else:
impactdir = None
# Counting and printing out number of records of input file
numOfRecords = core.countRecords(copts.input)
if not copts.stdout: printNumOfRecords(numOfRecords)
if options.args['logfile']:
logging.info(str(numOfRecords) + ' records to be annotated.')
# Writing header to output file
if options.args['outputformat'] == 'VCF':
outfile = open(copts.output + '.vcf', 'w')
else:
outfile = open(copts.output + '.txt', 'w')
header = readHeader(copts.input)
core.writeHeader(options, '\n'.join(header), outfile, copts.stdout)
outfile.close()
# Find break points in the input file
breaks = findFileBreaks(copts.input, copts.threads)
# Initializing annotation processes
threadidx = 0
processes = []
for (startline, endline) in breaks:
threadidx += 1
processes.append(
SingleJob(threadidx, options, copts, startline, endline, genelist,
transcriptlist, snplist, impactdir, numOfRecords))
# Running annotation processes
def run(copts, version, default_config_file):
copts.threads = int(copts.threads)
if copts.threads > 1:
copts.stdout = False
# Use default path read from the default_config_path file, if -c is not used
if copts.conf is None:
copts.conf = default_config_file
# Check if input and configuration files exist
if copts.conf is None:
print '\nError: no configuration file specified.'
print 'Please use option -c or add the absolute path to the default_config_path file.\n'
quit()
if not os.path.isfile(copts.conf):
print '\nError: configuration file (' + copts.conf + ') cannot be found.\n'
quit()
if not os.path.isfile(copts.input):
print '\nError: input file (' + copts.input + ') cannot be found.\n'
quit()
# Reading options from configuration file
options = Options(copts.conf)
# Initializing log file
if options.args['logfile']:
logging.basicConfig(filename=copts.output + '.log',
filemode='w',
format='%(asctime)s %(levelname)s: %(message)s',
level=logging.DEBUG)
# Printing out version information and start time
if not copts.stdout: starttime = printStartInfo(version)
if options.args['logfile']:
logging.info('CAVA ' + version + ' started.')
# Checking if options specified in the configuration file are correct
core.checkOptions(options)
# Printing out configuration, input and output file names
if not copts.stdout:
printInputFileNames(copts, options)
# Reading gene, transcript and snp lists from files
genelist = core.readSet(options, 'genelist')
transcriptlist = core.readSet(options, 'transcriptlist')
snplist = core.readSet(options, 'snplist')
# Parsing @impactdef string
if not (options.args['impactdef'] == '.'
or options.args['impactdef'] == ''):
impactdir = dict()
valuev = options.args['impactdef'].split('|')
for i in range(len(valuev)):
classv = valuev[i].split(',')
for c in classv:
impactdir[c.strip()] = str(i + 1)
else:
impactdir = None
# Counting and printing out number of records of input file
numOfRecords = core.countRecords(copts.input)
if not copts.stdout:
printNumOfRecords(numOfRecords)
if options.args['logfile']:
logging.info(str(numOfRecords) + ' records to be annotated.')
# Writing header to output file
if options.args['outputformat'] == 'VCF':
outfile = open(copts.output + '.vcf', 'w')
else:
outfile = open(copts.output + '.txt', 'w')
header = readHeader(copts.input)
core.writeHeader(options, '\n'.join(header), outfile, copts.stdout)
outfile.close()
# Find break points in the input file
breaks = findFileBreaks(copts.input, copts.threads)
# Initializing annotation processes
threadidx = 0
processes = []
for (startline, endline) in breaks:
threadidx += 1
processes.append(
SingleJob(threadidx, options, copts, startline, endline, genelist,
transcriptlist, snplist, impactdir, numOfRecords))
# Running annotation processes
for process in processes:
process.start()
for process in processes:
process.join()
# Merging tmp files
if copts.threads > 1:
mergeTmpFiles(copts.output, options.args['outputformat'],
copts.threads)
# Printing out summary information and end time
if not copts.stdout:
printEndInfo(options, copts, starttime)