def validateAndSanitizeExistingOptions(self, options):
options.runDir = os.path.abspath(options.runDir)
options.referenceFasta = validateFixExistingFileArg(
options.referenceFasta, "reference")
# check for reference fasta index file:
if options.referenceFasta is not None:
faiFile = options.referenceFasta + ".fai"
if not os.path.isfile(faiFile):
raise OptParseException(
"Can't find expected fasta index file: '%s'" % (faiFile))
checkFixTabixListOption(options.indelCandidatesList,
"candidate indel vcf")
checkFixTabixListOption(options.forcedGTList, "forced genotype vcf")
if (options.regionStrList is None) or (len(options.regionStrList)
== 0):
options.genomeRegionList = None
else:
options.genomeRegionList = [
parseGenomeRegion(rr) for r in options.regionStrList
for rr in r.split("+")
]
def validateAndSanitizeOptions(self,options) :
StrelkaSharedWorkflowOptionsBase.validateAndSanitizeOptions(self,options)
checkFixTabixListOption(options.noiseVcfList,"noise vcf")
groomBamList(options.normalBamList,"normal sample")
groomBamList(options.tumorBamList, "tumor sample")
def checkRequired(bamList,label):
if (bamList is None) or (len(bamList) == 0) :
raise OptParseException("No %s sample BAM/CRAM files specified" % (label))
checkRequired(options.tumorBamList,"tumor")
bamSetChecker = BamSetChecker()
def singleAppender(bamList,label):
if bamList is None : return
if len(bamList) > 1 :
raise OptParseException("More than one %s sample BAM/CRAM files specified" % (label))
bamSetChecker.appendBams(bamList,label)
singleAppender(options.normalBamList,"normal")
singleAppender(options.tumorBamList,"tumor")
bamSetChecker.check(options.htsfileBin,
options.referenceFasta)
def validateAndSanitizeOptions(self, options):
assertOptionExists(options.runDir, "run directory")
options.runDir = os.path.abspath(options.runDir)
assertOptionExists(options.referenceFasta, "reference fasta file")
options.referenceFasta = validateFixExistingFileArg(
options.referenceFasta, "reference fasta file")
# check for reference fasta index file:
referenceFastaIndex = options.referenceFasta + ".fai"
if not os.path.isfile(referenceFastaIndex):
raise OptParseException(
"Can't find expected fasta index file: '%s'" %
(referenceFastaIndex))
if options.isEstimateSequenceError:
# Determine if dynamic error estimation is feasible based on the reference size
# - Given reference contig set (S) with sequence length of at least 5 Mb
# - The total sequence length from S must be at least 50 Mb
class Constants:
Megabase = 1000000
minChromSize = options.errorEstimationMinChromMb * Megabase
minTotalSize = options.errorEstimationMinTotalMb * Megabase
# read fasta index
(_, chromSizes) = getFastaChromOrderSize(referenceFastaIndex)
totalEstimationSize = 0
for chromSize in chromSizes.values():
if chromSize < Constants.minChromSize: continue
totalEstimationSize += chromSize
if totalEstimationSize < Constants.minTotalSize:
sys.stderr.write(
"WARNING: Cannot estimate sequence errors from data due to small or overly fragmented reference sequence. Sequence error estimation disabled.\n"
)
options.isEstimateSequenceError = False
checkFixTabixListOption(options.indelCandidatesList,
"candidate indel vcf")
checkFixTabixListOption(options.forcedGTList, "forced genotype vcf")
options.callRegionsBed = checkFixTabixIndexedFileOption(
options.callRegionsBed, "call-regions bed")
if (options.regionStrList is None) or (len(options.regionStrList)
== 0):
options.genomeRegionList = None
else:
options.genomeRegionList = [
parseGenomeRegion(rr) for r in options.regionStrList
for rr in r.split("+")
]
options.snvScoringModelFile = validateFixExistingFileArg(
options.snvScoringModelFile, "SNV empirical scoring model file")
options.indelScoringModelFile = validateFixExistingFileArg(
options.indelScoringModelFile,
"Indel empirical scoring model file")
def validateAndSanitizeExistingOptions(self, options):
StrelkaSharedWorkflowOptionsBase.validateAndSanitizeExistingOptions(
self, options)
groomBamList(options.normalBamList, "normal sample")
groomBamList(options.tumorBamList, "tumor sample")
checkFixTabixListOption(options.noiseVcfList, "noise vcf")
options.somaticSnvScoringModelFile = validateFixExistingFileArg(
options.somaticSnvScoringModelFile,
"Somatic SNV empirical scoring file")
options.somaticIndelScoringModelFile = validateFixExistingFileArg(
options.somaticIndelScoringModelFile,
"Somatic indel empirical scoring file")
def validateAndSanitizeOptions(self, options):
assertOptionExists(options.runDir, "run directory")
options.runDir = os.path.abspath(options.runDir)
workflowScriptPath = os.path.join(options.runDir,
options.workflowScriptName)
if os.path.exists(workflowScriptPath):
raise OptParseException(
"Run directory already contains workflow script file '%s'. Each analysis must be configured in a separate directory."
% (workflowScriptPath))
assertOptionExists(options.referenceFasta, "reference fasta file")
options.referenceFasta = validateFixExistingFileArg(
options.referenceFasta, "reference fasta file")
# check for reference fasta index file:
referenceFastaIndex = options.referenceFasta + ".fai"
if not os.path.isfile(referenceFastaIndex):
raise OptParseException(
"Can't find expected fasta index file: '%s'" %
(referenceFastaIndex))
if options.isEstimateSequenceError:
# Determine if dynamic error estimation is feasible based on the reference size
# - Given reference contig set (S) with sequence length of at least 5 Mb
# - The total sequence length from S must be at least 50 Mb
class Constants:
Megabase = 1000000
minChromSize = options.errorEstimationMinChromMb * Megabase
minTotalSize = options.errorEstimationMinTotalMb * Megabase
# read fasta index
(_, chromSizes) = getFastaChromOrderSize(referenceFastaIndex)
totalEstimationSize = 0
for chromSize in chromSizes.values():
if chromSize < Constants.minChromSize: continue
totalEstimationSize += chromSize
if totalEstimationSize < Constants.minTotalSize:
sys.stderr.write(
"WARNING: Cannot estimate sequence errors from data due to small or overly fragmented reference sequence. Sequence error estimation disabled.\n"
)
options.isEstimateSequenceError = False
checkFixTabixListOption(options.indelCandidatesList,
"candidate indel vcf")
checkFixTabixListOption(options.forcedGTList, "forced genotype vcf")
options.callRegionsBed = checkFixTabixIndexedFileOption(
options.callRegionsBed, "call-regions bed")
def extendedRegionStrList():
"""
A generator on the regionStrList which parses the (intentionally undocumented/possibly deprecated) '+' entry format
to specify multiple regions in a single argument.
"""
for r in options.regionStrList:
for rr in r.split("+"):
yield rr
if (options.regionStrList is None) or (len(options.regionStrList)
== 0):
options.genomeRegionList = None
else:
options.genomeRegionList = [
parseGenomeRegion(r) for r in extendedRegionStrList()
]
# validate chromosome names appearing in region tags and callRegions bed file
if (options.callRegionsBed is not None) or (options.genomeRegionList
is not None):
refChromInfo = getFastaInfo(options.referenceFasta)
if options.callRegionsBed is not None:
for chrom in getTabixChromSet(options.tabixBin,
options.callRegionsBed):
if chrom not in refChromInfo:
raise OptParseException(
"Chromosome label '%s', in call regions bed file '%s', not found in reference genome."
% (chrom, options.callRegionsBed))
if options.genomeRegionList is not None:
for (genomeRegionIndex,
genomeRegion) in enumerate(options.genomeRegionList):
chrom = genomeRegion["chrom"]
if chrom not in refChromInfo:
raise OptParseException(
"Chromosome label '%s', parsed from region argument '%s', not found in reference genome."
% (chrom, list(
extendedRegionStrList())[genomeRegionIndex]))
options.snvScoringModelFile = validateFixExistingFileArg(
options.snvScoringModelFile, "SNV empirical scoring model file")
options.indelScoringModelFile = validateFixExistingFileArg(
options.indelScoringModelFile,
"Indel empirical scoring model file")