def validateAndSanitizeOptions(self, options): StrelkaSharedWorkflowOptionsBase.validateAndSanitizeOptions( self, options) if options.excludedRegions is not None: for excludeIndex in range(len(options.excludedRegions)): options.excludedRegions[excludeIndex] = \ checkFixTabixIndexedFileOption(options.excludedRegions[excludeIndex],"excluded-regions bed") if options.knownVariants is not None: options.knownVariants = \ checkFixTabixIndexedFileOption(options.knownVariants,"known-variants vcf") groomBamList(options.bamList, "input") bamSetChecker = BamSetChecker() def singleAppender(bamList, label): if len(bamList) > 1: raise OptParseException( "More than one %s sample BAM/CRAM files specified" % (label)) bamSetChecker.appendBams(bamList, label) singleAppender(options.bamList, "Input") 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 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)) # check reference fasta file exists assertOptionExists(options.referenceFasta, "reference fasta file") options.referenceFasta = validateFixExistingFileArg( options.referenceFasta, "reference") # check for reference fasta index file: faiFile = options.referenceFasta + ".fai" if not os.path.isfile(faiFile): raise OptParseException( "Can't find expected fasta index file: '%s'" % (faiFile)) # check for bed file of call regions and its index file 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(r) for r in options.regionStrList ] # 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, options.regionStrList[genomeRegionIndex]))
def validateAndSanitizeOptions(self, options): StrelkaSharedWorkflowOptionsBase.validateAndSanitizeOptions( self, options) options.ploidyFilename = checkFixTabixIndexedFileOption( options.ploidyFilename, "ploidy file") options.noCompressBed = checkFixTabixIndexedFileOption( options.noCompressBed, "no-compress bed") if options.snvScoringModelFile is None: if options.isRNA: options.snvScoringModelFile = options.rnaSnvScoringModelFile else: options.snvScoringModelFile = options.germlineSnvScoringModelFile if options.indelScoringModelFile is None: if options.isRNA: options.indelScoringModelFile = options.rnaIndelScoringModelFile else: options.indelScoringModelFile = options.germlineIndelScoringModelFile # Disable dynamic error estimation for Exome if options.isExome: options.isEstimateSequenceError = False # Disable dynamic error estimation for RNA if options.isRNA: options.isEstimateSequenceError = False groomBamList(options.bamList, "input") def safeLen(x): if x is None: return 0 return len(x) if safeLen(options.bamList) == 0: raise OptParseException( "No input sample alignment files specified") bamSetChecker = BamSetChecker() bamSetChecker.appendBams(options.bamList, "Input") bamSetChecker.check(options.htsfileBin, options.referenceFasta)
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)) # check reference fasta file exists assertOptionExists(options.referenceFasta,"reference fasta file") options.referenceFasta=validateFixExistingFileArg(options.referenceFasta,"reference") # check for reference fasta index file: faiFile=options.referenceFasta + ".fai" if not os.path.isfile(faiFile) : raise OptParseException("Can't find expected fasta index file: '%s'" % (faiFile)) # check for bed file of call regions and its index file 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(r) for r in options.regionStrList] # 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, options.regionStrList[genomeRegionIndex]))
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")