def test_bam(self):
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")
ds = AlignmentSet(bamFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 0)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P6-C4")
def test_bam (self):
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")
ds = AlignmentSet(bamFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 0)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P6-C4")
def test_cmph5(self):
base_dir = os.path.dirname(os.path.abspath(__file__))
dataDir = os.path.join(base_dir, 'data')
resourcesDir = os.path.join(base_dir, '../kineticsTools/resources')
refFile = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
ds = AlignmentSet(cmpFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 1)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P4-C2")
def test_cmph5 (self):
base_dir = os.path.dirname(os.path.abspath(__file__))
dataDir = os.path.join(base_dir,'data')
resourcesDir = os.path.join(base_dir, '../kineticsTools/resources')
refFile = os.path.join(dataDir, 'lambda', 'sequence', 'lambda.fasta')
cmpFile = os.path.join(dataDir, "p4-c2-lambda-mod-decode.cmp.h5")
ds = AlignmentSet(cmpFile, referenceFastaFname=refFile)
contigs = ReferenceUtils.loadReferenceContigs(refFile, ds)
self.assertEquals(len(contigs), 1)
self.assertEquals(contigs[0].cmph5ID, 1)
chemistry = ReferenceUtils.loadAlignmentChemistry(ds)
self.assertEquals(chemistry, "P4-C2")
def loadReferenceAndModel(self, referencePath):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the cmp.h5
logging.info("Loading reference contigs %s" % referencePath)
contigs = ReferenceUtils.loadReferenceContigs(referencePath,
alignmentSet=self.alignments, windows=self.referenceWindows)
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadAlignmentChemistry(self.alignments)
# Temporary solution for Sequel chemistries: we do not
# have trained kinetics models in hand yet for Sequel
# chemistries. However we have observed that the P5-C3
# training seems to yield fairly good results on Sequel
# chemistries to date. So for the moment, we will use
# that model for Sequel data.
if majorityChem.startswith("S/"):
logging.info("No trained model available yet for Sequel chemistries; modeling as P5-C3")
majorityChem = "P5-C3"
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.error("Chemistry cannot be identified---cannot perform kinetic analysis")
sys.exit(1)
elif not os.path.exists(ipdModel):
logging.error("Aborting, no kinetics model available for this chemistry: %s" % ipdModel)
sys.exit(1)
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def loadReferenceAndModel(self, referencePath):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the cmp.h5
logging.info("Loading reference contigs %s" % referencePath)
contigs = ReferenceUtils.loadReferenceContigs(referencePath,
alignmentSet=self.alignments, windows=self.referenceWindows)
# There are three different ways the ipdModel can be loaded.
# In order of precedence they are:
# 1. Explicit path passed to --ipdModel
# 2. Path to parameter bundle, model selected using the cmp.h5's sequencingChemistry tags
# 3. Fall back to built-in model.
# By default, use built-in model
ipdModel = None
if self.args.ipdModel:
ipdModel = self.args.ipdModel
logging.info("Using passed in ipd model: %s" % self.args.ipdModel)
if not os.path.exists(self.args.ipdModel):
logging.error("Couldn't find model file: %s" % self.args.ipdModel)
sys.exit(1)
elif self.args.paramsPath:
if not os.path.exists(self.args.paramsPath):
logging.error("Params path doesn't exist: %s" % self.args.paramsPath)
sys.exit(1)
majorityChem = ReferenceUtils.loadAlignmentChemistry(self.alignments)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.error("Chemistry cannot be identified---cannot perform kinetic analysis")
sys.exit(1)
elif not os.path.exists(ipdModel):
logging.error("Aborting, no kinetics model available for this chemistry: %s" % ipdModel)
sys.exit(1)
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
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
