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
def setUp(self):
"""Set up a test fastq file
"""
self.rootdir = tempfile.mkdtemp(
prefix="test_extract_pre_casava_index_")
# Set up a fastq file
fd, fqfile = tempfile.mkstemp(dir=self.rootdir, suffix=".fastq.gz")
os.close(fd)
fqw = fu.FastQWriter(fqfile)
# Generate a set of indexes
seqlen = 101
bclen = 6
barcodes = dict(
zip([td.generate_barcode(bclen) for i in xrange(100)],
[random.randint(10, 100) for i in xrange(100)]))
# Generate fastq records and append the barcode
for barcode, nseqs in barcodes.items():
for i in xrange(nseqs):
rec = td.generate_fastq_record(**{
'index': barcode,
'sequence_length': seqlen
})
rec[1] = "{}{}A".format(rec[1], barcode)
fqw.write(rec)
fqw.close()
self.sequence_length = seqlen
self.barcode_length = bclen
self.barcodes = barcodes
self.fastq_file = fqfile
def setUp(self):
"""Set up a test fastq file
"""
self.rootdir = tempfile.mkdtemp(prefix="test_extract_pre_casava_index_")
# Set up a fastq file
fd, fqfile = tempfile.mkstemp(dir=self.rootdir,suffix=".fastq.gz")
os.close(fd)
fqw = fu.FastQWriter(fqfile)
# Generate a set of indexes
seqlen = 101
bclen = 6
barcodes = dict(zip([td.generate_barcode(bclen) for i in xrange(100)],[random.randint(10,100) for i in xrange(100)]))
# Generate fastq records and append the barcode
for barcode, nseqs in barcodes.items():
for i in xrange(nseqs):
rec = td.generate_fastq_record(**{'index': barcode, 'sequence_length': seqlen})
rec[1] = "{}{}A".format(rec[1],barcode)
fqw.write(rec)
fqw.close()
self.sequence_length = seqlen
self.barcode_length = bclen
self.barcodes = barcodes
self.fastq_file = fqfile
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_FastQParser_")
# Create some fastq records with different properties
lanes = range(1, 9)
indexes = [td.generate_barcode() for n in xrange(4)]
fd, fqfile = tempfile.mkstemp(suffix=".fastq.gz", dir=self.rootdir)
os.close(fd)
# For each lane and index, create a random number of records
counts = {}
fqw = fu.FastQWriter(fqfile)
for l in lanes:
counts[l] = {}
for ix in indexes:
no = random.randint(10, 99)
counts[l][ix] = no
for n in xrange(no):
fqw.write(td.generate_fastq_record(lane=l, index=ix))
fqw.close()
self.example_fq = fqfile
self.example_counts = counts
def setUp(self):
self.rootdir = tempfile.mkdtemp(prefix="test_FastQParser_")
# Create some fastq records with different properties
lanes = range(1,9)
indexes = [td.generate_barcode() for n in xrange(4)]
fd, fqfile = tempfile.mkstemp(suffix=".fastq.gz", dir=self.rootdir)
os.close(fd)
# For each lane and index, create a random number of records
counts = {}
fqw = fu.FastQWriter(fqfile)
for l in lanes:
counts[l] = {}
for ix in indexes:
no = random.randint(10,99)
counts[l][ix] = no
for n in xrange(no):
fqw.write(td.generate_fastq_record(lane=l, index=ix))
fqw.close()
self.example_fq = fqfile
self.example_counts = counts
