self.rootdir,td.generate_run_id(fc_barcode=self.exp_fcid))
os.mkdir(self.exp_fcdir)
# Create multiple sequence read directories
self.exp_seqdir = [os.path.join(self.exp_fcdir,"Unaligned"),
os.path.join(self.exp_fcdir,"Unaligned_L6"),
os.path.join(self.exp_fcdir,"Unaligned_L8")]
for d in self.exp_seqdir:
os.mkdir(d)
# Create directories for undetermined indices reads
self.exp_unmatched_directory = [os.path.join(d,"Undetermined_indices") for d in self.exp_seqdir[:-1]]
for d in self.exp_unmatched_directory:
os.mkdir(d)
# Create basecall stats directories
self.exp_basecall_stats = [os.path.join(d,"Basecall_Stats_{}".format(self.exp_fcid)) for d in self.exp_seqdir[1:]]
for d in self.exp_basecall_stats:
os.mkdir(d)
self.run = IlluminaRun(self.exp_fcdir)
def test_get_samplesheet(self):
"""Locate the samplesheet in a folder
"""
# Work in a separate subdirectory
subdir = os.path.join(self.rootdir,"test_get_samplesheet")
os.mkdir(subdir)
# Create a few random files and folders and assert that they are not returned
suffixes = [".csv","",""]
for n in range(3):
os.mkdir(os.path.join(subdir,''.join(random.choice(string.ascii_uppercase) for x in range(5))))
fh, _ = tempfile.mkstemp(dir=subdir, suffix=suffixes[n])
os.close(fh)
self.assertIsNone(IlluminaRun.get_samplesheet(subdir),
"Getting non-existing samplesheet did not return None")
# Create a SampleSheet.csv and a [FCID].csv file and assert that they are
# returned with a preference for the [FCID].csv file
fcid = td.generate_fc_barcode()
fcdir = os.path.join(subdir,td.generate_run_id(fc_barcode=fcid))
os.mkdir(fcdir)
ss = [os.path.join(fcdir,"SampleSheet.csv"),
os.path.join(fcdir,"{}.csv".format(fcid))]
for s in ss:
utils.touch_file(s)
self.assertEqual(s,IlluminaRun.get_samplesheet(fcdir),
"Did not get existing {}".format(os.path.basename(s)))
shutil.rmtree(subdir)
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_illumina_run_")
# Create a fcdir
self.exp_fcid = td.generate_fc_barcode()
self.exp_fcdir = os.path.join(
self.rootdir, td.generate_run_id(fc_barcode=self.exp_fcid))
os.mkdir(self.exp_fcdir)
# Create multiple sequence read directories
self.exp_seqdir = [
os.path.join(self.exp_fcdir, "Unaligned"),
os.path.join(self.exp_fcdir, "Unaligned_L6"),
os.path.join(self.exp_fcdir, "Unaligned_L8")
]
for d in self.exp_seqdir:
os.mkdir(d)
# Create directories for undetermined indices reads
self.exp_unmatched_directory = [
os.path.join(d, "Undetermined_indices")
for d in self.exp_seqdir[:-1]
]
for d in self.exp_unmatched_directory:
os.mkdir(d)
# Create basecall stats directories
self.exp_basecall_stats = [
os.path.join(d, "Basecall_Stats_{}".format(self.exp_fcid))
for d in self.exp_seqdir[1:]
]
for d in self.exp_basecall_stats:
os.mkdir(d)
self.run = IlluminaRun(self.exp_fcdir)
def test_get_samplesheet(self):
"""Test that the _get_samplesheet method behaves as expected
"""
# Create a few random files and folders and assert that they are not returned
suffixes = [".csv","",""]
for n in range(3):
os.mkdir(os.path.join(self.rootdir,''.join(random.choice(string.ascii_uppercase) for x in range(5))))
fh, _ = tempfile.mkstemp(dir=self.rootdir, suffix=suffixes[n])
os.close(fh)
self.assertIsNone(sq.get_samplesheet(self.rootdir),
"Getting non-existing samplesheet did not return None")
# Create a SampleSheet.csv and a [FCID].csv file and assert that they are
# returned with a preference for the [FCID].csv file
fcid = td.generate_fc_barcode()
fcdir = os.path.join(self.rootdir,td.generate_run_id(fc_barcode=fcid))
os.mkdir(fcdir)
ss = [os.path.join(fcdir,"SampleSheet.csv"),
os.path.join(fcdir,"{}.csv".format(fcid))]
for s in ss:
utils.touch_file(s)
self.assertEqual(s,sq.get_samplesheet(fcdir),
"Did not get existing {}".format(os.path.basename(s)))
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_fastq_utils_")
# Generate some test fastq_files
indexes = {td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): []}
args = {'instrument': td.generate_instrument(),
'run_number': random.randint(101,9999),
'fcid': td.generate_fc_barcode(),
'lane': 1,
'pair': True}
fd, f1 = tempfile.mkstemp(suffix="_R1.fastq.gz", dir=self.rootdir)
os.close(fd)
f2 = f1.replace("_R1","_R2")
f1h = fu.FastQWriter(f1)
f2h = fu.FastQWriter(f2)
for n in range(1000):
args['index'] = random.choice(indexes.keys())
record = td.generate_fastq_record(**args)
indexes[args['index']].append(record[0])
f1h.write(record[0:4])
f2h.write(record[4:])
f1h.close()
f2h.close()
# Create a samplesheet to use for demultiplexing using all but the last index
samplesheet = f1.replace("_R1.fastq.gz",".csv")
sdata = []
for n, index in enumerate(indexes.keys()[0:-1]):
sdata.append([args['fcid'],
str(args['lane']),
"Sample_{}".format(str(n)),
"unknown",
index,
"DemuxTest",
"0",
"",
"",
"DemuxTestProject"])
# Add an entry that will not match
s = copy.copy(sdata[-1])
s[1] = str(args['lane']+1)
sdata.append(s)
self.samplesheet = td._write_samplesheet(sdata,samplesheet)
self.indexes = indexes
self.fastq_1 = f1
self.fastq_2 = f2
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_fastq_utils_")
# Generate some test fastq_files
indexes = {
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): [],
td.generate_barcode(): []
}
args = {
'instrument': td.generate_instrument(),
'run_number': random.randint(101, 9999),
'fcid': td.generate_fc_barcode(),
'lane': 1,
'pair': True
}
fd, f1 = tempfile.mkstemp(suffix="_R1.fastq.gz", dir=self.rootdir)
os.close(fd)
f2 = f1.replace("_R1", "_R2")
f1h = fu.FastQWriter(f1)
f2h = fu.FastQWriter(f2)
for n in range(1000):
args['index'] = random.choice(indexes.keys())
record = td.generate_fastq_record(**args)
indexes[args['index']].append(record[0])
f1h.write(record[0:4])
f2h.write(record[4:])
f1h.close()
f2h.close()
# Create a samplesheet to use for demultiplexing using all but the last index
samplesheet = f1.replace("_R1.fastq.gz", ".csv")
sdata = []
for n, index in enumerate(indexes.keys()[0:-1]):
sdata.append([
args['fcid'],
str(args['lane']), "Sample_{}".format(str(n)), "unknown",
index, "DemuxTest", "0", "", "", "DemuxTestProject"
])
# Add an entry that will not match
s = copy.copy(sdata[-1])
s[1] = str(args['lane'] + 1)
sdata.append(s)
self.samplesheet = td._write_samplesheet(sdata, samplesheet)
self.indexes = indexes
self.fastq_1 = f1
self.fastq_2 = f2
