def get_bases_mask(run_info_xml,sample_sheet_file):
"""
Get bases mask string
Generates initial bases mask based on data in RunInfo.xml (which
says how many reads there are, how many cycles in each read, and
which are index reads). Then updates this using the barcode
information in the sample sheet file.
Arguments:
run_info_xml: name and path of RunInfo.xml file from the
sequencing run
sample_sheet_file: name and path of sample sheet file.
Returns:
Bases mask string e.g. 'y101,I6'.
"""
# Get initial bases mask
bases_mask = IlluminaData.IlluminaRunInfo(run_info_xml).bases_mask
print "Bases mask: %s (from RunInfo.xml)" % bases_mask
# Update bases mask from sample sheet
example_barcode = IlluminaData.get_casava_sample_sheet(sample_sheet_file)[0]['Index']
bases_mask = IlluminaData.fix_bases_mask(bases_mask,example_barcode)
print "Bases mask: %s (updated for barcode sequence '%s')" % (bases_mask,
example_barcode)
return bases_mask
def get_bases_mask(run_info_xml, sample_sheet_file):
"""
Get bases mask string
Generates initial bases mask based on data in RunInfo.xml (which
says how many reads there are, how many cycles in each read, and
which are index reads). Then updates this using the barcode
information in the sample sheet file.
Arguments:
run_info_xml: name and path of RunInfo.xml file from the
sequencing run
sample_sheet_file: name and path of sample sheet file.
Returns:
Bases mask string e.g. 'y101,I6'.
"""
# Get initial bases mask
bases_mask = IlluminaData.IlluminaRunInfo(run_info_xml).bases_mask
print "Bases mask: %s (from RunInfo.xml)" % bases_mask
# Update bases mask from sample sheet
example_barcode = IlluminaData.get_casava_sample_sheet(
sample_sheet_file)[0]['Index']
bases_mask = IlluminaData.fix_bases_mask(bases_mask, example_barcode)
print "Bases mask: %s (updated for barcode sequence '%s')" % (
bases_mask, example_barcode)
return bases_mask
p.add_option('-N','--nprocessors',action="store",dest="cores",default=1,type='int',
help="spread work across multiple processors/cores (default is 1)")
options,args = p.parse_args()
# Check arguments
if not args and options.counts_file_in is None:
p.error("Need to supply at least one input Fastq file, a bclToFastq output "
"directory, or a counts file from a previous run (if using -c)")
if options.report_file is not None:
print "Writing report to %s" % options.report_file
fp = open(options.report_file,'w')
else:
fp = sys.stdout
# Handle input sample sheet
if options.sample_sheet is not None:
print "Loading sample sheet data from %s" % options.sample_sheet
sample_sheet = IlluminaData.get_casava_sample_sheet(options.sample_sheet)
# Process according to inputs
if options.counts_file_in:
# Use counts from a previously generated file
counts_file = options.counts_file_in
print "Loading counts from %s" % counts_file
counts = dict()
for line in open(counts_file,'r'):
seq = line.split('\t')[1]
count = int(line.split('\t')[2])
counts[seq] = count
report(counts,nseqs=options.n,cutoff=options.cutoff,fp=fp)
# Match barcodes to index sequences in sample sheet
if options.sample_sheet:
if options.lanes is not None:
lanes = [int(lane) for lane in options.lanes.split(',')]
p.add_option_group(deprecated_options)
# Process command line
options, args = p.parse_args()
if len(args) != 1:
p.error("input is a single SampleSheet.csv file")
if options.miseq:
logging.warning(
"--miseq option no longer necessary; MiSEQ-style sample sheets "
"are now converted automatically")
# Get input sample sheet file
samplesheet = args[0]
if not os.path.isfile(samplesheet):
logging.error("sample sheet '%s': not found" % samplesheet)
sys.exit(1)
# Read in the data as CSV
data = IlluminaData.get_casava_sample_sheet(samplesheet)
# Remove lanes
if options.lanes is not None:
lanes = parse_lane_expression(options.lanes)
print "Keeping lanes %s, removing the rest" % ','.join(
[str(x) for x in lanes])
new_data = IlluminaData.CasavaSampleSheet()
for line in data:
if line['Lane'] in lanes:
print "Keeping %s" % line
new_data.append(tabdata="%s" % line)
data = new_data
# Update the SampleID and SampleProject fields
for sample_id in options.sample_id:
lanes, name = parse_name_expression(sample_id)
for line in data:
"if required)")
p.add_option_group(deprecated_options)
# Process command line
options,args = p.parse_args()
if len(args) != 1:
p.error("input is a single SampleSheet.csv file")
if options.miseq:
logging.warning("--miseq option no longer necessary; MiSEQ-style sample sheets "
"are now converted automatically")
# Get input sample sheet file
samplesheet = args[0]
if not os.path.isfile(samplesheet):
logging.error("sample sheet '%s': not found" % samplesheet)
sys.exit(1)
# Read in the data as CSV
data = IlluminaData.get_casava_sample_sheet(samplesheet)
# Remove lanes
if options.lanes is not None:
lanes = parse_lane_expression(options.lanes)
print "Keeping lanes %s, removing the rest" % ','.join([str(x) for x in lanes])
new_data = IlluminaData.CasavaSampleSheet()
for line in data:
if line['Lane'] in lanes:
print "Keeping %s" % line
new_data.append(tabdata="%s" % line)
data = new_data
# Update the SampleID and SampleProject fields
for sample_id in options.sample_id:
lanes,name = parse_name_expression(sample_id)
for line in data:
if line['Lane'] in lanes:
