Пример #1
0
 def test_parseReferenceWindow(self):
     window = "gi|12057207|gb|AE001439.1|:1-5000"
     bamFile = os.path.join(big_data_dir, "Hpyl_1_5000.bam")
     refFile = os.path.join(ref_dir, "Helicobacter_pylori_J99", "sequence",
                            "Helicobacter_pylori_J99.fasta")
     alnFile = AlignmentSet(bamFile, referenceFastaFname=refFile)
     win = ReferenceUtils.parseReferenceWindow(window,
                                               alnFile.referenceInfo)
     self.assertEquals([win.refId, win.start, win.end], [0, 1, 5000])
 def test_parseReferenceWindow (self):
     window = "gi|12057207|gb|AE001439.1|:1-5000"
     bamFile = os.path.join(big_data_dir, "Hpyl_1_5000.bam")
     refFile = os.path.join(ref_dir, "Helicobacter_pylori_J99", "sequence",
         "Helicobacter_pylori_J99.fasta")
     alnFile = AlignmentSet(bamFile, referenceFastaFname=refFile)
     win = ReferenceUtils.parseReferenceWindow(window,
         alnFile.referenceInfo)
     self.assertEquals([win.refId, win.start, win.end], [0, 1, 5000])
Пример #3
0
    def _mainLoop(self):
        """
        Main loop
        First launch the worker and writer processes
        Then we loop over ReferenceGroups in the cmp.h5.  For each contig we will:
        1. Load the sequence into the main memory of the parent process
        3. Chunk up the contig and submit the chunk descriptions to the work queue
        Finally, wait for the writer process to finish.
        """

        # This looks scary but it's not.  Python uses reference
        # counting and has a secondary, optional garbage collector for
        # collecting garbage cycles.  Unfortunately when a cyclic GC
        # happens when a thread is calling cPickle.dumps, the
        # interpreter crashes sometimes.  See Bug 19704.  Since we
        # don't leak garbage cycles, disabling the cyclic GC is
        # essentially harmless.
        #gc.disable()

        self.loadSharedAlignmentSet(self.args.alignment_set)

        # Resolve the windows that will be visited.
        if self.args.referenceWindowsAsString is not None:
            self.referenceWindows = []
            for s in self.args.referenceWindowsAsString.split(","):
                try:
                    win = ReferenceUtils.parseReferenceWindow(s, self.alignments.referenceInfo)
                    self.referenceWindows.append(win)
                except:
                    if self.args.skipUnrecognizedContigs:
                        continue
                    else:
                        raise Exception, "Unrecognized contig!"
        elif self.args.referenceWindowsFromAlignment:
            self.referenceWindows = ReferenceUtils.referenceWindowsFromAlignment(self.alignments, self.alignments.referenceInfo)
            refNames = set([rw.refName for rw in self.referenceWindows])
            # limit output to contigs that overlap with reference windows
            self.refInfo = [r for r in self.refInfo if r.Name in refNames]
        else:
            self.referenceWindows = ReferenceUtils.createReferenceWindows(
                self.refInfo)

        # Load reference and IpdModel
        self.loadReferenceAndModel(self.args.reference)

        # Spawn workers
        self._launchSlaveProcesses()

        logging.info('Generating kinetics summary for [%s]' % self.args.alignment_set)

        #self.referenceMap = self.alignments['/RefGroup'].asDict('RefInfoID', 'ID')
        #self.alnInfo = self.alignments['/AlnInfo'].asRecArray()

        # Main loop -- we loop over ReferenceGroups in the cmp.h5.  For each contig we will:
        # 1. Load the sequence into the main memory of the parent process
        # 2. Fork the workers
        # 3. chunk up the contig and

        self.workChunkCounter = 0

        # Iterate over references
        for window in self.referenceWindows:
            logging.info('Processing window/contig: %s' % (window,))
            for chunk in ReferenceUtils.enumerateChunks(self.args.referenceStride, window):
                self._workQueue.put((self.workChunkCounter, chunk))
                self.workChunkCounter += 1

        # Shutdown worker threads with None sentinels
        for i in xrange(self.args.numWorkers):
            self._workQueue.put(None)

        for w in self._workers:
            w.join()

        # Join on the result queue and the resultsCollector process.
        # This ensures all the results are written before shutdown.
        self.monitoringThread.join()
        self._resultsQueue.join()
        self._resultCollectorProcess.join()
        logging.info("ipdSummary.py finished. Exiting.")
        self.alignments.close()
        return 0
Пример #4
0
    def _mainLoop(self):
        """
        Main loop
        First launch the worker and writer processes
        Then we loop over ReferenceGroups in the cmp.h5.  For each contig we will:
        1. Load the sequence into the main memory of the parent process
        3. Chunk up the contig and submit the chunk descriptions to the work queue
        Finally, wait for the writer process to finish.
        """

        # This looks scary but it's not.  Python uses reference
        # counting and has a secondary, optional garbage collector for
        # collecting garbage cycles.  Unfortunately when a cyclic GC
        # happens when a thread is calling cPickle.dumps, the
        # interpreter crashes sometimes.  See Bug 19704.  Since we
        # don't leak garbage cycles, disabling the cyclic GC is
        # essentially harmless.
        #gc.disable()

        self.loadSharedAlignmentSet(self.args.alignment_set)

        # Resolve the windows that will be visited.
        if self.args.referenceWindowsAsString is not None:
            self.referenceWindows = []
            for s in self.args.referenceWindowsAsString.split(","):
                try:
                    win = ReferenceUtils.parseReferenceWindow(
                        s, self.alignments.referenceInfo)
                    self.referenceWindows.append(win)
                except:
                    if self.args.skipUnrecognizedContigs:
                        continue
                    else:
                        raise Exception("Unrecognized contig!")
        elif self.args.referenceWindowsFromAlignment:
            self.referenceWindows = ReferenceUtils.referenceWindowsFromAlignment(
                self.alignments, self.alignments.referenceInfo)
            refNames = set([rw.refName for rw in self.referenceWindows])
            # limit output to contigs that overlap with reference windows
            self.refInfo = [r for r in self.refInfo if r.Name in refNames]
        else:
            self.referenceWindows = ReferenceUtils.createReferenceWindows(
                self.refInfo)

        # Load reference and IpdModel
        ipdModelFilename = basic.getIpdModelFilename(
            self.args.ipdModel,
            ReferenceUtils.loadAlignmentChemistry(self.alignments),
            self.args.paramsPath)
        self.loadReferenceAndModel(self.args.reference, ipdModelFilename)

        # Spawn workers
        self._launchSlaveProcesses()

        logging.info('Generating kinetics summary for [%s]' %
                     self.args.alignment_set)

        #self.referenceMap = self.alignments['/RefGroup'].asDict('RefInfoID', 'ID')
        #self.alnInfo = self.alignments['/AlnInfo'].asRecArray()

        # Main loop -- we loop over ReferenceGroups in the cmp.h5.  For each contig we will:
        # 1. Load the sequence into the main memory of the parent process
        # 2. Fork the workers
        # 3. chunk up the contig and

        self.workChunkCounter = 0

        # Iterate over references
        for window in self.referenceWindows:
            logging.info('Processing window/contig: %s' % (window, ))
            for chunk in ReferenceUtils.enumerateChunks(
                    self.args.referenceStride, window):
                self._workQueue.put((self.workChunkCounter, chunk))
                self.workChunkCounter += 1

        # Shutdown worker threads with None sentinels
        for i in xrange(self.args.numWorkers):
            self._workQueue.put(None)

        for w in self._workers:
            w.join()

        # Join on the result queue and the resultsCollector process.
        # This ensures all the results are written before shutdown.
        self.monitoringThread.join()
        self._resultsQueue.join()
        self._resultCollectorProcess.join()
        logging.info("ipdSummary.py finished. Exiting.")
        self.alignments.close()
        return 0