def __init__(self, inputFnameLs=None, **keywords):
"""
2012.5.23
"""
AbstractMapper.__init__(self, inputFnameLs=inputFnameLs, **keywords)
self.chromosomeList = utils.getListOutOfStr(self.chromosomeList,
data_type=str,
separator2=None)
self.chromosomeSet = set(self.chromosomeList)
self.fileFormatDict = {1: 'fasta', 2: 'fastq'}
if not self.inputFileFormat: #0 or None or ''
#use 1: to exclude the '.' in suffix
self.inputFileFormat = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(
self.inputFname)[1][1:]
else:
self.inputFileFormat = self.fileFormatDict.get(
self.inputFileFormat)
if not self.outputFileFormat: #0 or None or ''
self.outputFileFormat = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(
self.outputFname)[1][1:]
else:
self.outputFileFormat = self.fileFormatDict.get(
self.outputFileFormat)
def __init__(self, **keywords): """ 2011-7-11 """ self.ad = ProcessOptions.process_function_arguments(keywords, self.option_default_dict, error_doc=self.__doc__, \ class_to_have_attr=self) if not self.outputFnamePrefix: self.outputFnamePrefix = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(self.inputFname)[0]
def getPEInputFiles(input_dir, isPE=True):
"""
2011-8-28
copied from MpiBWA.py
2011-8-5
add argument isPE, which flags whether input_dir contains PE or single-end reads
become a classmethod
2011-2-7
for paired-end files, sequence_628BWAAXX_1_1.fastq.gz and sequence_628BWAAXX_1_2.fastq.gz
are regarded as one pair of two files.
"""
sys.stderr.write("Pair input files from %s ..." % input_dir)
pairedEndPrefix2FileLs = {}
files = os.listdir(input_dir)
no_of_fastq_files = 0
for fname in files:
fname_prefix, fname_suffix = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(
fname)
if fname_suffix != '.fastq': #skip non-fastq files
continue
no_of_fastq_files += 1
if isPE == True:
pairedEndPrefix = fname_prefix[:-2]
pairedEndOrder = fname_prefix[-2:]
if pairedEndPrefix not in pairedEndPrefix2FileLs:
pairedEndPrefix2FileLs[pairedEndPrefix] = ['', '']
if pairedEndOrder == '_1': #the first file
pairedEndPrefix2FileLs[pairedEndPrefix][0] = fname
else:
pairedEndPrefix2FileLs[pairedEndPrefix][1] = fname
else:
pairedEndPrefix2FileLs[fname_prefix] = [fname] #single End
no_of_files = len(files)
no_of_pairedEndPrefix = len(pairedEndPrefix2FileLs)
if no_of_pairedEndPrefix > 0:
avg_no_of_files_per_prefix = no_of_fastq_files / float(
no_of_pairedEndPrefix)
else:
avg_no_of_files_per_prefix = 0.0
sys.stderr.write("%.2f files per one pairedEnd prefix. %s fastq files. %s total files. Done.\n"%\
(avg_no_of_files_per_prefix, no_of_fastq_files, no_of_files))
return pairedEndPrefix2FileLs
def selectIntervalFromInputFile(self, jobData=None, chromosome=None,\
intervalData=None, mapEachChromosomeData=None,\
passingData=None, transferOutput=False,\
**keywords):
"""
2013.11.24
"""
inputSuffix = utils.getRealPrefixSuffixOfFilenameWithVariableSuffix(
jobData.file.name)[1]
outputFile = File(os.path.join(self.mapDirJob.output, '%s_%s%s'%(passingData.fileBasenamePrefix, \
intervalData.overlapInterval, inputSuffix)))
tabixRetrieveJob = self.addTabixRetrieveJob(executable=self.tabixRetrieve, \
tabixPath=self.tabixPath, \
inputF=jobData.file, outputF=outputFile, \
regionOfInterest=intervalData.overlapInterval, includeHeader=True,\
parentJobLs=jobData.jobLs + [self.mapDirJob], job_max_memory=100, \
extraDependentInputLs=jobData.fileLs[1:], \
transferOutput=False)
return self.constructJobDataFromJob(job=tabixRetrieveJob)
