def computeBias(self, fasta, chromDict, pwm):
"""compute bias track based on sequence and pwm"""
self.slop(chromDict, up=pwm.up, down=pwm.down)
sequence = seq.get_sequence(self, fasta)
seqmat = seq.seq_to_mat(sequence, pwm.nucleotides)
self.vals = signal.correlate(seqmat, np.log(pwm.mat), mode='valid')[0]
self.start += pwm.up
self.end -= pwm.down
def computeBias(self, fasta, chromDict, pwm):
"""compute bias track based on sequence and pwm"""
self.slop(chromDict, up = pwm.up, down = pwm.down)
sequence = seq.get_sequence(self, fasta)
seqmat = seq.seq_to_mat(sequence, pwm.nucleotides)
self.vals = signal.correlate(seqmat,np.log(pwm.mat),mode='valid')[0]
self.start += pwm.up
self.end -= pwm.down
def getInsertionSequences(self, fasta, nucleotides=["C", "G", "A", "T"], up=10, down=10):
"""Get sequence content at insertions"""
mat = np.zeros((len(nucleotides), up + down + 1))
if np.sum(self.vals) == 0:
return mat
offset = max(up, down)
seq_chunk = Chunk(self.chrom, self.start - offset, self.end + offset)
sequence = get_sequence(seq_chunk, fasta)
seq_mat = seq_to_mat(sequence, nucleotides)
for i in range(self.length()):
mat += self.vals[i] * seq_mat[:, (offset + i - up) : (offset + i + down + 1)]
return mat
def getInsertionSequences(self, fasta, nucleotides = ["C","G","A","T"], up = 10, down = 10):
"""Get sequence content at insertions"""
mat = np.zeros((len(nucleotides), up + down +1))
if np.sum(self.vals) == 0:
return mat
offset = max(up,down)
seq_chunk = Chunk(self.chrom, self.start - offset, self.end + offset)
sequence = get_sequence(seq_chunk, fasta)
seq_mat = seq_to_mat(sequence, nucleotides)
for i in range(self.length()):
mat += self.vals[i] * seq_mat[:,(offset + i - up):(offset + i + down + 1)]
return mat
def getStrandedInsertionSequences(self, fasta, nucleotides=["C", "G", "A", "T"], up=10, down=10):
"""Get sequence content at insertions, taking into account strand"""
mat = np.zeros((len(nucleotides), up + down + 1))
if np.sum(self.vals) == 0:
return mat
offset = max(up, down)
seq_chunk = Chunk(self.chrom, self.start - offset, self.end + offset)
sequence = get_sequence(seq_chunk, fasta)
minus_sequence = complement(sequence)
seq_mat = seq_to_mat(sequence, nucleotides)
minus_seq_mat = seq_to_mat(minus_sequence, nucleotides)
for i in range(self.length()):
mat += self.plus[i] * seq_mat[:, (offset + i - up) : (offset + i + down + 1)]
mat += self.minus[i] * np.fliplr(minus_seq_mat[:, (offset + i - down) : (offset + i + up + 1)])
return mat
def getStrandedInsertionSequences(self, fasta, nucleotides = ["C","G","A","T"], up = 10, down = 10):
"""Get sequence content at insertions, taking into account strand"""
mat = np.zeros((len(nucleotides), up + down +1))
if np.sum(self.vals) == 0:
return mat
offset = max(up,down)
seq_chunk = Chunk(self.chrom, self.start - offset, self.end + offset)
sequence = get_sequence(seq_chunk, fasta)
minus_sequence = complement(sequence)
seq_mat = seq_to_mat(sequence, nucleotides)
minus_seq_mat = seq_to_mat(minus_sequence, nucleotides)
for i in range(self.length()):
mat += self.plus[i] * seq_mat[:,(offset + i - up):(offset + i + down + 1)]
mat += self.minus[i] * np.fliplr(minus_seq_mat[:,(offset + i - down):(offset + i + up + 1)])
return mat
def _nucleotideHelper(arg):
"""Helper function for multiprocessing acquisition of sequence content around sites"""
(chunks, params) = arg
mat = np.zeros(params.matsize)
n = 0.0
try:
for chunk in chunks:
chunk.center()
chunk.slop(chromDict = params.chrs, up = params.up, down = params.down + params.dinucleotide)
sequence = seq.get_sequence(chunk, params.fasta)
submat = seq.seq_to_mat(sequence, params.nucleotides)
if len(sequence) == (params.up + params.down + 1 + params.dinucleotide):
mat += submat
n += 1
except Exception as e:
print('Caught exception when processing:\n'+ chunk.asBed()+'\n')
traceback.print_exc()
print()
raise e
return mat,n
def _nucleotideHelper(arg):
"""Helper function for multiprocessing acquisition of sequence content around sites"""
(chunks, params) = arg
mat = np.zeros(params.matsize)
n = 0.0
try:
for chunk in chunks:
chunk.center()
chunk.slop(chromDict=params.chrs,
up=params.up,
down=params.down + params.dinucleotide)
sequence = seq.get_sequence(chunk, params.fasta)
submat = seq.seq_to_mat(sequence, params.nucleotides)
if len(sequence) == (params.up + params.down + 1 +
params.dinucleotide):
mat += submat
n += 1
except Exception as e:
print(('Caught exception when processing:\n' + chunk.asBed() + '\n'))
traceback.print_exc()
print()
raise e
return mat, n
