def _loadIpdTable(self, nullModelGroup):
"""
Read the null kinetic model into a shared numpy array dataset
"""
nullModelDataset = nullModelGroup["KineticValues"]
# assert that the dataset is a uint8
assert(nullModelDataset.dtype == uint8)
# Construct a 'shared array' (a numpy wrapper around some shared memory
# Read the LUT into this table
self.sharedArray = SharedArray('B', nullModelDataset.shape[0])
lutArray = self.sharedArray.getNumpyWrapper()
nullModelDataset.read_direct(lutArray)
# Load the second-level LUT
self.floatLut = nullModelGroup["Lut"][:]
def __init__(self, fastaRecords, modelFile=None, modelIterations=-1):
"""
Load the reference sequences and the ipd lut into shared arrays that can be
used as numpy arrays in worker processes.
fastaRecords is a list of FastaRecords, in the cmp.h5 file order
"""
self.pre = 10
self.post = 4
self.pad = 30
self.base4 = 4 ** np.array(range(self.pre + self.post + 1))
self.refDict = {}
self.refLengthDict = {}
for contig in fastaRecords:
if contig.id is None:
# This contig has no mapped reads -- skip it
continue
rawSeq = contig.sequence
refSeq = np.fromstring(rawSeq, dtype=byte)
# Store the reference length
self.refLengthDict[contig.id] = len(rawSeq)
# Make a shared array
sa = SharedArray(dtype='B', shape=len(rawSeq) + self.pad * 2)
saWrap = sa.getNumpyWrapper()
# Lut Codes convert Ns to As so that we don't put Ns into the Gbm Model
# Seq Codes leaves Ns as Ns for getting reference snippets out
innerLutCodes = lutCodeMap[refSeq]
innerSeqCodes = seqCodeMap[refSeq]
innerCodes = np.bitwise_or(innerLutCodes, np.left_shift(innerSeqCodes, 4))
saWrap[self.pad:(len(rawSeq) + self.pad)] = innerCodes
# Padding codes -- the lut array is padded with 0s the sequence array is padded with N's (4)
outerCodes = np.left_shift(np.ones(self.pad, dtype=uint8) * 4, 4)
saWrap[0:self.pad] = outerCodes
saWrap[(len(rawSeq) + self.pad):(len(rawSeq) + 2 * self.pad)] = outerCodes
self.refDict[contig.id] = sa
# No correction factor for IPDs everything is normalized to 1
self.meanIpd = 1
# Find and open the ipd model file
if modelFile:
self.lutPath = modelFile
else:
self.lutPath = os.path.dirname(os.path.abspath(__file__)) + os.path.sep + "kineticLut.h5"
if os.path.exists(self.lutPath):
h5File = h5py.File(self.lutPath, mode='r')
gbmModelGroup = h5File["/AllMods_GbmModel"]
self.gbmModel = GbmContextModel(gbmModelGroup, modelIterations)
# We always use the model -- no more LUTS
self.predictIpdFunc = self.predictIpdFuncModel
self.predictManyIpdFunc = self.predictManyIpdFuncModel
else:
logging.info("Couldn't find model file: %s" % self.lutPath)
def __init__(self, fastaRecords, modelFile, modelIterations=-1):
"""
Load the reference sequences and the ipd lut into shared arrays that can be
used as numpy arrays in worker processes.
fastaRecords is a list of FastaRecords, in the alignments file order
"""
self.pre = 10
self.post = 4
self.pad = 30
self.base4 = 4**np.array(range(self.pre + self.post + 1))
self.refDict = {}
self.refLengthDict = {}
for contig in fastaRecords:
if contig.alignmentID is None:
# This contig has no mapped reads -- skip it
continue
rawSeq = contig.sequence[:]
refSeq = np.frombuffer(rawSeq.encode("utf-8"), dtype=byte)
# Store the reference length
self.refLengthDict[contig.alignmentID] = len(rawSeq)
# Make a shared array
sa = SharedArray(dtype='B', shape=len(rawSeq) + self.pad * 2)
saWrap = sa.getNumpyWrapper()
# Lut Codes convert Ns to As so that we don't put Ns into the Gbm Model
# Seq Codes leaves Ns as Ns for getting reference snippets out
innerLutCodes = lutCodeMap[refSeq]
innerSeqCodes = seqCodeMap[refSeq]
innerCodes = np.bitwise_or(innerLutCodes,
np.left_shift(innerSeqCodes, 4))
saWrap[self.pad:(len(rawSeq) + self.pad)] = innerCodes
# Padding codes -- the lut array is padded with 0s the sequence
# array is padded with N's (4)
outerCodes = np.left_shift(np.ones(self.pad, dtype=uint8) * 4, 4)
saWrap[0:self.pad] = outerCodes
saWrap[(len(rawSeq) + self.pad):(len(rawSeq) +
2 * self.pad)] = outerCodes
self.refDict[contig.alignmentID] = sa
# No correction factor for IPDs everything is normalized to 1
self.meanIpd = 1
# Find and open the ipd model file
self.lutPath = modelFile
if os.path.exists(self.lutPath):
with gzip.open(self.lutPath, "rb") as npz_in:
gbmModelData = np.load(npz_in, allow_pickle=True)
self.gbmModel = GbmContextModel(gbmModelData, modelIterations)
# We always use the model -- no more LUTS
self.predictIpdFunc = self.predictIpdFuncModel
self.predictManyIpdFunc = self.predictManyIpdFuncModel
else:
logging.info("Couldn't find model file: %s" % self.lutPath)
