def summary(self):
summary = {"name": "sequana_summary_pacbio_qc"}
summary["read_stats"] = self.stats.copy()
summary["mean_gc"] = float(np.mean(self._df.loc[:,'GC_content']))
a, b = np.histogram(self._df.loc[:,'GC_content'], bins=100)
summary['hist_gc'] = {"Y": a.tolist(), "X": b.tolist()}
a, b = np.histogram(self._df['read_length'],100)
summary['hist_read_length'] = {"Y": a.tolist(), "X": b.tolist()}
return summary
def summary(self):
summary = {"name": "sequana_summary_pacbio_qc"}
summary["read_stats"] = self.stats.copy()
summary["mean_gc"] = float(np.mean(self._df.loc[:, 'GC_content']))
a, b = np.histogram(self._df.loc[:, 'GC_content'], bins=100)
summary['hist_gc'] = {"Y": a.tolist(), "X": b.tolist()}
a, b = np.histogram(self._df['read_length'], 100)
summary['hist_read_length'] = {"Y": a.tolist(), "X": b.tolist()}
return summary
def histogram_sequence_lengths(self, logy=True):
"""Histogram sequence lengths
.. plot::
:include-source:
from sequana import sequana_data
from sequana import FastQC
filename = sequana_data("test.fastq", "testing")
qc = FastQC(filename)
qc.histogram_sequence_lengths()
"""
data = [len(x) for x in self.sequences]
bary, barx = np.histogram(data, bins=range(max(data)+1))
# get rid of zeros to avoid warnings
bx = [x for x,y in zip(barx, bary) if y!=0]
by = [y for x,y in zip(barx, bary) if y!=0]
if logy:
pylab.bar(bx, pylab.log10(by))
else:
pylab.bar(bx, by)
pylab.xlim([1,max(data)+1])
pylab.grid(True)
pylab.xlabel("position (bp)", fontsize=self.fontsize)
pylab.ylabel("Count (log scale)", fontsize=self.fontsize)
def run(self,
bins=50,
xmin=0,
xmax=30000,
step=1000,
burn=1000,
alpha=1,
output_filename=None):
# compute histogram of the input reads once for all to be used
# in the target_distribution method
self.bins = bins
self.Y, self.X = np.histogram(self.bam.df.read_length,
bins=bins,
normed=True)
lengths = self.bam_simul.df.read_length.values
self.tokeep = []
vec = []
x = self.bam.df.read_length.mean()
for i in range(self.bam_simul.df.shape[0]):
can = lengths[i]
aprob = min([
alpha,
self.target_distribution(can) / self.target_distribution(x)
])
#acceptance probability
u = pylab.uniform(0, 1)
if u < aprob:
x = can
vec.append(x)
self.tokeep.append(True)
else:
self.tokeep.append(False)
#plotting the results:
#theoretical curve
x = pylab.arange(xmin, xmax, step)
y = self.target_distribution(x)
pylab.subplot(211)
pylab.title('Metropolis-Hastings')
pylab.plot(vec)
pylab.subplot(212)
pylab.hist(vec[burn:], bins=bins, normed=1)
pylab.plot(x, y, 'r-')
pylab.ylabel('Frequency')
pylab.xlabel('x')
pylab.legend(('PDF', 'Samples'))
if output_filename is not None:
self.bam_simul.filter_bool(output_filename, self.tokeep)
def run(self, bins=50, xmin=0, xmax=30000, step=1000, burn=1000,alpha=1,output_filename=None):
# compute histogram of the input reads once for all to be used
# in the target_distribution method
self.bins = bins
self.Y, self.X = np.histogram(self.bam.df.read_length, bins=bins, density=True)
lengths = self.bam_simul.df.read_length.values
self.tokeep = []
vec = []
x = self.bam.df.read_length.mean()
for i in range(self.bam_simul.df.shape[0]):
can = lengths[i]
aprob = min([alpha,self.target_distribution(can)/self.target_distribution(x)])
#acceptance probability
u = pylab.uniform(0,1)
if u < aprob:
x = can
vec.append(x)
self.tokeep.append(True)
else:
self.tokeep.append(False)
#plotting the results:
#theoretical curve
x = pylab.arange(xmin, xmax, step)
y = self.target_distribution(x)
pylab.subplot(211)
pylab.title('Metropolis-Hastings')
pylab.plot(vec)
pylab.subplot(212)
pylab.hist(vec[burn:], bins=bins, density=1)
pylab.plot(x,y,'r-')
pylab.ylabel('Frequency')
pylab.xlabel('x')
pylab.legend(('PDF','Samples'))
if output_filename is not None:
self.bam_simul.filter_bool(output_filename, self.tokeep)