def get_tag_count(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000):
"""
Gets the tag count associated with self.bam based on start, end and ext.
Keyword arguments:
ref -- Chromosome name.
start -- Initial genomic coordinate of signal.
end -- Final genomic coordinate of signal.
downstream_ext -- Number of bps to extend towards the downstream region (right for forward strand and left for reverse strand).
upstream_ext -- Number of bps to extend towards the upstream region (left for forward strand and right for reverse strand).
forward_shift -- Number of bps to shift the reads aligned to the forward strand. Can be a positive number for a shift towards the downstream region (towards the inside of the aligned read) and a negative number for a shift towards the upstream region.
reverse_shift -- Number of bps to shift the reads aligned to the reverse strand. Can be a positive number for a shift towards the upstream region and a negative number for a shift towards the downstream region (towards the inside of the aligned read).
initial_clip -- Signal will be initially clipped at this level to avoid outliers.
Return:
tag_count -- Total signal.
"""
# Fetch raw signal
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter: pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
# Tag count
try:
tag_count = sum(raw_signal)
except Exception:
tag_count = 0
return tag_count
def get_tag_count(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000):
"""
Gets the tag count associated with self.bam based on start, end and ext.
Keyword arguments:
ref -- Chromosome name.
start -- Initial genomic coordinate of signal.
end -- Final genomic coordinate of signal.
downstream_ext -- Number of bps to extend towards the downstream region (right for forward strand and left for reverse strand).
upstream_ext -- Number of bps to extend towards the upstream region (left for forward strand and right for reverse strand).
forward_shift -- Number of bps to shift the reads aligned to the forward strand. Can be a positive number for a shift towards the downstream region (towards the inside of the aligned read) and a negative number for a shift towards the upstream region.
reverse_shift -- Number of bps to shift the reads aligned to the reverse strand. Can be a positive number for a shift towards the upstream region and a negative number for a shift towards the downstream region (towards the inside of the aligned read).
initial_clip -- Signal will be initially clipped at this level to avoid outliers.
Return:
tag_count -- Total signal.
"""
# Fetch raw signal
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter: pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
# Tag count
try:
tag_count = sum(raw_signal)
except Exception:
tag_count = 0
return tag_count
# Iterating on MPBSs
intFile = open(intFileName, "r")
spr = 0.0
counter = 0.0
for line in intFile:
# Fetching signal
ll = line.strip().split("\t")
mLen = int(ll[2]) - int(ll[1])
mid = (int(ll[1]) + int(ll[2])) / 2
p1 = max(mid - halfWindow, 0)
p2 = mid + halfWindow
# Fetch raw signal
pileup_region = PileupRegion(p1, p2, 1)
if (ps_version == "0.7.5"):
bam.fetch(reference=ll[0],
start=p1,
end=p2,
callback=pileup_region)
else:
iter = bam.fetch(reference=ll[0], start=p1, end=p2)
for alignment in iter:
pileup_region.__call__(alignment)
raw_signal = array(
[min(e, initial_clip) for e in pileup_region.vector])
# Std-based clipping
mean = raw_signal.mean()
std = raw_signal.std()
# Iterating on MPBSs
intFile = open(intFileName,"r")
spr = 0.0
counter = 0.0
for line in intFile:
# Fetching signal
ll = line.strip().split("\t")
mLen = int(ll[2]) - int(ll[1])
mid = (int(ll[1])+int(ll[2]))/2
p1 = max(mid - halfWindow,0)
p2 = mid + halfWindow
# Fetch raw signal
pileup_region = PileupRegion(p1,p2,1)
if(ps_version == "0.7.5"):
bam.fetch(reference=ll[0], start=p1, end=p2, callback = pileup_region)
else:
iter = bam.fetch(reference=ll[0], start=p1, end=p2)
for alignment in iter: pileup_region.__call__(alignment)
raw_signal = array([min(e,initial_clip) for e in pileup_region.vector])
# Std-based clipping
mean = raw_signal.mean()
std = raw_signal.std()
clip_signal = [min(e, mean + (10 * std)) for e in raw_signal]
# Bias Correction
correctedSignal = bias_correction(bam, clip_signal, biasTableF, biasTableR, genomeFileName, ll[0], p1, p2)
def get_signal(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000, per_norm=98, per_slope=98,
bias_table=None, genome_file_name=None, print_raw_signal=False):
"""
Gets the signal associated with self.bam based on start, end and ext.
initial_clip, per_norm and per_slope are used as normalization factors during the normalization
and slope evaluation procedures.
Keyword arguments:
ref -- Chromosome name.
start -- Initial genomic coordinate of signal.
end -- Final genomic coordinate of signal.
initial_clip -- Signal will be initially clipped at this level to avoid outliers.
per_norm -- Percentile value for 'hon_norm' function of the normalized signal.
per_slope -- Percentile value for 'hon_norm' function of the slope signal.
bias_table -- Bias table to perform bias correction.
genome_file_name -- Genome to perform bias correction.
downstream_ext -- Number of bps to extend towards the downstream region
(right for forward strand and left for reverse strand).
upstream_ext -- Number of bps to extend towards the upstream region
(left for forward strand and right for reverse strand).
forward_shift -- Number of bps to shift the reads aligned to the forward strand.
Can be a positive number for a shift towards the downstream region
(towards the inside of the aligned read) and a negative number for a shift towards the upstream region.
reverse_shift -- Number of bps to shift the reads aligned to the reverse strand.
Can be a positive number for a shift towards the upstream region and a negative number
for a shift towards the downstream region (towards the inside of the aligned read).
Return:
hon_signal -- Normalized signal.
slopehon_signal -- Slope signal.
"""
# Fetch raw signal
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter:
pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
# Std-based clipping
mean = raw_signal.mean()
std = raw_signal.std()
clip_signal = [min(e, mean + (10 * std)) for e in raw_signal]
# Cleavage bias correction
bc_signal = self.bias_correction_dnase(clip_signal, bias_table, genome_file_name, ref, start, end,
forward_shift, reverse_shift)
# Boyle normalization (within-dataset normalization)
boyle_signal = array(self.boyle_norm(bc_signal))
# Hon normalization (between-dataset normalization)
perc = scoreatpercentile(boyle_signal, per_norm)
std = boyle_signal.std()
hon_signal = self.hon_norm_dnase(boyle_signal, perc, std)
# Slope signal
slope_signal = self.slope(hon_signal, self.sg_coefs)
# Returning normalized and slope sequences
return hon_signal, slope_signal
def print_signal(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000, per_norm=98, per_slope=98, bias_table=None, genome_file_name=None,
raw_signal_file=None, bc_signal_file=None, norm_signal_file=None, strand_specific=False):
if raw_signal_file:
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter:
pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
f = open(raw_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(raw_signal)]) + "\n")
f.close()
if bc_signal_file or norm_signal_file:
# Parameters
window = 50
defaultKmerValue = 1.0
# Initialization
fasta = Fastafile(genome_file_name)
fBiasDict = bias_table[0]
rBiasDict = bias_table[1]
k_nb = len(fBiasDict.keys()[0])
p1 = start
p2 = end
p1_w = p1 - (window / 2)
p2_w = p2 + (window / 2)
p1_wk = p1_w - int(k_nb / 2.)
p2_wk = p2_w + int(k_nb / 2.)
currStr = str(fasta.fetch(ref, p1_wk, p2_wk - 1)).upper()
currRevComp = AuxiliaryFunctions.revcomp(str(fasta.fetch(ref, p1_wk + 1, p2_wk)).upper())
# Iterating on sequence to create the bias signal
signal_bias_f = []
signal_bias_r = []
for i in range(int(k_nb / 2.), len(currStr) - int(k_nb / 2) + 1):
fseq = currStr[i - int(k_nb / 2.):i + int(k_nb / 2.)]
rseq = currRevComp[len(currStr) - int(k_nb / 2.) - i:len(currStr) + int(k_nb / 2.) - i]
try:
signal_bias_f.append(fBiasDict[fseq])
except Exception:
signal_bias_f.append(defaultKmerValue)
try:
signal_bias_r.append(rBiasDict[rseq])
except Exception:
signal_bias_r.append(defaultKmerValue)
# Raw counts
signal_raw_f = [0.0] * (p2_w - p1_w)
signal_raw_r = [0.0] * (p2_w - p1_w)
for read in self.bam.fetch(ref, p1_w, p2_w):
if not read.is_reverse:
cut_site = read.pos + forward_shift
if p1_w <= cut_site < p2_w:
signal_raw_f[cut_site - p1_w] += 1.0
else:
cut_site = read.aend + reverse_shift - 1
if p1_w <= cut_site < p2_w:
signal_raw_r[cut_site - p1_w] += 1.0
# Smoothed counts
Nf = []
Nr = []
fSum = sum(signal_raw_f[:window])
rSum = sum(signal_raw_r[:window])
fLast = signal_raw_f[0]
rLast = signal_raw_r[0]
for i in range((window / 2), len(signal_raw_f) - (window / 2)):
Nf.append(fSum)
Nr.append(rSum)
fSum -= fLast
fSum += signal_raw_f[i + (window / 2)]
fLast = signal_raw_f[i - (window / 2) + 1]
rSum -= rLast
rSum += signal_raw_r[i + (window / 2)]
rLast = signal_raw_r[i - (window / 2) + 1]
# Calculating bias and writing to wig file
fSum = sum(signal_bias_f[:window])
rSum = sum(signal_bias_r[:window])
fLast = signal_bias_f[0]
rLast = signal_bias_r[0]
signal_bc = []
signal_bc_f = []
signal_bc_r = []
for i in range((window / 2), len(signal_bias_f) - (window / 2)):
nhatf = Nf[i - (window / 2)] * (signal_bias_f[i] / fSum)
nhatr = Nr[i - (window / 2)] * (signal_bias_r[i] / rSum)
signal_bc.append(nhatf + nhatr)
signal_bc_f.append(nhatf)
signal_bc_r.append(nhatr)
fSum -= fLast
fSum += signal_bias_f[i + (window / 2)]
fLast = signal_bias_f[i - (window / 2) + 1]
rSum -= rLast
rSum += signal_bias_r[i + (window / 2)]
rLast = signal_bias_r[i - (window / 2) + 1]
if bc_signal_file:
f = open(bc_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc)]) + "\n")
f.close()
if strand_specific:
prefix = bc_signal_file.split(".")[0]
bc_signal_file_f = prefix + "_Forward" + ".bc.wig"
bc_signal_file_r = prefix + "_Reverse" + ".bc.wig"
f = open(bc_signal_file_f, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc_f)]) + "\n")
f.close()
f = open(bc_signal_file_r, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc_r)]) + "\n")
f.close()
if norm_signal_file:
norm_signal_bc = self.boyle_norm(signal_bc)
perc = scoreatpercentile(norm_signal_bc, 98)
std = np.std(norm_signal_bc)
norm_signal_bc = self.hon_norm_atac(norm_signal_bc, perc, std)
f = open(norm_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(norm_signal_bc)]) + "\n")
f.close()
if strand_specific:
prefix = bc_signal_file.split(".")[0]
norm_signal_file_f = prefix + "_Forward" + ".norm.wig"
norm_signal_file_r = prefix + "_Reverse" + ".norm.wig"
signal_norm_f = self.boyle_norm(signal_bc_f)
perc = scoreatpercentile(signal_norm_f, 98)
std = np.std(signal_norm_f)
signal_norm_f = self.hon_norm_atac(signal_norm_f, perc, std)
signal_norm_r = self.boyle_norm(signal_bc_r)
perc = scoreatpercentile(signal_norm_r, 98)
std = np.std(signal_norm_r)
signal_norm_r = self.hon_norm_atac(signal_norm_r, perc, std)
f = open(norm_signal_file_f, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_norm_f)]) + "\n")
f.close()
f = open(norm_signal_file_r, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_norm_r)]) + "\n")
f.close()
def get_signal(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000, per_norm=98, per_slope=98,
bias_table=None, genome_file_name=None, print_raw_signal=False):
"""
Gets the signal associated with self.bam based on start, end and ext.
initial_clip, per_norm and per_slope are used as normalization factors during the normalization
and slope evaluation procedures.
Keyword arguments:
ref -- Chromosome name.
start -- Initial genomic coordinate of signal.
end -- Final genomic coordinate of signal.
initial_clip -- Signal will be initially clipped at this level to avoid outliers.
per_norm -- Percentile value for 'hon_norm' function of the normalized signal.
per_slope -- Percentile value for 'hon_norm' function of the slope signal.
bias_table -- Bias table to perform bias correction.
genome_file_name -- Genome to perform bias correction.
downstream_ext -- Number of bps to extend towards the downstream region
(right for forward strand and left for reverse strand).
upstream_ext -- Number of bps to extend towards the upstream region
(left for forward strand and right for reverse strand).
forward_shift -- Number of bps to shift the reads aligned to the forward strand.
Can be a positive number for a shift towards the downstream region
(towards the inside of the aligned read) and a negative number for a shift towards the upstream region.
reverse_shift -- Number of bps to shift the reads aligned to the reverse strand.
Can be a positive number for a shift towards the upstream region and a negative number
for a shift towards the downstream region (towards the inside of the aligned read).
Return:
hon_signal -- Normalized signal.
slopehon_signal -- Slope signal.
"""
# Fetch raw signal
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter:
pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
# Std-based clipping
mean = raw_signal.mean()
std = raw_signal.std()
clip_signal = [min(e, mean + (10 * std)) for e in raw_signal]
# Cleavage bias correction
bc_signal = self.bias_correction_dnase(clip_signal, bias_table, genome_file_name, ref, start, end,
forward_shift, reverse_shift)
# Boyle normalization (within-dataset normalization)
boyle_signal = array(self.boyle_norm(bc_signal))
# Hon normalization (between-dataset normalization)
perc = scoreatpercentile(boyle_signal, per_norm)
std = boyle_signal.std()
hon_signal = self.hon_norm_dnase(boyle_signal, perc, std)
# Slope signal
slope_signal = self.slope(hon_signal, self.sg_coefs)
# Returning normalized and slope sequences
return hon_signal, slope_signal
def print_signal(self, ref, start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift,
initial_clip=1000, per_norm=98, per_slope=98, bias_table=None, genome_file_name=None,
raw_signal_file=None, bc_signal_file=None, norm_signal_file=None, strand_specific=False):
if raw_signal_file:
pileup_region = PileupRegion(start, end, downstream_ext, upstream_ext, forward_shift, reverse_shift)
if ps_version == "0.7.5":
self.bam.fetch(reference=ref, start=start, end=end, callback=pileup_region)
else:
iter = self.bam.fetch(reference=ref, start=start, end=end)
for alignment in iter:
pileup_region.__call__(alignment)
raw_signal = array([min(e, initial_clip) for e in pileup_region.vector])
f = open(raw_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(raw_signal)]) + "\n")
f.close()
if bc_signal_file or norm_signal_file:
# Parameters
window = 50
defaultKmerValue = 1.0
# Initialization
fasta = Fastafile(genome_file_name)
fBiasDict = bias_table[0]
rBiasDict = bias_table[1]
k_nb = len(fBiasDict.keys()[0])
p1 = start
p2 = end
p1_w = p1 - (window / 2)
p2_w = p2 + (window / 2)
p1_wk = p1_w - int(k_nb / 2.)
p2_wk = p2_w + int(k_nb / 2.)
currStr = str(fasta.fetch(ref, p1_wk, p2_wk - 1)).upper()
currRevComp = AuxiliaryFunctions.revcomp(str(fasta.fetch(ref, p1_wk + 1, p2_wk)).upper())
# Iterating on sequence to create the bias signal
signal_bias_f = []
signal_bias_r = []
for i in range(int(k_nb / 2.), len(currStr) - int(k_nb / 2) + 1):
fseq = currStr[i - int(k_nb / 2.):i + int(k_nb / 2.)]
rseq = currRevComp[len(currStr) - int(k_nb / 2.) - i:len(currStr) + int(k_nb / 2.) - i]
try:
signal_bias_f.append(fBiasDict[fseq])
except Exception:
signal_bias_f.append(defaultKmerValue)
try:
signal_bias_r.append(rBiasDict[rseq])
except Exception:
signal_bias_r.append(defaultKmerValue)
# Raw counts
signal_raw_f = [0.0] * (p2_w - p1_w)
signal_raw_r = [0.0] * (p2_w - p1_w)
for read in self.bam.fetch(ref, p1_w, p2_w):
if not read.is_reverse:
cut_site = read.pos + forward_shift
if p1_w <= cut_site < p2_w:
signal_raw_f[cut_site - p1_w] += 1.0
else:
cut_site = read.aend + reverse_shift - 1
if p1_w <= cut_site < p2_w:
signal_raw_r[cut_site - p1_w] += 1.0
# Smoothed counts
Nf = []
Nr = []
fSum = sum(signal_raw_f[:window])
rSum = sum(signal_raw_r[:window])
fLast = signal_raw_f[0]
rLast = signal_raw_r[0]
for i in range((window / 2), len(signal_raw_f) - (window / 2)):
Nf.append(fSum)
Nr.append(rSum)
fSum -= fLast
fSum += signal_raw_f[i + (window / 2)]
fLast = signal_raw_f[i - (window / 2) + 1]
rSum -= rLast
rSum += signal_raw_r[i + (window / 2)]
rLast = signal_raw_r[i - (window / 2) + 1]
# Calculating bias and writing to wig file
fSum = sum(signal_bias_f[:window])
rSum = sum(signal_bias_r[:window])
fLast = signal_bias_f[0]
rLast = signal_bias_r[0]
signal_bc = []
signal_bc_f = []
signal_bc_r = []
for i in range((window / 2), len(signal_bias_f) - (window / 2)):
nhatf = Nf[i - (window / 2)] * (signal_bias_f[i] / fSum)
nhatr = Nr[i - (window / 2)] * (signal_bias_r[i] / rSum)
signal_bc.append(nhatf + nhatr)
signal_bc_f.append(nhatf)
signal_bc_r.append(nhatr)
fSum -= fLast
fSum += signal_bias_f[i + (window / 2)]
fLast = signal_bias_f[i - (window / 2) + 1]
rSum -= rLast
rSum += signal_bias_r[i + (window / 2)]
rLast = signal_bias_r[i - (window / 2) + 1]
if bc_signal_file:
f = open(bc_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc)]) + "\n")
f.close()
if strand_specific:
prefix = bc_signal_file.split(".")[0]
bc_signal_file_f = prefix + "_Forward" + ".bc.wig"
bc_signal_file_r = prefix + "_Reverse" + ".bc.wig"
f = open(bc_signal_file_f, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc_f)]) + "\n")
f.close()
f = open(bc_signal_file_r, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_bc_r)]) + "\n")
f.close()
if norm_signal_file:
norm_signal_bc = self.boyle_norm(signal_bc)
perc = scoreatpercentile(norm_signal_bc, 98)
std = np.std(norm_signal_bc)
norm_signal_bc = self.hon_norm_atac(norm_signal_bc, perc, std)
f = open(norm_signal_file, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(norm_signal_bc)]) + "\n")
f.close()
if strand_specific:
prefix = bc_signal_file.split(".")[0]
norm_signal_file_f = prefix + "_Forward" + ".norm.wig"
norm_signal_file_r = prefix + "_Reverse" + ".norm.wig"
signal_norm_f = self.boyle_norm(signal_bc_f)
perc = scoreatpercentile(signal_norm_f, 98)
std = np.std(signal_norm_f)
signal_norm_f = self.hon_norm_atac(signal_norm_f, perc, std)
signal_norm_r = self.boyle_norm(signal_bc_r)
perc = scoreatpercentile(signal_norm_r, 98)
std = np.std(signal_norm_r)
signal_norm_r = self.hon_norm_atac(signal_norm_r, perc, std)
f = open(norm_signal_file_f, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_norm_f)]) + "\n")
f.close()
f = open(norm_signal_file_r, "a")
f.write("fixedStep chrom=" + ref + " start=" + str(start + 1) + " step=1\n" + "\n".join(
[str(e) for e in nan_to_num(signal_norm_r)]) + "\n")
f.close()