def get_pgm_log_files(rawdatadir):
# Create a tarball of the pgm raw data log files for inclusion into CSA.
# tarball it now before the raw data gets deleted.
# inst diagnostic files are always in toplevel raw data dir:
if 'thumbnail' in rawdatadir:
rawdatadir = rawdatadir.replace('thumbnail', '')
files=[
'explog_final.txt',
'explog.txt',
'InitLog.txt',
'InitLog1.txt',
'InitLog2.txt',
'RawInit.txt',
'RawInit.jpg',
'InitValsW3.txt',
'InitValsW2.txt',
'Controller',
'debug',
'chipCalImage.bmp.bz2',
]
for afile in files:
if os.path.exists(os.path.join(rawdatadir,afile)):
make_zip ('pgm_logs.zip',os.path.join(rawdatadir,afile),arcname=afile)
return
def get_pgm_log_files(rawdatadir):
# Create a tarball of the instrument raw data log files for inclusion into CSA.
# tarball it now before the raw data gets deleted.
from ion.utils.makeCSA import rawdata_patterns as files
# inst diagnostic files are always in toplevel raw data dir:
if 'thumbnail' in rawdatadir:
rawdatadir = rawdatadir.replace('thumbnail', '')
for afile in files:
if os.path.exists(os.path.join(rawdatadir, afile)):
make_zip('pgm_logs.zip', os.path.join(rawdatadir, afile), arcname=afile)
def get_pgm_log_files(rawdatadir):
# Create a tarball of the instrument raw data log files for inclusion into CSA.
# tarball it now before the raw data gets deleted.
from ion.utils.makeCSA import rawdata_patterns as files
# inst diagnostic files are always in toplevel raw data dir:
if "thumbnail" in rawdatadir:
rawdatadir = rawdatadir.replace("thumbnail", "")
for afile in files:
if os.path.exists(os.path.join(rawdatadir, afile)):
make_zip("pgm_logs.zip",
os.path.join(rawdatadir, afile),
arcname=afile)
def get_pgm_log_files(rawdatadir):
# Create a tarball of the pgm raw data log files for inclusion into CSA.
# tarball it now before the raw data gets deleted.
files = [
"explog_final.txt",
"explog.txt",
"InitLog.txt",
"RawInit.txt",
"RawInit.jpg",
"InitValsW3.txt",
"InitValsW2.txt",
"Controller",
"debug",
]
for afile in files:
make_zip("pgm_logs.zip", os.path.join(rawdatadir, afile), arcname=afile)
return
def get_pgm_log_files(rawdatadir):
# Create a tarball of the pgm raw data log files for inclusion into CSA.
# tarball it now before the raw data gets deleted.
# inst diagnostic files are always in toplevel raw data dir:
if "thumbnail" in rawdatadir:
rawdatadir = rawdatadir.replace("thumbnail", "")
files = [
"explog_final.txt",
"explog.txt",
"InitLog.txt",
"InitLog1.txt",
"InitLog2.txt",
"RawInit.txt",
"RawInit.jpg",
"InitValsW3.txt",
"InitValsW2.txt",
"Controller",
"debug",
]
for afile in files:
if os.path.exists(os.path.join(rawdatadir, afile)):
make_zip("pgm_logs.zip", os.path.join(rawdatadir, afile), arcname=afile)
return
ionstats_file = 'ionstats_alignment.json'
try:
stats = json.load(open(ionstats_file))
l = stats['full']['max_read_length']
graph_max_x = int(round(l + 49, -2))
# Make alignment_rate_plot.png and base_error_plot.png
ionstats_plots.alignment_rate_plot2(ionstats_file,
'alignment_rate_plot.png',
int(graph_max_x))
ionstats_plots.base_error_plot(ionstats_file,
'base_error_plot.png',
int(graph_max_x))
except:
traceback.print_exc()
if args.zip and len(args.files) > 1:
# zip barcoded files
zipname = args.zip
printtime("Zip merged barcode files to %s" % zipname)
for filename in args.files:
if os.path.exists(filename):
try:
make_zip(zipname, filename, arcname=filename)
except:
print("ERROR: zip target: %s" % filename)
traceback.print_exc()
printtime("DEBUG: CA job done.")
'alignment_rate_plot.png', int(graph_max_x))
print("Ionstats plot created successfully")
except:
print("ERROR: Failed to generate alignment rate plot")
try:
# Make base_error_plot.png
base_error_plot.generate_base_error_plot(
'alignStats_err.json',
'base_error_plot.png',int(graph_max_x))
except:
print("ERROR: Failed to generate base error plot")
traceback.print_exc()
if args.zip and len(args.files) > 1:
# zip barcoded files
zipname = args.zip
print "Zip merged barcode files to %s" % zipname
for filename in args.files:
if os.path.exists(filename):
try:
make_zip(zipname, filename, arcname=filename)
except:
print("ERROR: zip target: %s" % filename)
traceback.print_exc()
def runForBarcodes():
global pluginParams, pluginResult, pluginReport
# read barcode ids
barcodes = []
try:
bcfileName = pluginParams['analysis_dir']+'/barcodeList.txt'
with open(bcfileName) as bcfile:
for line in bcfile:
if line.startswith('barcode '):
barcodes.append(line.split(',')[1])
except:
printerr("Reading barcode list file '%s'" % bcfileName)
raise
numGoodBams = 0
numUnalBams = 0
minFileSize = pluginParams['cmdOptions'].minbamsize
(bcBamPath,bcBamRoot) = os.path.split(pluginParams['bamroot'])
validBarcodes = []
for barcode in barcodes:
# use unmapped BAM if there else mapped BAM (unmapped may not be present on Proton)
bcbam = os.path.join( bcBamPath, "%s_%s"%(barcode,bcBamRoot) )
if not os.path.exists(bcbam):
bcbam = os.path.join( pluginParams['analysis_dir'], "%s_rawlib.bam"%barcode )
numUnalBams += 1
if not os.path.exists(bcbam):
bcbam = ": BAM file not found"
numUnalBams -= 1
elif os.stat(bcbam).st_size < minFileSize:
bcbam = ": BAM file too small"
else:
numGoodBams += 1
validBarcodes.append(barcode)
printlog("Processing %d barcodes...\n" % numGoodBams)
if numUnalBams > 0:
printlog("Warning: %d barcodes will be processed using mapped BAM files. (Unmapped BAMs were not available.)\n" % numUnalBams)
pluginReport['num_barcodes_processed'] = numGoodBams
pluginReport['num_barcodes_failed'] = 0
# iterate over all barcodes and process the valid ones
skip_analysis = pluginParams['cmdOptions'].skip_analysis
stop_on_error = pluginParams['cmdOptions'].stop_on_error
create_scraper = pluginParams['cmdOptions'].scraper
sample_names = pluginParams['sample_names']
postout = False; # just for logfile prettiness
sampleNamesFile = ("%s/sampleNames.txt" % pluginParams['results_dir'])
sampleNamesFW = open(sampleNamesFile, 'w')
for barcode in barcodes:
sample = sample_names[barcode] if barcode in sample_names else ''
sampleNamesFW.write("%s:%s\n" %(barcode, sample))
sampleNamesFW.close()
binDir = os.path.join(pluginParams['plugin_dir'], 'bin')
outDir = pluginParams['results_dir']
analysisDir = pluginParams['analysis_dir']
global hotspotsFile
hotspotsFile = pluginParams['hotspots_file']
global targetsFile
targetsFile = pluginParams['regions_file']
printlog("hotspots file is %s " %hotspotsFile)
pluginOutDir = os.path.join(analysisDir, 'plugin_out')
global variantCallerName
if not filter(re.compile(r'variantCaller_out*').search, os.listdir(pluginOutDir)):
printerr("Variant Caller plugin has to be run before launching the PGX Analysis plugin. Please run Torrent Variant Caller plugin")
return
variantCallerName = max(filter(re.compile(r'variantCaller_out*').search, os.listdir(pluginOutDir)))
global coverageAnalysisName
if not filter(re.compile(r'coverageAnalysis_out*').search, os.listdir(pluginOutDir)):
printerr("Coverage Analysis plugin has to be run before launching the PGX Analysis plugin. Please run the Coverage Analysis plugin")
return
coverageAnalysisName = max(filter(re.compile(r'coverageAnalysis_out*').search, os.listdir(pluginOutDir)))
printlog(variantCallerName)
printlog(coverageAnalysisName)
variantCallerDir = os.path.join(pluginOutDir, variantCallerName)
printlog("variantcaller dir is %s" % variantCallerDir)
coverageAnalysisDir = os.path.join(pluginOutDir, coverageAnalysisName)
hotspotsFileVC = ""
resultsJsonFile = os.path.join(variantCallerDir, "results.json")
if not os.path.isfile(resultsJsonFile):
printerr("VariantCaller results are not ready. Please wait for the variant Caller plugin to finish and then launch the PGx plugin")
return
covAnalysisResultsJsonFile = os.path.join(coverageAnalysisDir, "results.json")
if not os.path.isfile(covAnalysisResultsJsonFile):
printerr("Coverage Analysis results are not ready. Please wait for the Coverage Analysis plugin to finish and then launch the PGx plugin")
return
targetsFileVC = ""
with open(resultsJsonFile) as fin:
for line in fin:
if "hotspots_bed" in line and ":" in line and "type" not in line :
kvp = line.split(":")
hotspotsFileVC = (os.path.basename(kvp[1].strip()))
if "," in hotspotsFileVC:
hotspotsFileVC = hotspotsFileVC[:-2]
else:
hotspotsFileVC = hotspotsFileVC[:-1]
hotspotsFileVC = os.path.join(variantCallerDir, hotspotsFileVC)
if "targets_bed" in line and ":" in line and "type" not in line :
kvp = line.split(":")
targetsFileVC = (os.path.basename(kvp[1].strip()))
if "," in targetsFileVC:
targetsFileVC = targetsFileVC[:-2]
else:
targetsFileVC = targetsFileVC[:-1]
targetsFileVC = os.path.join(variantCallerDir, targetsFileVC)
if not hotspotsFileVC:
printerr("Cannot obtain the hotspots file used by the VariantCaller. Trying to obtain the hotspots file from plan")
else:
hotspotsFile = hotspotsFileVC
if not hotspotsFile:
printerr("The plan is not set up with a hotspots file.")
return
if not targetsFileVC:
printerr("Cannot obtain the Target Regions file used by the VariantCaller. Trying to obtain the regions file from plan")
else:
targetsFile = targetsFileVC
cmd = ("java -jar %s/PGX_Analysis.jar %s %s %s %s %s %s %s %s" % (binDir, hotspotsFile, outDir, bcfileName, analysisDir, variantCallerDir, coverageAnalysisDir, binDir, sampleNamesFile));
printlog(cmd)
RunCommand(cmd);
# parse out data in results text file to dict AND coverts spaces to underscores in keys to avoid Django issues
statsfile = 'summary.txt'
analysisData = parseToDict( os.path.join(outDir,statsfile), "\t" )
global numPass, numUniformity, numAvgCov, totalSamples
totalSamples = numGoodBams
numPass = numGoodBams
numAvgCov = 0
numUniformity = 0
for keys,values in analysisData.items():
printlog(keys)
printlog(values)
for file in os.listdir("%s/cnvCalls" %outDir):
if file.endswith(".log"):
cnvCallsDir = os.path.join(outDir,"cnvCalls")
filein = os.path.join(cnvCallsDir, file)
printlog("filein is %s " % filein)
with open(filein) as fin:
sep = "="
for line in fin:
if("valid Samples =" in line):
kvp = line.split(sep);
totalSamples = kvp[1].strip()
elif("CNV Calling =" in line):
kvp = line.split(sep);
numPass = kvp[1].strip()
elif("Average coverage" in line):
kvp = line.split(sep);
numAvgCov = kvp[1].strip()
elif("Uniformate Rate" in line):
kvp = line.split(sep);
numUniformity = kvp[1].strip()
zipfilename = "%s/cnvExports.zip" % outDir
cnvExportsDir = "%s/cnvExports" % outDir
for file in os.listdir(cnvExportsDir):
if file.endswith("_cn.txt"):
filein = os.path.join(cnvExportsDir, file)
compress.make_zip(zipfilename, filein, arcname=os.path.basename(filein), use_sys_zip = False)
vcfZipFilename = "%s/%s.vcf.zip" % (outDir, pluginParams['prefix'])
mergedVcfsDir = "%s/merged_VCFs" % outDir
for file in os.listdir(mergedVcfsDir):
if file.endswith(".gz") or file.endswith(".tbi"):
filein = os.path.join(mergedVcfsDir, file)
compress.make_zip(vcfZipFilename, filein, arcname=os.path.basename(filein), use_sys_zip = False)
global barcodeData
for barcode in validBarcodes:
barcode_entry = {}
sample = sample_names[barcode] if barcode in sample_names else ''
barcode_entry['name'] = barcode
if barcode in analysisData:
barcodeLine = analysisData[barcode]
kvp = barcodeLine.split("\t")
#key = kvp[0].strip()
if sample=='':
barcode_entry['sample'] = 'none'
else:
barcode_entry['sample'] = sample
if len(kvp) < 8 and kvp[2].strip() == 'null':
barcode_entry['hotspots_variants_total'] = "none"
barcode_entry['novel_variants_total'] = "none"
barcode_entry['exon9_cnv'] = kvp[3].strip()
barcode_entry['gene_cnv'] = kvp[4].strip()
barcode_entry['exon9_cnv_confidence'] = kvp[5].strip()
barcode_entry['gene_cnv_confidence'] = kvp[6].strip()
else:
barcode_entry['hotspots_variants_total'] = "%d/%s" %(int(kvp[2].strip()) - int(kvp[4].strip()) - int(kvp[5].strip()), kvp[2].strip())
barcode_entry['novel_variants_total'] = int(kvp[3].strip()) - int(kvp[2].strip())
barcode_entry['exon9_cnv'] = kvp[6].strip()
barcode_entry['gene_cnv'] = kvp[7].strip()
barcode_entry['exon9_cnv_confidence'] = kvp[8].strip()
barcode_entry['gene_cnv_confidence'] = kvp[9].strip()
barcodeData.append(barcode_entry)
updateBarcodeSummaryReport()
if create_scraper:
createScraperLinksFolder( pluginParams['results_dir'], pluginParams['prefix'] )
printtime(traceback.format_exc())
prefix_list = [dataset['file_prefix'] for dataset in datasets_basecaller.get("datasets",[])]
if len(prefix_list) > 1:
zip_task_list = [
('bam', env['ALIGNMENT_RESULTS']),
('bam.bai', env['ALIGNMENT_RESULTS']),
('basecaller.bam', env['BASECALLER_RESULTS']),]
for extension,base_dir in zip_task_list:
zipname = "%s/%s_%s.barcode.%s.zip" % (download_links, env['expName'], env['resultsName'], extension)
for prefix in prefix_list:
try:
filename = "%s/%s_%s_%s.%s" % (download_links, prefix.rstrip('_rawlib'), env['expName'], env['resultsName'], extension)
src = os.path.join(base_dir, prefix+'.'+extension)
if os.path.exists(src):
os.symlink(os.path.relpath(src,os.path.dirname(filename)),filename)
make_zip(zipname, filename, arcname=filename, compressed=False)
except:
printtime("ERROR: target: %s" % filename)
traceback.print_exc()
else:
printtime("MergeTLScript: No barcode run")
printtime("MergeTLScript exit")
sys.exit(0)
]
for extension, base_dir in zip_task_list:
zipname = "%s/%s_%s.barcode.%s.zip" % (
download_links, env['expName'], env['resultsName'],
extension)
for prefix in prefix_list:
try:
filename = "%s/%s_%s_%s.%s" % (
download_links, prefix.rstrip('_rawlib'),
env['expName'], env['resultsName'], extension)
src = os.path.join(base_dir, prefix + '.' + extension)
if os.path.exists(src):
os.symlink(
os.path.relpath(src,
os.path.dirname(filename)),
filename)
make_zip(zipname,
filename,
arcname=filename,
compressed=False)
except:
printtime("ERROR: target: %s" % filename)
traceback.print_exc()
else:
printtime("MergeTLScript: No barcode run")
printtime("MergeTLScript exit")
sys.exit(0)
except:
pass
try:
r = subprocess.call(["ln", "-s", "rawtf.bam", tfbam])
except:
pass
##################################################
# Create zip of files
##################################################
#sampled sff
#make_zip(libsff.replace(".sff",".sampled.sff")+'.zip', libsff.replace(".sff",".sampled.sff"))
#library sff
make_zip(libsff + '.zip', libsff )
#tf sff
make_zip(tfsff + '.zip', tfsff)
#fastq zip
make_zip(fastqpath + '.zip', fastqpath)
#sampled fastq
#make_zip(fastqpath.replace(".fastq",".sampled.fastq")+'.zip', fastqpath.replace(".fastq",".sampled.fastq"))
########################################################
# barcode processing #
# Zip up and move sff, fastq, bam, bai files #
# Move zip files to results directory #
########################################################
def plugin_main():
global PLUGIN_DEV_SKIP_VARIANT_CALLING
global DIRNAME
global TSP_URLPATH_PLUGIN_DIR
global TSP_FILEPATH_PLUGIN_DIR
global startplugin_json
global output_files
parser = OptionParser()
parser.add_option('-d', '--install-dir', help='Directory containing plugin files', dest='install_dir')
parser.add_option('-o', '--output-dir', help='Directory for results files', dest='output_dir')
parser.add_option('-u', '--output-url', help='URL matching the output directory', dest='output_url')
parser.add_option('-r', '--report-dir', help='Directory containing analysis report files', dest='report_dir')
parser.add_option('-f', '--genome-fasta', help='Reference genome fasta file', dest='genome_fasta')
parser.add_option('-s', '--skip-tvc', help='(debug) Skip variant calling and reuse existing results', dest='skip_tvc', action="store_true", default=False)
(options, args) = parser.parse_args()
DIRNAME = options.install_dir #os.environ['DIRNAME'] # home directory for the plugin files
TSP_FILEPATH_PLUGIN_DIR = options.output_dir #os.environ['TSP_FILEPATH_PLUGIN_DIR'] # target plugin results directory
ANALYSIS_DIR = options.report_dir #os.environ['ANALYSIS_DIR'] # main report directory
TSP_URLPATH_PLUGIN_DIR = options.output_url
PLUGIN_DEV_SKIP_VARIANT_CALLING = options.skip_tvc
settings.configure(DEBUG=True, TEMPLATE_DEBUG=True, TEMPLATE_DIRS=((DIRNAME+'/templates'),))
subprocess.call('rm -f %s/results.json' % TSP_FILEPATH_PLUGIN_DIR,shell=True)
printtime('')
printtime('Variant Caller Plugin started')
printtime('')
try:
json_file = open(os.path.join(TSP_FILEPATH_PLUGIN_DIR,'startplugin.json'), 'r')
startplugin_json = json.load(json_file,parse_float=str)
json_file.close()
except:
printtime('ERROR: Failed to load and parse startplugin.json')
return 1
# Uncomment to emulate autorun:
#startplugin_json['pluginconfig'] = {}
vc_options = options_for_manual_start(startplugin_json)
#if not vc_options:
# vc_options = options_for_plan_autostart(startplugin_json)
vc_options['run_name'] = startplugin_json['expmeta'].get('run_name','Current run')
vc_options['genome_name'] = startplugin_json['runinfo'].get('library','')
vc_options['plugin_name'] = startplugin_json['runinfo'].get('plugin_name','')
vc_options['genome_fasta'] = options.genome_fasta #os.environ['TSP_FILEPATH_GENOME_FASTA']
if 'error' in vc_options:
printtime(vc_options['error'])
generate_incomplete_report_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS),vc_options['error'], vc_options)
return 1
f = open(os.path.join(TSP_FILEPATH_PLUGIN_DIR,BASENAME_PARAMETERS_JSON),'w')
json.dump(vc_options['parameters'],f,indent=4)
f.close()
add_output_file('parameters_json', BASENAME_PARAMETERS_JSON)
TSP_FILEPATH_BARCODE_TXT = ANALYSIS_DIR + '/barcodeList.txt'
vc_options['has_barcodes'] = False
if os.path.exists(TSP_FILEPATH_BARCODE_TXT):
vc_options['has_barcodes'] = True
# Call tvc -v to get the version string
tvc_args = vc_options['parameters'].get('meta',{}).get('tvcargs','tvc')
if tvc_args == 'tvc' and os.path.exists(DIRNAME + '/tvc'): # try local binary first, then go to global one
tvc_args = DIRNAME + '/tvc'
vc_options['tvc_version'] = execute_output(tvc_args + ' -v').splitlines()[0]
if vc_options['tvc_version'].endswith('- Torrent Variant Caller'):
vc_options['tvc_version'] = vc_options['tvc_version'][:-24].strip()
# Parameters from plugin customization
printtime('Variant Caller plugin run options:')
printtime(' Plugin name : ' + vc_options['plugin_name'])
printtime(' Plugin start mode : ' + vc_options['start_mode'])
printtime(' Variant Caller version : ' + vc_options['tvc_version'])
printtime(' Run is barcoded : ' + str(vc_options['has_barcodes']))
printtime(' Genome : ' + vc_options['genome_name'])
printtime(' Library Type : ' + vc_options['library_type'])
printtime(' Target Regions : ' + (vc_options['targets_name'] if vc_options['has_targets'] else 'Not using'))
printtime(' Hotspots : ' + (vc_options['hotspots_name'] if vc_options['has_hotspots'] else 'Not using'))
if 'original_parameters' in vc_options:
printtime(' Requested Parameters : ' + vc_options["original_config_line1"])
printtime(' ' + vc_options["original_config_line2"])
printtime(' Auto-Updated Parameters : ' + vc_options["config_line1"])
printtime(' ' + vc_options["config_line2"])
else:
printtime(' Used Parameters : ' + vc_options['config_line1'])
printtime(' ' + vc_options["config_line2"])
printtime(' Trim Reads : ' + str(vc_options['trim_reads']))
printtime('')
printtime('Used files:')
printtime(' Reference Genome : ' + vc_options['genome_fasta'])
printtime(' Parameters file : ' + os.path.join(TSP_FILEPATH_PLUGIN_DIR,BASENAME_PARAMETERS_JSON))
if 'parameters_source' in vc_options:
printtime(' Parameters source file : ' + vc_options['parameters_source'])
if vc_options['has_targets']:
printtime(' Target unmerged BED : ' + vc_options['targets_bed_unmerged'])
printtime(' Target merged BED : ' + vc_options['targets_bed_merged'])
if vc_options['has_hotspots']:
printtime(' Hotspots unmerged BED : ' + vc_options['hotspots_bed_unmerged'])
printtime(' Hotspots merged BED : ' + vc_options['hotspots_bed_merged'])
printtime('')
PLUGIN_HS_ALIGN_DIR = TSP_FILEPATH_PLUGIN_DIR + '/hs_align'
# Remove previous results to avoid displaying old before ready
subprocess.call('rm -f %s/%s' % (TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS),shell=True)
subprocess.call('rm -f %s' % (TSP_FILEPATH_PLUGIN_DIR + '/results.json'),shell=True)
subprocess.call('rm -f %s/*.bed' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -rf %s/*.bam*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -rf %s' % (PLUGIN_HS_ALIGN_DIR),shell=True)
subprocess.call('rm -f %s/hotspot*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/variant*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/allele*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/*.xls' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/*.log' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/*.done' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -rf %s/lifegrid' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
if not PLUGIN_DEV_SKIP_VARIANT_CALLING:
subprocess.call('rm -f %s/SNP*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/indel*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('rm -f %s/TSVC*' % (TSP_FILEPATH_PLUGIN_DIR),shell=True)
printtime('Results folder initialized')
# Get local copy of BED files (may be deleted from system later)
if vc_options['has_targets']:
if not os.path.exists( vc_options['targets_bed_unmerged']):
printtime('ERROR: Cannot locate target regions file: ' + vc_options['targets_bed_unmerged'])
return 1
if not os.path.exists(vc_options['targets_bed_merged']):
printtime('ERROR: Cannot locate merged target regions file: ' + vc_options['targets_bed_merged'])
return 1
subprocess.call('cp -f %s %s/%s' % (vc_options['targets_bed_unmerged'],TSP_FILEPATH_PLUGIN_DIR,os.path.basename(vc_options['targets_bed_unmerged'])),shell=True)
add_output_file('target_regions_bed', os.path.basename(vc_options['targets_bed_unmerged']))
if vc_options['has_hotspots']:
if not os.path.exists(vc_options['hotspots_bed_unmerged']):
printtime('ERROR: Cannot locate hotspots file: ' + vc_options['hotspots_bed_unmerged'])
return 1
if not os.path.exists(vc_options['hotspots_bed_merged']):
printtime('ERROR: Cannot locate merged hotspots file: ' + vc_options['hotspots_bed_merged'])
return 1
vc_options['hotspots_bed_unmerged_local'] = os.path.join(TSP_FILEPATH_PLUGIN_DIR,os.path.basename(vc_options['hotspots_bed_unmerged']))
vc_options['hotspots_bed_unmerged_leftalign'] = vc_options['hotspots_bed_unmerged_local'][:-4] + '.left.bed'
subprocess.call('cp -f %s %s' % (vc_options['hotspots_bed_unmerged'],vc_options['hotspots_bed_unmerged_local']),shell=True)
prepare_hotspots_command = 'tvcutils prepare_hotspots'
prepare_hotspots_command += ' --input-bed %s' % vc_options['hotspots_bed_unmerged']
prepare_hotspots_command += ' --reference %s' % vc_options['genome_fasta']
prepare_hotspots_command += ' --left-alignment on'
prepare_hotspots_command += ' --allow-block-substitutions on'
prepare_hotspots_command += ' --output-bed %s' % vc_options['hotspots_bed_unmerged_leftalign']
prepare_hotspots_command += ' --output-vcf %s/hotspot.vcf' % TSP_FILEPATH_PLUGIN_DIR
run_command(prepare_hotspots_command, 'Generate filtered, left-aligned, and merged hotspot VCF file')
hotspot_file_empty = True
try:
f = open('%s/hotspot.vcf' % TSP_FILEPATH_PLUGIN_DIR, 'r')
for line in f:
if not line or line.startswith('#'):
continue
hotspot_file_empty = False
except:
pass
if hotspot_file_empty:
printtime('Filtered hotspot file has no hotspot entries. Disabling hotspots')
vc_options['has_hotspots'] = False
else:
#run_command('bgzip -c %s/hotspot.vcf > %s/hotspot.vcf.gz' % (TSP_FILEPATH_PLUGIN_DIR,TSP_FILEPATH_PLUGIN_DIR), 'Generate compressed hotspot vcf')
#run_command('tabix -p vcf %s/hotspot.vcf.gz' % (TSP_FILEPATH_PLUGIN_DIR), 'Generate index for compressed hotspot vcf')
vc_options['hotspots_vcf'] = TSP_FILEPATH_PLUGIN_DIR + '/hotspot.vcf'
add_output_file('hotspots_bed', os.path.basename(vc_options['hotspots_bed_unmerged']))
# Make links to js/css used for barcodes table and empty results page
subprocess.call('ln -sf "%s/js" "%s"' % (DIRNAME,TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('ln -sf "%s/css" "%s"' % (DIRNAME,TSP_FILEPATH_PLUGIN_DIR),shell=True)
subprocess.call('ln -sf %s/scripts/*.php3 "%s"' % (DIRNAME,TSP_FILEPATH_PLUGIN_DIR),shell=True)
results_json = {
'Aligned Reads' : vc_options['run_name'],
'Library Type' : vc_options['library_type'],
'Configuration' : vc_options['parameters']['meta']['configuration'],
'Target Regions' : (vc_options['targets_name'] if vc_options['has_targets'] else 'Not using'),
'Target Loci' : (vc_options['hotspots_name'] if vc_options['has_hotspots'] else 'Not using'),
'Trim Reads' : vc_options['trim_reads'],
'barcoded' : 'false',
'files' : []
}
if vc_options['has_targets']:
results_json['targets_bed'] = vc_options['targets_bed_unmerged']
if vc_options['has_hotspots']:
results_json['hotspots_bed'] = vc_options['hotspots_bed_unmerged']
if vc_options['has_barcodes']: # Run for barcodes or single page
barcode_samples_string = startplugin_json.get('plan',{}).get('barcodedSamples',"")
barcode_sample_info = {}
if barcode_samples_string:
barcode_samples_json = json.loads(barcode_samples_string)
for k,v in barcode_samples_json.iteritems():
barcode_sample_info.update(v.get('barcodeSampleInfo',{}))
# Load barcode list
barcode_data = []
bc_list_file = open(TSP_FILEPATH_BARCODE_TXT,'r')
for line in bc_list_file:
if not line.startswith('barcode '):
continue
barcode_entry = {}
barcode_entry['name'] = line.split(',')[1]
barcode_entry['bam'] = os.path.join(ANALYSIS_DIR, barcode_entry['name'] + '_rawlib.bam')
barcode_entry['status'] = 'queued'
if not PLUGIN_DEV_SKIP_VARIANT_CALLING:
subprocess.call('rm -rf %s/%s' % (TSP_FILEPATH_PLUGIN_DIR,barcode_entry['name']),shell=True)
if not os.path.exists(barcode_entry['bam']):
continue
if barcode_entry['name'] in barcode_sample_info:
barcode_nuc_type = barcode_sample_info[barcode_entry['name']].get('nucleotideType','')
if not barcode_nuc_type:
barcode_nuc_type = 'DNA'
barcode_reference = barcode_sample_info[barcode_entry['name']].get('reference',vc_options['genome_name'])
if barcode_nuc_type != 'DNA':
printtime('Skipping barcode ' + barcode_entry['name'] + ' : Unsupported nuc type ' + barcode_nuc_type)
continue
if barcode_reference != vc_options['genome_name']:
printtime('Skipping barcode ' + barcode_entry['name'] + ' : Barcode reference ' + barcode_reference +
'different from run reference ' + vc_options['genome_name'])
continue
# Size enough to process? TODO - just get from datasets_basecaller.json
if os.stat(barcode_entry['bam']).st_size < BCFILE_MIN_SIZE:
barcode_entry['status'] = 'insufficient_reads'
elif is_bam_invalid(barcode_entry['bam']):
barcode_entry['status'] = 'invalid_bam'
barcode_data.append(barcode_entry)
bc_list_file.close()
# End load barcode list
printtime('')
printtime('Processing %d barcodes...' % len(barcode_data))
# Start json file
results_json['barcoded'] = 'true'
results_json['barcodes'] = {}
all_barcodes_successful = True
for barcode_idx in range(len(barcode_data)):
if barcode_data[barcode_idx]['status'] != 'queued':
printtime('Skipping barcode ' + barcode_data[barcode_idx]['name'])
continue
barcode_data[barcode_idx]['status'] = 'in_progress'
generate_barcode_links_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS), barcode_data, vc_options)
BARCODE_DIR = TSP_FILEPATH_PLUGIN_DIR + '/' + barcode_data[barcode_idx]['name']
if not os.path.exists(BARCODE_DIR):
os.makedirs(BARCODE_DIR)
# perform coverage anaysis and write content
printtime('')
printtime('Processing barcode ' + barcode_data[barcode_idx]['name'])
try:
summary = call_variants(BARCODE_DIR,barcode_data[barcode_idx]['bam'],vc_options,barcode_data[barcode_idx]['name'])
results_json['barcodes'][barcode_data[barcode_idx]['name']] = {}
results_json['barcodes'][barcode_data[barcode_idx]['name']]['variants'] = summary.get('variants_total',{})
results_json['barcodes'][barcode_data[barcode_idx]['name']]['hotspots'] = summary.get('hotspots_total',{})
barcode_data[barcode_idx]['summary'] = summary
barcode_data[barcode_idx]['status'] = 'completed'
except:
traceback.print_exc()
all_barcodes_successful = False
barcode_data[barcode_idx]['status'] = 'error'
# Replaced with python zip library because of failures due to too-long argument lists.
#
# #Zip all vcf.gz and vcf.gz.tbi files
# zip_vcf_command = 'echo "'
# zip_vcf_command += ' '.join(('%s/%s/TSVC_variants_%s.vcf.gz' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name']))
# for barcode in barcode_data if barcode['status'] == 'completed')
# zip_vcf_command += ' '
# zip_vcf_command += ' '.join(('%s/%s/TSVC_variants_%s.vcf.gz.tbi' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name']))
# for barcode in barcode_data if barcode['status'] == 'completed')
# zip_vcf_command += '" | xargs zip --junk-paths %s/%s.vcf.zip' % (TSP_FILEPATH_PLUGIN_DIR,vc_options['run_name'])
# run_command(zip_vcf_command, 'Store per-barcode vcf files in a single zip file')
#
# #Zip all variants_*.xls files.
# zip_xls_command = 'echo "'
# zip_xls_command += ' '.join(('%s/%s/alleles_%s.xls' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name']))
# for barcode in barcode_data if barcode['status'] == 'completed')
# zip_xls_command += '" | xargs zip --junk-paths %s/%s.xls.zip' % (TSP_FILEPATH_PLUGIN_DIR,vc_options['run_name'])
# run_command(zip_xls_command, 'Store per-barcode xls files in a single zip file')
printtime(' ')
printtime('Task : ' + 'Store per-barcode vcf files in a single zip file')
zipfilename = '%s/%s.vcf.zip' % (TSP_FILEPATH_PLUGIN_DIR,vc_options['run_name'])
for myfile in [('%s/%s/TSVC_variants_%s.vcf.gz' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name'])) for barcode in barcode_data if barcode['status'] == 'completed']:
compress.make_zip(zipfilename, myfile, arcname=os.path.basename(myfile), use_sys_zip = False)
for myfile in [('%s/%s/TSVC_variants_%s.vcf.gz.tbi' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name'])) for barcode in barcode_data if barcode['status'] == 'completed']:
compress.make_zip(zipfilename, myfile, arcname=os.path.basename(myfile), use_sys_zip = False)
printtime(' ')
printtime(' ')
printtime('Task : ' + 'Store per-barcode xls files in a single zip file')
zipfilename = '%s/%s.xls.zip' % (TSP_FILEPATH_PLUGIN_DIR,vc_options['run_name'])
for myfile in [('%s/%s/alleles_%s.xls' % (TSP_FILEPATH_PLUGIN_DIR,barcode['name'],barcode['name'])) for barcode in barcode_data if barcode['status'] == 'completed']:
compress.make_zip(zipfilename, myfile, arcname=os.path.basename(myfile), use_sys_zip = False)
printtime(' ')
generate_barcode_links_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS), barcode_data, vc_options)
generate_barcode_links_block(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_BLOCK), barcode_data, vc_options)
if not all_barcodes_successful:
return 1
else: # Non-barcoded run
generate_incomplete_report_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS), 'Variant calling still in progress', vc_options, autorefresh=True)
fullpath_input_bam = os.path.join(ANALYSIS_DIR, 'rawlib.bam')
if is_bam_invalid(fullpath_input_bam):
generate_incomplete_report_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS), 'BAM file format validation failed. Regenerate BAM with latest TS.', vc_options)
return 1
try:
summary = call_variants(TSP_FILEPATH_PLUGIN_DIR,fullpath_input_bam,vc_options)
results_json['variants'] = summary.get('variants_total',{})
results_json['hotspots'] = summary.get('hotspots_total',{})
except:
traceback.print_exc()
generate_incomplete_report_page(os.path.join(TSP_FILEPATH_PLUGIN_DIR,HTML_RESULTS), 'An error occurred - check Log File for details', vc_options)
return 1
results_json['files'] = output_files
out = open(TSP_FILEPATH_PLUGIN_DIR + '/results.json','w')
json.dump(results_json,out,indent=4)
out.close()
printtime('')
printtime('Variant Caller Plugin complete')
printtime('')
return 0
if not os.path.exists(dst):
try:
os.symlink(src,dst)
except:
printtime("ERROR: Unable to symlink '%s' to '%s'" % (src, dst))
printtime(traceback.format_exc())
##################################################
# Create zip of files
##################################################
#sampled sff
#make_zip(libsff.replace(".sff",".sampled.sff")+'.zip', libsff.replace(".sff",".sampled.sff"))
#library sff
make_zip(libsff + '.zip', libsff, arcname=libsff )
#tf sff
make_zip(tfsff + '.zip', tfsff, arcname=tfsff)
#fastq zip
make_zip(fastqpath + '.zip', fastqpath, arcname=fastqpath)
#sampled fastq
#make_zip(fastqpath.replace(".fastq",".sampled.fastq")+'.zip', fastqpath.replace(".fastq",".sampled.fastq"))
########################################################
# barcode processing #
# Zip up and move sff, fastq, bam, bai files #
# Move zip files to results directory #
########################################################
start_time,
env['ALIGNMENT_RESULTS'],
bidirectional,
sam_parsed
)
try:
quality = os.path.join('.',"quality.summary")
shutil.copy(quality, "../"+status+".quality.summary")
except:
printtime("ERROR: %s doesn't exist" % quality)
pass
shutil.copy("alignTable.txt", "../"+status+".alignTable.txt")
shutil.copy("alignment.summary", "../"+status+".alignment.summary")
make_zip(sff_path+'.zip',sff_path,arcname=sff_path)
make_zip(fastq_path+'.zip',fastq_path,arcname=fastq_path)
os.chdir(top_dir)
# plugin framework expects the sff file in the env['BASECALLER_RESULTS'] subdirectory
union_sff = os.path.join(env['BASECALLER_RESULTS'],basename+".sff")
union_fastq = os.path.join(env['BASECALLER_RESULTS'],basename+".fastq")
# merge sff files
try:
com = "SFFMerge"
com += " -r"
com += " -o %s" % union_sff
for status in ["Paired_Fwd","Paired_Rev","Singleton_Fwd","Singleton_Rev","corrected"]:
sff = basename+"_"+status+".sff"
site_name,
flows,
notes,
barcodeId,
aligner_opts_extra,
start_time,
env['ALIGNMENT_RESULTS'],
bidirectional,
sam_parsed
)
shutil.copy("alignment.summary", "../"+status+".alignment.summary")
shutil.copy("quality.summary", "../"+status+".quality.summary")
shutil.copy("alignTable.txt", "../"+status+".alignTable.txt")
make_zip(sff_path+'.zip',sff_path)
make_zip(fastq_path+'.zip',fastq_path)
os.chdir(top_dir)
union_sff = basename+".sff"
union_fastq = basename+".fastq"
# merge sff files
try:
com = "SFFMerge"
com += " -r"
com += " -o %s" % union_sff
for status in ["Paired_Fwd","Paired_Rev","Singleton_Fwd","Singleton_Rev","corrected"]:
sff = basename+"_"+status+".sff"
if os.path.exists(sff):
def runForBarcodes():
global pluginParams, pluginResult, pluginReport
# read barcode ids
barcodes = []
try:
bcfileName = pluginParams['analysis_dir'] + '/barcodeList.txt'
with open(bcfileName) as bcfile:
for line in bcfile:
if line.startswith('barcode '):
barcodes.append(line.split(',')[1])
except:
printerr("Reading barcode list file '%s'" % bcfileName)
raise
numGoodBams = 0
numUnalBams = 0
minFileSize = pluginParams['cmdOptions'].minbamsize
(bcBamPath, bcBamRoot) = os.path.split(pluginParams['bamroot'])
validBarcodes = []
for barcode in barcodes:
# use unmapped BAM if there else mapped BAM (unmapped may not be present on Proton)
bcbam = os.path.join(bcBamPath, "%s_%s" % (barcode, bcBamRoot))
if not os.path.exists(bcbam):
bcbam = os.path.join(pluginParams['analysis_dir'],
"%s_rawlib.bam" % barcode)
numUnalBams += 1
if not os.path.exists(bcbam):
bcbam = ": BAM file not found"
numUnalBams -= 1
elif os.stat(bcbam).st_size < minFileSize:
bcbam = ": BAM file too small"
else:
numGoodBams += 1
validBarcodes.append(barcode)
printlog("Processing %d barcodes...\n" % numGoodBams)
if numUnalBams > 0:
printlog(
"Warning: %d barcodes will be processed using mapped BAM files. (Unmapped BAMs were not available.)\n"
% numUnalBams)
pluginReport['num_barcodes_processed'] = numGoodBams
pluginReport['num_barcodes_failed'] = 0
# iterate over all barcodes and process the valid ones
skip_analysis = pluginParams['cmdOptions'].skip_analysis
stop_on_error = pluginParams['cmdOptions'].stop_on_error
create_scraper = pluginParams['cmdOptions'].scraper
sample_names = pluginParams['sample_names']
postout = False
# just for logfile prettiness
sampleNamesFile = ("%s/sampleNames.txt" % pluginParams['results_dir'])
sampleNamesFW = open(sampleNamesFile, 'w')
for barcode in barcodes:
sample = sample_names[barcode] if barcode in sample_names else ''
sampleNamesFW.write("%s:%s\n" % (barcode, sample))
sampleNamesFW.close()
binDir = os.path.join(pluginParams['plugin_dir'], 'bin')
outDir = pluginParams['results_dir']
analysisDir = pluginParams['analysis_dir']
global hotspotsFile
hotspotsFile = pluginParams['hotspots_file']
global targetsFile
targetsFile = pluginParams['regions_file']
printlog("hotspots file is %s " % hotspotsFile)
pluginOutDir = os.path.join(analysisDir, 'plugin_out')
global variantCallerName
if not filter(
re.compile(r'variantCaller_out*').search,
os.listdir(pluginOutDir)):
printerr(
"Variant Caller plugin has to be run before launching the PGX Analysis plugin. Please run Torrent Variant Caller plugin"
)
return
variantCallerName = max(
filter(
re.compile(r'variantCaller_out*').search,
os.listdir(pluginOutDir)))
global coverageAnalysisName
if not filter(
re.compile(r'coverageAnalysis_out*').search,
os.listdir(pluginOutDir)):
printerr(
"Coverage Analysis plugin has to be run before launching the PGX Analysis plugin. Please run the Coverage Analysis plugin"
)
return
coverageAnalysisName = max(
filter(
re.compile(r'coverageAnalysis_out*').search,
os.listdir(pluginOutDir)))
printlog(variantCallerName)
printlog(coverageAnalysisName)
variantCallerDir = os.path.join(pluginOutDir, variantCallerName)
printlog("variantcaller dir is %s" % variantCallerDir)
coverageAnalysisDir = os.path.join(pluginOutDir, coverageAnalysisName)
hotspotsFileVC = ""
resultsJsonFile = os.path.join(variantCallerDir, "results.json")
if not os.path.isfile(resultsJsonFile):
printerr(
"VariantCaller results are not ready. Please wait for the variant Caller plugin to finish and then launch the PGx plugin"
)
return
covAnalysisResultsJsonFile = os.path.join(coverageAnalysisDir,
"results.json")
if not os.path.isfile(covAnalysisResultsJsonFile):
printerr(
"Coverage Analysis results are not ready. Please wait for the Coverage Analysis plugin to finish and then launch the PGx plugin"
)
return
targetsFileVC = ""
with open(resultsJsonFile) as fin:
for line in fin:
if "hotspots_bed" in line and ":" in line and "type" not in line:
kvp = line.split(":")
hotspotsFileVC = (os.path.basename(kvp[1].strip()))
if "," in hotspotsFileVC:
hotspotsFileVC = hotspotsFileVC[:-2]
else:
hotspotsFileVC = hotspotsFileVC[:-1]
hotspotsFileVC = os.path.join(variantCallerDir, hotspotsFileVC)
if "targets_bed" in line and ":" in line and "type" not in line:
kvp = line.split(":")
targetsFileVC = (os.path.basename(kvp[1].strip()))
if "," in targetsFileVC:
targetsFileVC = targetsFileVC[:-2]
else:
targetsFileVC = targetsFileVC[:-1]
targetsFileVC = os.path.join(variantCallerDir, targetsFileVC)
if not hotspotsFileVC:
printerr(
"Cannot obtain the hotspots file used by the VariantCaller. Trying to obtain the hotspots file from plan"
)
else:
hotspotsFile = hotspotsFileVC
if not hotspotsFile:
printerr("The plan is not set up with a hotspots file.")
return
if not targetsFileVC:
printerr(
"Cannot obtain the Target Regions file used by the VariantCaller. Trying to obtain the regions file from plan"
)
else:
targetsFile = targetsFileVC
cmd = ("java -jar %s/PGX_Analysis.jar %s %s %s %s %s %s %s %s" %
(binDir, hotspotsFile, outDir, bcfileName, analysisDir,
variantCallerDir, coverageAnalysisDir, binDir, sampleNamesFile))
printlog(cmd)
RunCommand(cmd)
# parse out data in results text file to dict AND coverts spaces to underscores in keys to avoid Django issues
statsfile = 'summary.txt'
analysisData = parseToDict(os.path.join(outDir, statsfile), "\t")
global numPass, numUniformity, numAvgCov, totalSamples
totalSamples = numGoodBams
numPass = numGoodBams
numAvgCov = 0
numUniformity = 0
for keys, values in analysisData.items():
printlog(keys)
printlog(values)
for file in os.listdir("%s/cnvCalls" % outDir):
if file.endswith(".log"):
cnvCallsDir = os.path.join(outDir, "cnvCalls")
filein = os.path.join(cnvCallsDir, file)
printlog("filein is %s " % filein)
with open(filein) as fin:
sep = "="
for line in fin:
if ("valid Samples =" in line):
kvp = line.split(sep)
totalSamples = kvp[1].strip()
elif ("CNV Calling =" in line):
kvp = line.split(sep)
numPass = kvp[1].strip()
elif ("Average coverage" in line):
kvp = line.split(sep)
numAvgCov = kvp[1].strip()
elif ("Uniformate Rate" in line):
kvp = line.split(sep)
numUniformity = kvp[1].strip()
zipfilename = "%s/cnvExports.zip" % outDir
cnvExportsDir = "%s/cnvExports" % outDir
for file in os.listdir(cnvExportsDir):
if file.endswith("_cn.txt"):
filein = os.path.join(cnvExportsDir, file)
compress.make_zip(zipfilename,
filein,
arcname=os.path.basename(filein),
use_sys_zip=False)
vcfZipFilename = "%s/%s.vcf.zip" % (outDir, pluginParams['prefix'])
mergedVcfsDir = "%s/merged_VCFs" % outDir
for file in os.listdir(mergedVcfsDir):
if file.endswith(".gz") or file.endswith(".tbi"):
filein = os.path.join(mergedVcfsDir, file)
compress.make_zip(vcfZipFilename,
filein,
arcname=os.path.basename(filein),
use_sys_zip=False)
global barcodeData
for barcode in validBarcodes:
barcode_entry = {}
sample = sample_names[barcode] if barcode in sample_names else ''
barcode_entry['name'] = barcode
if barcode in analysisData:
barcodeLine = analysisData[barcode]
kvp = barcodeLine.split("\t")
#key = kvp[0].strip()
if sample == '':
barcode_entry['sample'] = 'none'
else:
barcode_entry['sample'] = sample
if len(kvp) < 8 and kvp[2].strip() == 'null':
barcode_entry['hotspots_variants_total'] = "none"
barcode_entry['novel_variants_total'] = "none"
barcode_entry['exon9_cnv'] = kvp[3].strip()
barcode_entry['gene_cnv'] = kvp[4].strip()
barcode_entry['exon9_cnv_confidence'] = kvp[5].strip()
barcode_entry['gene_cnv_confidence'] = kvp[6].strip()
else:
barcode_entry['hotspots_variants_total'] = "%d/%s" % (
int(kvp[2].strip()) - int(kvp[4].strip()) -
int(kvp[5].strip()), kvp[2].strip())
barcode_entry['novel_variants_total'] = int(
kvp[3].strip()) - int(kvp[2].strip())
barcode_entry['exon9_cnv'] = kvp[6].strip()
barcode_entry['gene_cnv'] = kvp[7].strip()
barcode_entry['exon9_cnv_confidence'] = kvp[8].strip()
barcode_entry['gene_cnv_confidence'] = kvp[9].strip()
barcodeData.append(barcode_entry)
updateBarcodeSummaryReport()
if create_scraper:
createScraperLinksFolder(pluginParams['results_dir'],
pluginParams['prefix'])