class KineticsToolsRunner(object):
def __init__(self, args):
self.args = args
self.alignments = None
def start(self):
self.validateArgs()
return self.run()
def getVersion(self):
return __version__
def validateArgs(self):
parser = get_parser()
if not os.path.exists(self.args.alignment_set):
parser.error('Input AlignmentSet file provided does not exist')
if self.args.identify and self.args.control:
parser.error('--control and --identify are mutally exclusive. Please choose one or the other')
if self.args.useLDA:
if self.args.m5Cclassifier is None:
parser.error('Please specify a folder containing forward.csv and reverse.csv classifiers in --m5Cclassifier.')
if self.args.m5Cgff:
if not self.args.useLDA:
parser.error('m5Cgff file can only be generated in --useLDA mode.')
# if self.args.methylFraction and not self.args.identify:
# parser.error('Currently, --methylFraction only works when the --identify option is specified.')
def run(self):
# Figure out what modifications to identify
mods = self.args.identify
modsToCall = []
if mods:
items = mods.split(",")
if 'm6A' in items:
modsToCall.append('H')
if 'm4C' in items:
modsToCall.append('J')
if 'm5C_TET' in items:
modsToCall.append('K')
self.args.identify = True
self.args.modsToCall = modsToCall
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# set random seed
# XXX note that this is *not* guaranteed to yield reproducible results
# indepenently of the number of processing cores used!
if self.options.randomSeed is not None:
np.random.seed(self.options.randomSeed)
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()",
globals=globals(),
locals=locals(),
filename="profile.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on the main thread
if not self.args.threaded:
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
if self.options.threaded:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = Queue.Queue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
else:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus,))
logging.info("Requested worker processes: %d" % (self.options.numWorkers,))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn("More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance."
% (self.options.numWorkers, availableCpus))
self._initQueues()
if self.options.threaded:
self.options.numWorkers = 1
WorkerType = KineticWorkerThread
else:
WorkerType = KineticWorkerProcess
# Launch the worker processes
self._workers = []
for i in xrange(self.options.numWorkers):
p = WorkerType(self.options, self._workQueue, self._resultsQueue,
self.ipdModel,
sharedAlignmentSet=self.alignments)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options, self._resultsQueue, self.refInfo, self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(target=monitorChildProcesses, args=(self._workers + [self._resultCollectorProcess],))
self.monitoringThread.start()
def _queueChunksForWindow(self, refWindow):
"""
Compute the chunk extents and queue up the work for a single reference
"""
winId = refWindow.refId
winStart = refWindow.start
winEnd = refWindow.end
pass
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 loadSharedAlignmentSet(self, cmpH5Filename):
"""
Read the input AlignmentSet so the indices can be shared with the
slaves. This is also used to pass to ReferenceUtils for setting up
the ipdModel object.
"""
logging.info("Reading AlignmentSet: %s" % cmpH5Filename)
logging.info(" reference: %s" % self.args.reference)
self.alignments = AlignmentSet(cmpH5Filename,
referenceFastaFname=self.args.reference)
# XXX this should ensure that the file(s) get opened, including any
# .pbi indices - but need to confirm this
self.refInfo = self.alignments.referenceInfoTable
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
class KineticsToolsRunner(object):
def __init__(self, args):
self.args = args
self.alignments = None
def start(self):
self.validateArgs()
return self.run()
def getVersion(self):
return __version__
def validateArgs(self):
parser = get_parser()
if not os.path.exists(self.args.alignment_set):
parser.error('Input AlignmentSet file provided does not exist')
# Over-ride --identify if --control was specified
if self.args.control:
self.args.identify = ""
if self.args.useLDA:
if self.args.m5Cclassifier is None:
parser.error(
'Please specify a folder containing forward.csv and reverse.csv classifiers in --m5Cclassifier.'
)
if self.args.m5Cgff:
if not self.args.useLDA:
parser.error(
'm5Cgff file can only be generated in --useLDA mode.')
# if self.args.methylFraction and not self.args.identify:
# parser.error('Currently, --methylFraction only works when the --identify option is specified.')
def run(self):
# Figure out what modifications to identify
mods = self.args.identify
modsToCall = []
if mods:
items = mods.split(",")
if 'm6A' in items:
modsToCall.append('H')
if 'm4C' in items:
modsToCall.append('J')
if 'm5C_TET' in items:
modsToCall.append('K')
self.args.identify = True
self.args.modsToCall = modsToCall
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# set random seed
# XXX note that this is *not* guaranteed to yield reproducible results
# indepenently of the number of processing cores used!
if self.options.randomSeed is not None:
np.random.seed(self.options.randomSeed)
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()",
globals=globals(),
locals=locals(),
filename="profile.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on
# the main thread
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in
# self._workers
self._workQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus, ))
logging.info("Requested worker processes: %d" %
(self.options.numWorkers, ))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn(
"More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance." %
(self.options.numWorkers, availableCpus))
self._initQueues()
# Launch the worker processes
self._workers = []
for i in range(self.options.numWorkers):
p = KineticWorkerProcess(self.options,
self._workQueue,
self._resultsQueue,
self.ipdModel,
sharedAlignmentSet=self.alignments)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options,
self._resultsQueue,
self.refInfo,
self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(
target=monitorChildProcesses,
args=(self._workers + [self._resultCollectorProcess], ))
self.monitoringThread.start()
def _queueChunksForWindow(self, refWindow):
"""
Compute the chunk extents and queue up the work for a single reference
"""
winId = refWindow.refId
winStart = refWindow.start
winEnd = refWindow.end
pass
def loadReferenceAndModel(self, referencePath, ipdModelFilename):
assert self.alignments is not None and self.referenceWindows is not None
# Load the reference contigs - annotated with their refID from the
# alignments
logging.info("Loading reference contigs {!r}".format(referencePath))
contigs = ReferenceUtils.loadReferenceContigs(
referencePath,
alignmentSet=self.alignments,
windows=self.referenceWindows)
self.ipdModel = IpdModel(contigs, ipdModelFilename,
self.args.modelIters)
def loadSharedAlignmentSet(self, alignmentFilename):
"""
Read the input AlignmentSet so the indices can be shared with the
slaves. This is also used to pass to ReferenceUtils for setting up
the ipdModel object.
"""
logging.info("Reading AlignmentSet: %s" % alignmentFilename)
logging.info(" reference: %s" % self.args.reference)
self.alignments = AlignmentSet(alignmentFilename,
referenceFastaFname=self.args.reference)
# XXX this should ensure that the file(s) get opened, including any
# .pbi indices - but need to confirm this
self.refInfo = self.alignments.referenceInfoTable
def _mainLoop(self):
"""
Main loop
First launch the worker and writer processes
Then we loop over ReferenceGroups in the alignments. 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 BaseException:
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
chemName = ReferenceUtils.loadAlignmentChemistry(self.alignments)
if self.args.useChemistry is not None:
chemName = self.args.useChemistry
ipdModelFilename = loader.getIpdModelFilename(
ipdModel=self.args.ipdModel,
majorityChem=chemName,
paramsPath=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 alignments. 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 range(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
class ReprocessMotifSites(PBToolRunner):
def __init__(self):
desc = [
'For all sites in motifs.gff, reports estimated methylated fraction and 95% confidence interval',
'Notes: For all command-line arguments, default values are listed in [].'
]
super(ReprocessMotifSites, self).__init__('\n'.join(desc))
self.parser.add_argument(
'--numWorkers',
dest='numWorkers',
default=-1, # Defaults to using all logical CPUs
type=int,
help='Number of thread to use (-1 uses all logical cpus)')
self.parser.add_argument('infile',
metavar='input.cmp.h5',
help='Input cmp.h5 filename')
# self.parser.add_argument('--control',
# dest='control',
# default=None,
# help='cmph.h5 file ')
# self.parser.add_argument('--outfile',
# dest='outfile',
# default=None,
# help='Use this option to generate all possible output files. Argument here is the root filename of the output files.')
self.parser.add_argument('--gff',
dest='gff',
default=None,
help='Name of output GFF file [%(default)s]')
# self.parser.add_argument('--identify',
# dest='identify',
# default=False,
# help='Identify modification types. Comma-separated list of know modification types. Current options are: m6A, m4C, m5C_TET. Cannot be used with --control')
# self.parser.add_argument('--csv',
# dest='csv',
# default=None,
# help='Name of output CSV file [%(default)s]')
# self.parser.add_argument('--pickle',
# dest='pickle',
# default=None,
# help='Name of output pickle file [%(default)s]')
# self.parser.add_argument('--summary_h5',
# dest='summary_h5',
# default=None,
# help='Name of output summary h5 file [%(default)s]')
self.parser.add_argument('--reference',
dest='reference',
required=True,
help='Path to reference FASTA file')
self.parser.add_argument(
"--maxLength",
default=3e12,
type=int,
help="Maximum number of bases to process per contig")
self.parser.add_argument(
'--minCoverage',
dest='minCoverage',
default=3,
type=int,
help='Minimum coverage required to call a modified base')
self.parser.add_argument('--maxQueueSize',
dest='maxQueueSize',
default=1000,
type=int,
help='Max Queue Size')
self.parser.add_argument('--maxCoverage',
dest='maxCoverage',
type=int,
default=None,
help='Maximum coverage to use at each site')
self.parser.add_argument('--mapQvThreshold',
dest='mapQvThreshold',
type=float,
default=-1.0)
# self.parser.add_argument('--pvalue',
# dest='pvalue',
# default=0.01,
# type=float,
# help='p-value required to call a modified base')
self.parser.add_argument('--subread_norm',
dest='subread_norm',
default=True,
type=lambda x: x != 'False',
help='Normalized subread ipds')
self.parser.add_argument(
'--ipdModel',
dest='ipdModel',
default=None,
help='Alternate synthetic IPD model HDF5 file')
self.parser.add_argument('--cap_percentile',
dest='cap_percentile',
type=float,
default=99.0,
help='Global IPD percentile to cap IPDs at')
self.parser.add_argument(
"--threaded",
"-T",
action="store_true",
dest="threaded",
default=False,
help=
"Run threads instead of processes (for debugging purposes only)")
self.parser.add_argument(
"--profile",
action="store_true",
dest="doProfiling",
default=False,
help="Enable Python-level profiling (using cProfile).")
# self.parser.add_argument("--methylFraction",
# action="store_true",
# dest="methylFraction",
# default=False,
# help="In the --identify mode, add --methylFraction to command line to estimate the methylated fraction, along with 95% confidence interval bounds.")
# The following are in addition to ipdSummary.py's inputs:
self.parser.add_argument('--motifs',
dest="motifs",
required=True,
help='Name of motifs GFF file [%(default)s]')
self.parser.add_argument('--motif_summary',
dest="motif_summary",
required=True,
help='Name of motif summary CSV file')
self.parser.add_argument(
'--undetected',
action="store_true",
dest="undetected",
default=False,
help=
"Setting this flag yields output with only undetected motif sites."
)
self.parser.add_argument(
'--modifications',
dest="modifications",
default=None,
help='Name of modifications GFF file [%(default)s]')
self.parser.add_argument(
'--oldData',
action="store_true",
dest="oldData",
default=False,
help=
"For datasets prior to 1.3.3 (use this option to increase testing possibilities)"
)
# A new addition to ipdSummary.py
self.parser.add_argument(
'--paramsPath',
dest='paramsPath',
default=None,
help=
'Directory containing in-silico trained model for each chemistry')
self.parser.add_argument(
'--modelIters',
dest='modelIters',
type=int,
default=-1,
help='[Internal] Number of GBM model iteration to use')
def getVersion(self):
return __version__
def validateArgs(self):
if not os.path.exists(self.args.infile):
self.parser.error('input.cmp.h5 file provided does not exist')
# Add checks corresponding to new required inputs:
if not os.path.exists(self.args.motifs):
self.parser.error('input motifs gff file provided does not exist')
if not os.path.exists(self.args.motif_summary):
self.parser.error(
'input motif_summary csv file provided does not exist')
if not self.args.undetected and not os.path.exists(
self.args.modifications):
self.parser.error(
'either the --undetected flag must be set, or a valid modifications.gff must be provided'
)
def run(self):
# The following arguments are set in order to use ResultWriter.py as is:
self.args.methylFraction = True
self.args.outfile = None
self.args.csv = None
self.args.control = None
self.args.summary_h5 = None
self.args.pickle = None
self.args.identify = False
self.args.pvalue = 1.0
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# Log generously
logFormat = '%(asctime)s [%(levelname)s] %(message)s'
logging.basicConfig(level=logging.INFO, format=logFormat)
stdOutHandler = logging.StreamHandler(sys.stdout)
# logging.Logger.root.addHandler(stdOutHandler)
# logging.info("t1")
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()",
globals=globals(),
locals=locals(),
filename="profile-main4.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on the main thread
if not self.args.threaded:
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
if self.options.threaded:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = Queue.Queue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
else:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus, ))
logging.info("Requested worker processes: %d" %
(self.options.numWorkers, ))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn(
"More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance." %
(self.options.numWorkers, availableCpus))
self._initQueues()
if self.options.threaded:
self.options.numWorkers = 1
WorkerType = KineticWorkerThread
else:
WorkerType = KineticWorkerProcess
# Launch the worker processes
self._workers = []
for i in xrange(self.options.numWorkers):
p = WorkerType(self.options, self._workQueue, self._resultsQueue,
self.ipdModel)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options,
self._resultsQueue,
self.refInfo,
self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(
target=monitorChildProcesses,
args=(self._workers + [self._resultCollectorProcess], ))
self.monitoringThread.start()
def _queueChunksForReference(self):
# Read in motif_summary.csv
motifInfo = {}
reader = csv.reader(open(self.args.motif_summary, 'r'), delimiter=',')
reader.next()
if self.options.oldData:
col = 1
else:
col = 2
for row in reader:
motifInfo[row[0]] = row[col]
# Figure out the length of the motifs file:
motReader = GffReader(self.args.motifs)
if self.options.undetected:
motifDicts = [{
"seqID": x.seqid,
"type": x.type,
"score": x.score,
"pos": x.start,
"strand": x.strand,
"attributes": x.attributes
} for x in motReader if x.type == '.']
else:
motifDicts = [{
"seqID": x.seqid,
"type": x.type,
"score": x.score,
"pos": x.start,
"strand": x.strand,
"attributes": x.attributes
} for x in motReader]
refLength = len(motifDicts)
# Maximum number of hits per chunk
MAX_HITS = 500
nBases = min(refLength, self.args.maxLength)
nBlocks = max(self.options.numWorkers * 4, nBases / MAX_HITS)
# Block layout
blockSize = min(nBases, max(nBases / nBlocks + 1, 100))
blockStarts = np.arange(0, nBases, step=blockSize)
blockEnds = blockStarts + blockSize
blocks = zip(blockStarts, blockEnds)
if self.options.undetected:
self.options.modifications = None
# Queue up work blocks
for block in blocks:
# NOTE! The format of a work chunk is (refId <int>, refStartBase <int>, refEndBase <int>)
# chunk = (refInfoId, block[0], block[1])
# chunk = (self.options.motifs, self.refInfo, motifInfo, self.options.modifications, self.options.undetected, self.options.oldData, block[0], block[1])
chunk = (motifDicts[block[0]:block[1]], self.refInfo, motifInfo,
self.options.modifications, self.options.undetected,
self.options.oldData, block[0], block[1])
self._workQueue.put((self.workChunkCounter, chunk))
self.workChunkCounter += 1
def loadReference(self):
# FIXME - support a bare fasta file as well?
self.referenceEntry = ReferenceEntry(self.args.reference)
self.refInfo = self.referenceEntry.contigs
if self.args.ipdModel:
self.lutPath = self.args.ipdModel
if not os.path.exists(self.lutPath):
logging.info("Couldn't find model file: %s" % self.lutPath)
raise Exception("Couldn't find model file: %s" % self.lutPath)
else:
self.lutPath = None
self.ipdModel = IpdModel(self.referenceEntry, self.lutPath)
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
self.refInfo = refInfoTable
# 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 chemistry info
# 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)
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.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.warning(
"Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
else:
logging.info("Using Chemistry matched IPD model: %s" %
ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def _mainLoop(self):
# See comments in ipdSummary.py
gc.disable()
# Load reference and IpdModel
# self.loadReference()
# Load reference and IpdModel
self.loadReferenceAndModel(self.args.reference, self.args.infile)
# Spawn workers
self._launchSlaveProcesses()
# cmp.h5 we're using -- use this to orchestrate the work
self.cmph5 = CmpH5Reader(self.args.infile)
logging.info('Generating kinetics summary for [%s]' % self.args.infile)
self.workChunkCounter = 0
self._queueChunksForReference()
# 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("reprocessMotifSites.py finished. Exiting.")
del self.cmph5
return 0
class KineticsToolsRunner(object):
def __init__(self):
desc = [
'Tool for detecting DNA base-modifications from kinetic signatures',
'Notes: For all command-line arguments, default values are listed in [].'
]
description = '\n'.join(desc)
self.parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=description)
# Positional arguments:
self.parser.add_argument('infile',
metavar='input.cmp.h5',
type=validateFile,
help='Input cmp.h5 filename')
# Optional arguments:
# Output options:
# Note: reference is actually not optional:
self.parser.add_argument('--reference',
type=validateFile,
help='Path to reference FASTA file')
self.parser.add_argument(
'--outfile',
dest='outfile',
default=None,
help=
'Use this option to generate all possible output files. Argument here is the root filename of the output files.'
)
self.parser.add_argument('--gff',
dest='gff',
default=None,
help='Name of output GFF file')
# FIXME: Need to add an extra check for this; it can only be used if --useLDA flag is set.
self.parser.add_argument(
'--m5Cgff',
dest='m5Cgff',
default=None,
help='Name of output GFF file containing m5C scores')
# FIXME: Make sure that this is specified if --useLDA flag is set.
self.parser.add_argument(
'--m5Cclassifer',
dest='m5Cclassifier',
default=None,
help='Specify csv file containing a 127 x 2 matrix')
self.parser.add_argument('--csv',
dest='csv',
default=None,
help='Name of output CSV file.')
self.parser.add_argument(
'--csv_h5',
dest='csv_h5',
default=None,
help='Name of csv output to be written in hdf5 format.')
self.parser.add_argument('--pickle',
dest='pickle',
default=None,
help='Name of output pickle file.')
self.parser.add_argument('--summary_h5',
dest='summary_h5',
default=None,
help='Name of output summary h5 file.')
self.parser.add_argument('--ms_csv',
dest='ms_csv',
default=None,
help='Multisite detection CSV file.')
# Calculation options:
self.parser.add_argument(
'--control',
dest='control',
default=None,
type=validateNoneOrFile,
help=
'cmph.h5 file containing a control sample. Tool will perform a case-control analysis'
)
self.parser.add_argument(
'--identify',
dest='identify',
default=False,
help=
'Identify modification types. Comma-separated list of know modification types. Current options are: m6A, m4C, m5C_TET. Cannot be used with --control'
)
self.parser.add_argument(
"--methylFraction",
action="store_true",
dest="methylFraction",
default=False,
help=
"In the --identify mode, add --methylFraction to command line to estimate the methylated fraction, along with 95%% confidence interval bounds."
)
# Temporary addition to test LDA for Ca5C detection:
self.parser.add_argument(
'--useLDA',
action="store_true",
dest='useLDA',
default=False,
help='Set this flag to debug LDA for m5C/Ca5C detection')
# Parameter options:
self.parser.add_argument(
'--paramsPath',
dest='paramsPath',
default=_getResourcePath(),
type=validateNoneOrDir,
help=
'Directory containing in-silico trained model for each chemistry')
self.parser.add_argument(
"--maxLength",
default=3e12,
type=int,
help="Maximum number of bases to process per contig")
self.parser.add_argument(
'--minCoverage',
dest='minCoverage',
default=3,
type=int,
help='Minimum coverage required to call a modified base')
self.parser.add_argument('--maxQueueSize',
dest='maxQueueSize',
default=20,
type=int,
help='Max Queue Size')
self.parser.add_argument('--maxCoverage',
dest='maxCoverage',
type=int,
default=-1,
help='Maximum coverage to use at each site')
self.parser.add_argument('--mapQvThreshold',
dest='mapQvThreshold',
type=float,
default=-1.0)
self.parser.add_argument(
'--pvalue',
dest='pvalue',
default=0.01,
type=float,
help='p-value required to call a modified base')
self.parser.add_argument(
'--ipdModel',
dest='ipdModel',
default=None,
help='Alternate synthetic IPD model HDF5 file')
self.parser.add_argument(
'--modelIters',
dest='modelIters',
type=int,
default=-1,
help='[Internal] Number of GBM model iteration to use')
self.parser.add_argument('--cap_percentile',
dest='cap_percentile',
type=float,
default=99.0,
help='Global IPD percentile to cap IPDs at')
self.parser.add_argument(
"--methylMinCov",
type=int,
dest='methylMinCov',
default=10,
help=
"Do not try to estimate methylFraction unless coverage is at least this."
)
self.parser.add_argument(
"--identifyMinCov",
type=int,
dest='identifyMinCov',
default=5,
help=
"Do not try to identify the modification type unless coverage is at least this."
)
# Computation management options:
self.parser.add_argument("--refContigs", "-w",
type=str,
dest='refContigs',
default=None,
help="Specify one reference contig name, or multiple comma-separated " \
"contig names, to be processed. By default, processes all " \
"contigs with mapped coverage.")
def slurpWindowFile(fname):
return ",".join(map(str.strip, open(fname).readlines()))
self.parser.add_argument(
"--refContigIndex",
type=int,
dest='refContigIndex',
default=-1,
help=
"For debugging purposes only - rather than enter a reference contig name, simply enter an index"
)
self.parser.add_argument(
"--refContigsFile",
"-W",
type=slurpWindowFile,
dest='refContigs',
default=None,
help="A file containing contig names, one per line")
self.parser.add_argument(
'--numWorkers',
dest='numWorkers',
default=-1, # Defaults to using all logical CPUs
type=int,
help='Number of thread to use (-1 uses all logical cpus)')
# Debugging help options:
self.parser.add_argument(
"--threaded",
"-T",
action="store_true",
dest="threaded",
default=False,
help=
"Run threads instead of processes (for debugging purposes only)")
self.parser.add_argument(
"--profile",
action="store_true",
dest="doProfiling",
default=False,
help="Enable Python-level profiling (using cProfile).")
self.parser.add_argument(
'--pdb',
action='store_true',
dest="usePdb",
default=False,
help=
"Enable dropping down into pdb debugger if an Exception is raised."
)
# Verbosity
self.parser.add_argument("--verbose",
"-v",
action="store_true",
default=False)
# Version
class PrintVersionAction(argparse.Action):
def __call__(self, parser, namespace, values, option_string=None):
print __version__
sys.exit(0)
self.parser.add_argument("--version",
nargs=0,
action=PrintVersionAction)
def parseArgs(self):
self.args = self.parser.parse_args()
def start(self):
self.parseArgs()
self.validateArgs()
return self.run()
def getVersion(self):
return __version__
def validateArgs(self):
if not os.path.exists(self.args.infile):
self.parser.error('input.cmp.h5 file provided does not exist')
if self.args.identify and self.args.control:
self.parser.error(
'--control and --identify are mutally exclusive. Please choose one or the other'
)
if self.args.useLDA:
if self.args.m5Cclassifier is None:
self.parser.error(
'Please specify a folder containing forward.csv and reverse.csv classifiers in --m5Cclassifier.'
)
if self.args.m5Cgff:
if not self.args.useLDA:
self.parser.error(
'm5Cgff file can only be generated in --useLDA mode.')
# if self.args.methylFraction and not self.args.identify:
# self.parser.error('Currently, --methylFraction only works when the --identify option is specified.')
def run(self):
# Figure out what modifications to identify
mods = self.args.identify
modsToCall = []
if mods:
items = mods.split(",")
if 'm6A' in items:
modsToCall.append('H')
if 'm4C' in items:
modsToCall.append('J')
if 'm5C_TET' in items:
modsToCall.append('K')
self.args.identify = True
self.args.modsToCall = modsToCall
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# Log generously
stdOutHandler = logging.StreamHandler(sys.stdout)
logFormat = '%(asctime)s [%(levelname)s] %(message)s'
if self.args.verbose:
logging.basicConfig(level=logging.INFO, format=logFormat)
else:
logging.basicConfig(level=logging.WARN, format=logFormat)
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()",
globals=globals(),
locals=locals(),
filename="profile.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on the main thread
if not self.args.threaded:
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
if self.options.threaded:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = Queue.Queue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
else:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(
self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus, ))
logging.info("Requested worker processes: %d" %
(self.options.numWorkers, ))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn(
"More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance." %
(self.options.numWorkers, availableCpus))
self._initQueues()
if self.options.threaded:
self.options.numWorkers = 1
WorkerType = KineticWorkerThread
else:
WorkerType = KineticWorkerProcess
# Launch the worker processes
self._workers = []
for i in xrange(self.options.numWorkers):
p = WorkerType(self.options, self._workQueue, self._resultsQueue,
self.ipdModel)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options,
self._resultsQueue,
self.refInfo,
self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(
target=monitorChildProcesses,
args=(self._workers + [self._resultCollectorProcess], ))
self.monitoringThread.start()
def _queueChunksForReference(self, refInfo):
"""
Compute the chunk extents and queue up the work for a single reference
"""
# Number of hits on current reference
refGroupId = refInfo.ID
numHits = (self.cmph5.RefGroupID == refGroupId).sum()
# Don't process reference groups with 0 hits. They may not exist?
if numHits == 0:
return
# Maximum chunk size (set no larger than 1Mb for now)
MAX_BLOCK_SIZE = 25000
# Maximum number of hits per chunk
MAX_HITS = 5000
nBases = min(refInfo.Length, self.args.maxLength)
# Adjust numHits if we are only doing part of the contig
numHits = (numHits * nBases) / refInfo.Length
nBlocks = max([numHits / MAX_HITS, nBases / (MAX_BLOCK_SIZE - 1) + 1])
# Including nBases / (MAX_BLOCK_SIZE - 1) + 1 in nBlocks calculation:
# E. coli genome: this should be ~ 10.
# Human genome: ought to be largest & is meant to ensure that blockSize < MAX_BLOCK_SIZE.
# Block layout
blockSize = min(nBases, max(nBases / nBlocks + 1, 1000))
blockStarts = np.arange(0, nBases, step=blockSize)
blockEnds = blockStarts + blockSize
blocks = zip(blockStarts, blockEnds)
logging.info(
"Queueing chunks for ref: %d. NumReads: %d, Block Size: %d " %
(refGroupId, numHits, blockSize))
# Queue up work blocks
for block in blocks:
# NOTE! The format of a work chunk is (refId <int>, refStartBase <int>, refEndBase <int>)
chunk = (refInfo.ID, block[0], block[1])
self._workQueue.put((self.workChunkCounter, chunk))
self.workChunkCounter += 1
if self.workChunkCounter % 10 == 0:
logging.info("Queued chunk: %d. Chunks in queue: %d" %
(self.workChunkCounter, self._workQueue.qsize()))
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
if (self.options.refContigs is not None
or self.options.refContigIndex != -1):
if (self.options.refContigs is not None
and self.options.refContigIndex != -1):
requestedIds = set(self.options.refContigs.split(',')).union(
[self.options.refContigIndex])
elif (self.options.refContigs is None
and self.options.refContigIndex != -1):
requestedIds = set([self.options.refContigIndex])
elif (self.options.refContigs is not None
and self.options.refContigIndex == -1):
requestedIds = set(self.options.refContigs.split(','))
relevantContigs = [
i for (i, rec) in enumerate(refInfoTable)
if (rec.FullName in requestedIds or rec.Name in requestedIds
or rec.RefInfoID in requestedIds)
]
self.refInfo = refInfoTable[relevantContigs]
else:
self.refInfo = refInfoTable
# 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.loadCmpH5Chemistry(cmpH5Path)
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()
# Load reference and IpdModel
self.loadReferenceAndModel(self.args.reference, self.args.infile)
# Spawn workers
self._launchSlaveProcesses()
# WARNING -- cmp.h5 file must be opened AFTER worker processes have been spawned
# cmp.h5 we're using -- use this to orchestrate the work
self.cmph5 = CmpH5Reader(self.args.infile)
logging.info('Generating kinetics summary for [%s]' % self.args.infile)
#self.referenceMap = self.cmph5['/RefGroup'].asDict('RefInfoID', 'ID')
#self.alnInfo = self.cmph5['/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 ref in self.refInfo:
logging.info('Processing reference entry: [%s]' % ref.ID)
self._queueChunksForReference(ref)
# 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.")
del self.cmph5
return 0
class KineticsToolsRunner(object):
def __init__(self):
desc = ['Tool for detecting DNA base-modifications from kinetic signatures',
'Notes: For all command-line arguments, default values are listed in [].']
description = '\n'.join(desc)
self.parser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter,
description=description,
version=__version__)
# Positional arguments:
self.parser.add_argument('infile',
metavar='input.cmp.h5',
type=validateFile,
help='Input cmp.h5 filename')
# Optional arguments:
# Output options:
# Note: reference is actually not optional:
self.parser.add_argument('--reference',
type=validateFile,
help='Path to reference FASTA file')
self.parser.add_argument('--outfile',
dest='outfile',
default=None,
help='Use this option to generate all possible output files. Argument here is the root filename of the output files.')
self.parser.add_argument('--gff',
dest='gff',
default=None,
help='Name of output GFF file')
# FIXME: Need to add an extra check for this; it can only be used if --useLDA flag is set.
self.parser.add_argument('--m5Cgff',
dest='m5Cgff',
default=None,
help='Name of output GFF file containing m5C scores')
# FIXME: Make sure that this is specified if --useLDA flag is set.
self.parser.add_argument('--m5Cclassifer',
dest='m5Cclassifier',
default=None,
help='Specify csv file containing a 127 x 2 matrix')
self.parser.add_argument('--csv',
dest='csv',
default=None,
help='Name of output CSV file.')
self.parser.add_argument('--csv_h5',
dest='csv_h5',
default=None,
help='Name of csv output to be written in hdf5 format.')
self.parser.add_argument('--pickle',
dest='pickle',
default=None,
help='Name of output pickle file.')
self.parser.add_argument('--summary_h5',
dest='summary_h5',
default=None,
help='Name of output summary h5 file.')
self.parser.add_argument('--ms_csv',
dest='ms_csv',
default=None,
help='Multisite detection CSV file.')
# Calculation options:
self.parser.add_argument('--control',
dest='control',
default=None,
type=validateNoneOrFile,
help='cmph.h5 file containing a control sample. Tool will perform a case-control analysis')
self.parser.add_argument('--identify',
dest='identify',
default=False,
help='Identify modification types. Comma-separated list of know modification types. Current options are: m6A, m4C, m5C_TET. Cannot be used with --control')
self.parser.add_argument("--methylFraction",
action="store_true",
dest="methylFraction",
default=False,
help="In the --identify mode, add --methylFraction to command line to estimate the methylated fraction, along with 95%% confidence interval bounds.")
# Temporary addition to test LDA for Ca5C detection:
self.parser.add_argument('--useLDA',
action="store_true",
dest='useLDA',
default=False,
help='Set this flag to debug LDA for m5C/Ca5C detection')
# Parameter options:
self.parser.add_argument('--paramsPath',
dest='paramsPath',
default=None,
type=validateNoneOrDir,
help='Directory containing in-silico trained model for each chemistry')
self.parser.add_argument("--maxLength",
default=3e12,
type=int,
help="Maximum number of bases to process per contig")
self.parser.add_argument('--minCoverage',
dest='minCoverage',
default=3,
type=int,
help='Minimum coverage required to call a modified base')
self.parser.add_argument('--maxQueueSize',
dest='maxQueueSize',
default=20,
type=int,
help='Max Queue Size')
self.parser.add_argument('--maxCoverage',
dest='maxCoverage',
type=int, default=-1,
help='Maximum coverage to use at each site')
self.parser.add_argument('--mapQvThreshold',
dest='mapQvThreshold',
type=float,
default=-1.0)
self.parser.add_argument('--pvalue',
dest='pvalue',
default=0.01,
type=float,
help='p-value required to call a modified base')
self.parser.add_argument('--ipdModel',
dest='ipdModel',
default=None,
help='Alternate synthetic IPD model HDF5 file')
self.parser.add_argument('--modelIters',
dest='modelIters',
type=int,
default=-1,
help='[Internal] Number of GBM model iteration to use')
self.parser.add_argument('--cap_percentile',
dest='cap_percentile',
type=float,
default=99.0,
help='Global IPD percentile to cap IPDs at')
self.parser.add_argument("--methylMinCov",
type=int,
dest='methylMinCov',
default=10,
help="Do not try to estimate methylFraction unless coverage is at least this.")
self.parser.add_argument("--identifyMinCov",
type=int,
dest='identifyMinCov',
default=5,
help="Do not try to identify the modification type unless coverage is at least this.")
# Computation management options:
self.parser.add_argument("--refContigs", "-w",
type=str,
dest='refContigs',
default=None,
help="Specify one reference contig name, or multiple comma-separated " \
"contig names, to be processed. By default, processes all " \
"contigs with mapped coverage.")
def slurpWindowFile(fname):
return ",".join(map(str.strip, open(fname).readlines()))
self.parser.add_argument("--refContigIndex", type=int, dest='refContigIndex', default=-1, help="For debugging purposes only - rather than enter a reference contig name, simply enter an index" )
self.parser.add_argument("--refContigsFile", "-W",
type=slurpWindowFile,
dest='refContigs',
default=None,
help="A file containing contig names, one per line")
self.parser.add_argument('--numWorkers',
dest='numWorkers',
default=-1, # Defaults to using all logical CPUs
type=int,
help='Number of thread to use (-1 uses all logical cpus)')
# Debugging help options:
self.parser.add_argument("--threaded", "-T",
action="store_true",
dest="threaded",
default=False,
help="Run threads instead of processes (for debugging purposes only)")
self.parser.add_argument("--profile",
action="store_true",
dest="doProfiling",
default=False,
help="Enable Python-level profiling (using cProfile).")
self.parser.add_argument('--pdb',
action='store_true',
dest="usePdb",
default=False,
help="Enable dropping down into pdb debugger if an Exception is raised.")
def parseArgs(self):
self.args = self.parser.parse_args()
def start(self):
self.parseArgs()
self.validateArgs()
return self.run()
def getVersion(self):
return __version__
def validateArgs(self):
if not os.path.exists(self.args.infile):
self.parser.error('input.cmp.h5 file provided does not exist')
if self.args.identify and self.args.control:
self.parser.error('--control and --identify are mutally exclusive. Please choose one or the other')
if self.args.useLDA:
if self.args.m5Cclassifier is None:
self.parser.error('Please specify a folder containing forward.csv and reverse.csv classifiers in --m5Cclassifier.')
if self.args.m5Cgff:
if not self.args.useLDA:
self.parser.error('m5Cgff file can only be generated in --useLDA mode.')
# if self.args.methylFraction and not self.args.identify:
# self.parser.error('Currently, --methylFraction only works when the --identify option is specified.')
def run(self):
# Figure out what modifications to identify
mods = self.args.identify
modsToCall = []
if mods:
items = mods.split(",")
if 'm6A' in items:
modsToCall.append('H')
if 'm4C' in items:
modsToCall.append('J')
if 'm5C_TET' in items:
modsToCall.append('K')
self.args.identify = True
self.args.modsToCall = modsToCall
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# Log generously
stdOutHandler = logging.StreamHandler(sys.stdout)
logFormat = '%(asctime)s [%(levelname)s] %(message)s'
logging.basicConfig(level=logging.INFO, format=logFormat)
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()",
globals=globals(),
locals=locals(),
filename="profile.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on the main thread
if not self.args.threaded:
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
if self.options.threaded:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = Queue.Queue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
else:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus,))
logging.info("Requested worker processes: %d" % (self.options.numWorkers,))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn("More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance."
% (self.options.numWorkers, availableCpus))
self._initQueues()
if self.options.threaded:
self.options.numWorkers = 1
WorkerType = KineticWorkerThread
else:
WorkerType = KineticWorkerProcess
# Launch the worker processes
self._workers = []
for i in xrange(self.options.numWorkers):
p = WorkerType(self.options, self._workQueue, self._resultsQueue, self.ipdModel)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options, self._resultsQueue, self.refInfo, self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(target=monitorChildProcesses, args=(self._workers + [self._resultCollectorProcess],))
self.monitoringThread.start()
def _queueChunksForReference(self, refInfo):
"""
Compute the chunk extents and queue up the work for a single reference
"""
# Number of hits on current reference
refGroupId = refInfo.ID
numHits = (self.cmph5.RefGroupID == refGroupId).sum()
# Don't process reference groups with 0 hits. They may not exist?
if numHits == 0:
return
# Maximum chunk size (set no larger than 1Mb for now)
MAX_BLOCK_SIZE = 25000
# Maximum number of hits per chunk
MAX_HITS = 5000
nBases = min(refInfo.Length, self.args.maxLength)
# Adjust numHits if we are only doing part of the contig
numHits = (numHits * nBases) / refInfo.Length
nBlocks = max([numHits / MAX_HITS, nBases / (MAX_BLOCK_SIZE - 1) + 1])
# Including nBases / (MAX_BLOCK_SIZE - 1) + 1 in nBlocks calculation:
# E. coli genome: this should be ~ 10.
# Human genome: ought to be largest & is meant to ensure that blockSize < MAX_BLOCK_SIZE.
# Block layout
blockSize = min(nBases, max(nBases / nBlocks + 1, 1000))
blockStarts = np.arange(0, nBases, step=blockSize)
blockEnds = blockStarts + blockSize
blocks = zip(blockStarts, blockEnds)
logging.info("Queueing chunks for ref: %d. NumReads: %d, Block Size: %d " % (refGroupId, numHits, blockSize))
# Queue up work blocks
for block in blocks:
# NOTE! The format of a work chunk is (refId <int>, refStartBase <int>, refEndBase <int>)
chunk = (refInfo.ID, block[0], block[1])
self._workQueue.put((self.workChunkCounter, chunk))
self.workChunkCounter += 1
if self.workChunkCounter % 10 == 0:
logging.info("Queued chunk: %d. Chunks in queue: %d" % (self.workChunkCounter, self._workQueue.qsize()))
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
if (self.options.refContigs is not None or
self.options.refContigIndex != -1):
if (self.options.refContigs is not None and
self.options.refContigIndex != -1):
requestedIds = set(self.options.refContigs.split(',')).union([self.options.refContigIndex])
elif (self.options.refContigs is None and
self.options.refContigIndex != -1):
requestedIds = set([self.options.refContigIndex])
elif (self.options.refContigs is not None and
self.options.refContigIndex == -1):
requestedIds = set(self.options.refContigs.split(','))
relevantContigs = [ i for (i, rec) in enumerate(refInfoTable)
if (rec.FullName in requestedIds or
rec.Name in requestedIds or
rec.RefInfoID in requestedIds) ]
self.refInfo = refInfoTable[relevantContigs]
else:
self.refInfo = refInfoTable
# 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.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == 'unknown':
logging.warning("Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
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()
# Load reference and IpdModel
self.loadReferenceAndModel(self.args.reference, self.args.infile)
# Spawn workers
self._launchSlaveProcesses()
# WARNING -- cmp.h5 file must be opened AFTER worker processes have been spawned
# cmp.h5 we're using -- use this to orchestrate the work
self.cmph5 = CmpH5Reader(self.args.infile)
logging.info('Generating kinetics summary for [%s]' % self.args.infile)
#self.referenceMap = self.cmph5['/RefGroup'].asDict('RefInfoID', 'ID')
#self.alnInfo = self.cmph5['/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 ref in self.refInfo:
logging.info('Processing reference entry: [%s]' % ref.ID)
self._queueChunksForReference(ref)
# 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.")
del self.cmph5
return 0
class ReprocessMotifSites(PBToolRunner):
def __init__(self):
desc = [
"For all sites in motifs.gff, reports estimated methylated fraction and 95% confidence interval",
"Notes: For all command-line arguments, default values are listed in [].",
]
super(ReprocessMotifSites, self).__init__("\n".join(desc))
self.parser.add_argument(
"--numWorkers",
dest="numWorkers",
default=-1, # Defaults to using all logical CPUs
type=int,
help="Number of thread to use (-1 uses all logical cpus)",
)
self.parser.add_argument("infile", metavar="input.cmp.h5", help="Input cmp.h5 filename")
# self.parser.add_argument('--control',
# dest='control',
# default=None,
# help='cmph.h5 file ')
# self.parser.add_argument('--outfile',
# dest='outfile',
# default=None,
# help='Use this option to generate all possible output files. Argument here is the root filename of the output files.')
self.parser.add_argument("--gff", dest="gff", default=None, help="Name of output GFF file [%(default)s]")
# self.parser.add_argument('--identify',
# dest='identify',
# default=False,
# help='Identify modification types. Comma-separated list of know modification types. Current options are: m6A, m4C, m5C_TET. Cannot be used with --control')
# self.parser.add_argument('--csv',
# dest='csv',
# default=None,
# help='Name of output CSV file [%(default)s]')
# self.parser.add_argument('--pickle',
# dest='pickle',
# default=None,
# help='Name of output pickle file [%(default)s]')
# self.parser.add_argument('--summary_h5',
# dest='summary_h5',
# default=None,
# help='Name of output summary h5 file [%(default)s]')
self.parser.add_argument("--reference", dest="reference", required=True, help="Path to reference FASTA file")
self.parser.add_argument(
"--maxLength", default=3e12, type=int, help="Maximum number of bases to process per contig"
)
self.parser.add_argument(
"--minCoverage",
dest="minCoverage",
default=3,
type=int,
help="Minimum coverage required to call a modified base",
)
self.parser.add_argument("--maxQueueSize", dest="maxQueueSize", default=1000, type=int, help="Max Queue Size")
self.parser.add_argument(
"--maxCoverage", dest="maxCoverage", type=int, default=None, help="Maximum coverage to use at each site"
)
self.parser.add_argument("--mapQvThreshold", dest="mapQvThreshold", type=float, default=-1.0)
# self.parser.add_argument('--pvalue',
# dest='pvalue',
# default=0.01,
# type=float,
# help='p-value required to call a modified base')
self.parser.add_argument(
"--subread_norm",
dest="subread_norm",
default=True,
type=lambda x: x != "False",
help="Normalized subread ipds",
)
self.parser.add_argument(
"--ipdModel", dest="ipdModel", default=None, help="Alternate synthetic IPD model HDF5 file"
)
self.parser.add_argument(
"--cap_percentile",
dest="cap_percentile",
type=float,
default=99.0,
help="Global IPD percentile to cap IPDs at",
)
self.parser.add_argument(
"--threaded",
"-T",
action="store_true",
dest="threaded",
default=False,
help="Run threads instead of processes (for debugging purposes only)",
)
self.parser.add_argument(
"--profile",
action="store_true",
dest="doProfiling",
default=False,
help="Enable Python-level profiling (using cProfile).",
)
# self.parser.add_argument("--methylFraction",
# action="store_true",
# dest="methylFraction",
# default=False,
# help="In the --identify mode, add --methylFraction to command line to estimate the methylated fraction, along with 95% confidence interval bounds.")
# The following are in addition to ipdSummary.py's inputs:
self.parser.add_argument("--motifs", dest="motifs", required=True, help="Name of motifs GFF file [%(default)s]")
self.parser.add_argument(
"--motif_summary", dest="motif_summary", required=True, help="Name of motif summary CSV file"
)
self.parser.add_argument(
"--undetected",
action="store_true",
dest="undetected",
default=False,
help="Setting this flag yields output with only undetected motif sites.",
)
self.parser.add_argument(
"--modifications", dest="modifications", default=None, help="Name of modifications GFF file [%(default)s]"
)
self.parser.add_argument(
"--oldData",
action="store_true",
dest="oldData",
default=False,
help="For datasets prior to 1.3.3 (use this option to increase testing possibilities)",
)
# A new addition to ipdSummary.py
self.parser.add_argument(
"--paramsPath",
dest="paramsPath",
default=None,
help="Directory containing in-silico trained model for each chemistry",
)
self.parser.add_argument(
"--modelIters",
dest="modelIters",
type=int,
default=-1,
help="[Internal] Number of GBM model iteration to use",
)
def getVersion(self):
return __version__
def validateArgs(self):
if not os.path.exists(self.args.infile):
self.parser.error("input.cmp.h5 file provided does not exist")
# Add checks corresponding to new required inputs:
if not os.path.exists(self.args.motifs):
self.parser.error("input motifs gff file provided does not exist")
if not os.path.exists(self.args.motif_summary):
self.parser.error("input motif_summary csv file provided does not exist")
if not self.args.undetected and not os.path.exists(self.args.modifications):
self.parser.error("either the --undetected flag must be set, or a valid modifications.gff must be provided")
def run(self):
# The following arguments are set in order to use ResultWriter.py as is:
self.args.methylFraction = True
self.args.outfile = None
self.args.csv = None
self.args.control = None
self.args.summary_h5 = None
self.args.pickle = None
self.args.identify = False
self.args.pvalue = 1.0
self.options = self.args
self.options.cmdLine = " ".join(sys.argv)
self._workers = []
# Log generously
logFormat = "%(asctime)s [%(levelname)s] %(message)s"
logging.basicConfig(level=logging.INFO, format=logFormat)
stdOutHandler = logging.StreamHandler(sys.stdout)
# logging.Logger.root.addHandler(stdOutHandler)
# logging.info("t1")
if self.args.doProfiling:
cProfile.runctx("self._mainLoop()", globals=globals(), locals=locals(), filename="profile-main4.out")
else:
try:
ret = self._mainLoop()
finally:
# Be sure to shutdown child processes if we get an exception on the main thread
if not self.args.threaded:
for w in self._workers:
if w.is_alive():
w.terminate()
return ret
def _initQueues(self):
if self.options.threaded:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = Queue.Queue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
else:
# Work chunks are created by the main thread and put on this queue
# They will be consumed by KineticWorker threads, stored in self._workers
self._workQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
# Completed chunks are put on this queue by KineticWorker threads
# They are consumed by the KineticsWriter process
self._resultsQueue = multiprocessing.JoinableQueue(self.options.maxQueueSize)
def _launchSlaveProcesses(self):
"""
Launch a group of worker processes (self._workers), the queue
(self._workQueue) that will be used to send them chunks of
work, and the queue that will be used to receive back the
results (self._resultsQueue).
Additionally, launch the result collector process.
"""
availableCpus = multiprocessing.cpu_count()
logging.info("Available CPUs: %d" % (availableCpus,))
logging.info("Requested worker processes: %d" % (self.options.numWorkers,))
# Use all CPUs if numWorkers < 1
if self.options.numWorkers < 1:
self.options.numWorkers = availableCpus
# Warn if we make a bad numWorker argument is used
if self.options.numWorkers > availableCpus:
logging.warn(
"More worker processes requested (%d) than CPUs available (%d);"
" may result in suboptimal performance." % (self.options.numWorkers, availableCpus)
)
self._initQueues()
if self.options.threaded:
self.options.numWorkers = 1
WorkerType = KineticWorkerThread
else:
WorkerType = KineticWorkerProcess
# Launch the worker processes
self._workers = []
for i in xrange(self.options.numWorkers):
p = WorkerType(self.options, self._workQueue, self._resultsQueue, self.ipdModel)
self._workers.append(p)
p.start()
logging.info("Launched worker processes.")
# Launch result collector
self._resultCollectorProcess = KineticsWriter(self.options, self._resultsQueue, self.refInfo, self.ipdModel)
self._resultCollectorProcess.start()
logging.info("Launched result collector process.")
# Spawn a thread that monitors worker threads for crashes
self.monitoringThread = threading.Thread(
target=monitorChildProcesses, args=(self._workers + [self._resultCollectorProcess],)
)
self.monitoringThread.start()
def _queueChunksForReference(self):
# Read in motif_summary.csv
motifInfo = {}
reader = csv.reader(open(self.args.motif_summary, "r"), delimiter=",")
reader.next()
if self.options.oldData:
col = 1
else:
col = 2
for row in reader:
motifInfo[row[0]] = row[col]
# Figure out the length of the motifs file:
motReader = GffReader(self.args.motifs)
if self.options.undetected:
motifDicts = [
{
"seqID": x.seqid,
"type": x.type,
"score": x.score,
"pos": x.start,
"strand": x.strand,
"attributes": x.attributes,
}
for x in motReader
if x.type == "."
]
else:
motifDicts = [
{
"seqID": x.seqid,
"type": x.type,
"score": x.score,
"pos": x.start,
"strand": x.strand,
"attributes": x.attributes,
}
for x in motReader
]
refLength = len(motifDicts)
# Maximum number of hits per chunk
MAX_HITS = 500
nBases = min(refLength, self.args.maxLength)
nBlocks = max(self.options.numWorkers * 4, nBases / MAX_HITS)
# Block layout
blockSize = min(nBases, max(nBases / nBlocks + 1, 100))
blockStarts = np.arange(0, nBases, step=blockSize)
blockEnds = blockStarts + blockSize
blocks = zip(blockStarts, blockEnds)
if self.options.undetected:
self.options.modifications = None
# Queue up work blocks
for block in blocks:
# NOTE! The format of a work chunk is (refId <int>, refStartBase <int>, refEndBase <int>)
# chunk = (refInfoId, block[0], block[1])
# chunk = (self.options.motifs, self.refInfo, motifInfo, self.options.modifications, self.options.undetected, self.options.oldData, block[0], block[1])
chunk = (
motifDicts[block[0] : block[1]],
self.refInfo,
motifInfo,
self.options.modifications,
self.options.undetected,
self.options.oldData,
block[0],
block[1],
)
self._workQueue.put((self.workChunkCounter, chunk))
self.workChunkCounter += 1
def loadReference(self):
# FIXME - support a bare fasta file as well?
self.referenceEntry = ReferenceEntry(self.args.reference)
self.refInfo = self.referenceEntry.contigs
if self.args.ipdModel:
self.lutPath = self.args.ipdModel
if not os.path.exists(self.lutPath):
logging.info("Couldn't find model file: %s" % self.lutPath)
raise Exception("Couldn't find model file: %s" % self.lutPath)
else:
self.lutPath = None
self.ipdModel = IpdModel(self.referenceEntry, self.lutPath)
def loadReferenceAndModel(self, referencePath, cmpH5Path):
# Load the reference contigs - annotated with their refID from the cmp.h5
contigs = ReferenceUtils.loadReferenceContigs(referencePath, cmpH5Path)
# Read reference info table from cmp.h5
(refInfoTable, _) = ReferenceUtils.loadCmpH5Tables(cmpH5Path)
self.refInfo = refInfoTable
# 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 chemistry info
# 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)
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.loadCmpH5Chemistry(cmpH5Path)
ipdModel = os.path.join(self.args.paramsPath, majorityChem + ".h5")
if majorityChem == "unknown":
logging.warning("Chemistry is unknown. Falling back to built-in model")
ipdModel = None
elif not os.path.exists(ipdModel):
logging.warning("Model not found: %s" % ipdModel)
logging.warning("Falling back to built-in model")
ipdModel = None
else:
logging.info("Using Chemistry matched IPD model: %s" % ipdModel)
self.ipdModel = IpdModel(contigs, ipdModel, self.args.modelIters)
def _mainLoop(self):
# See comments in ipdSummary.py
gc.disable()
# Load reference and IpdModel
# self.loadReference()
# Load reference and IpdModel
self.loadReferenceAndModel(self.args.reference, self.args.infile)
# Spawn workers
self._launchSlaveProcesses()
# cmp.h5 we're using -- use this to orchestrate the work
self.cmph5 = CmpH5Reader(self.args.infile)
logging.info("Generating kinetics summary for [%s]" % self.args.infile)
self.workChunkCounter = 0
self._queueChunksForReference()
# 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("reprocessMotifSites.py finished. Exiting.")
del self.cmph5
return 0