def plot(self,
color_line='r',
bgcolor='grey',
color='yellow',
lw=4,
hold=False,
ax=None):
xmax = self.xmax + 1
if ax:
pylab.sca(ax)
pylab.fill_between([0, xmax], [0, 0], [20, 20], color='red', alpha=0.3)
pylab.fill_between([0, xmax], [20, 20], [30, 30],
color='orange',
alpha=0.3)
pylab.fill_between([0, xmax], [30, 30], [41, 41],
color='green',
alpha=0.3)
if self.X is None:
X = range(1, self.xmax + 1)
pylab.fill_between(X,
self.df.mean() + self.df.std(),
self.df.mean() - self.df.std(),
color=color,
interpolate=False)
pylab.plot(X, self.df.mean(), color=color_line, lw=lw)
pylab.ylim([0, 41])
pylab.xlim([0, self.xmax + 1])
pylab.title("Quality scores across all bases")
pylab.xlabel("Position in read (bp)")
pylab.ylabel("Quality")
pylab.grid(axis='x')
def boxplot_quality(self, color_line='r', bgcolor='grey', color='yellow', lw=4,
hold=False, ax=None):
quality = self.df[[str(x) for x in range(42)]] # not sure why we have phred score from 0 to 41
N = self.metadata['ReadNum']
proba = quality / N
self.xmax = 150
xmax = self.xmax + 1
if ax:
pylab.sca(ax) # pragma no cover
pylab.fill_between([0,xmax], [0,0], [20,20], color='red', alpha=0.3)
pylab.fill_between([0,xmax], [20,20], [30,30], color='orange', alpha=0.3)
pylab.fill_between([0,xmax], [30,30], [41,41], color='green', alpha=0.3)
X = []
Q = []
S = []
for pos in range(1, 151):
qualities = [((int(k)+1)*v) for k,v in quality.loc[pos].items()]
mean_quality = sum(qualities) / N
X.append(pos)
Q.append(mean_quality)
proba = quality.loc[pos] / N
std = pylab.sqrt(sum([(x-mean_quality)**2 * y for x, y in zip(range(42), proba)]))
S.append(std)
print(len(X))
print(len(Q))
print(len(S))
Q = np.array(Q)
X = np.array(X)
S = np.array(S)
pylab.fill_between(X, Q+S, Q-S,
color=color, interpolate=False)
pylab.plot(X, Q, color=color_line, lw=lw)
pylab.ylim([0, 41])
pylab.xlim([0, self.xmax+1])
pylab.title("Quality scores across all bases")
pylab.xlabel("Position in read (bp)")
pylab.ylabel("Quality")
pylab.grid(axis='x')
def plot_sequence_quality(self, max_score=40, ax=None):
ymax = max_score + 1
xmax = 0
for sample in self.fastqc_data.keys():
if "per_sequence_quality_scores" in self.fastqc_data[sample]:
data = {
self._avg_bp_from_range(d['base']): d['mean']
for d in self.fastqc_data[sample]
['per_base_sequence_quality']
}
df = pd.Series(data)
df.plot(color="k", alpha=0.5)
if df.max() > ymax:
ymax = df.max()
if df.index.max() > xmax:
xmax = df.index.max()
if ax:
pylab.sca(ax)
pylab.fill_between([0, xmax], [0, 0], [20, 20], color='red', alpha=0.4)
pylab.fill_between([0, xmax], [20, 20], [30, 30],
color='orange',
alpha=0.4)
pylab.fill_between([0, xmax], [30, 30], [ymax, ymax],
color='green',
alpha=0.4)
X = range(1, xmax + 1)
pylab.ylim([0, ymax])
if xmax != 0:
pylab.xlim([0, xmax])
pylab.title("Quality scores across all bases")
pylab.xlabel("Position in read (bp)")
pylab.ylabel("Phred Score", fontsize=12)
pylab.grid(axis='x')