def hist_average_quality(self, fontsize=16, bins=None):
"""
bins is from 0 to 94
"""
hq_qv = [pylab.mean([ord(X)-33 for X in read['quality'].decode()])
for read in self.hq_sequence]
lq_qv = [pylab.mean([ord(X) -33 for X in read['quality'].decode()])
for read in self.lq_sequence]
if bins is None:
bins = range(0,94)
Y1, X = np.histogram(hq_qv, bins=bins)
Y2, X = np.histogram(lq_qv, bins=bins)
pylab.bar(X[1:], Y1, width=1, label="HQ")
pylab.bar(X[1:], Y2, bottom=Y1, width=1, label="LQ")
pylab.xlim([0.5, 93.5])
pylab.xlabel("Isoform average QV")
pylab.ylabel("# Isoform")
pylab.legend(fontsize=fontsize)
ax = pylab.twinx()
N = np.sum(Y1+Y2)
ax.plot(X, [N] + list(N-np.cumsum(Y1+Y2)), "k")
def hist_average_quality(self, fontsize=16, bins=None):
"""
bins is from 0 to 94
"""
hq_qv = [pylab.mean([ord(X)-33 for X in read['quality'].decode()])
for read in self.hq_sequence]
lq_qv = [pylab.mean([ord(X) -33 for X in read['quality'].decode()])
for read in self.lq_sequence]
if bins is None:
bins = range(0,94)
Y1, X = np.histogram(hq_qv, bins=bins)
Y2, X = np.histogram(lq_qv, bins=bins)
pylab.bar(X[1:], Y1, width=1, label="HQ")
pylab.bar(X[1:], Y2, bottom=Y1, width=1, label="LQ")
pylab.xlim([0.5, 93.5])
pylab.xlabel("Isoform average QV")
pylab.ylabel("# Isoform")
pylab.legend(fontsize=fontsize)
ax = pylab.twinx()
N = np.sum(Y1+Y2)
ax.plot(X, [N] + list(N-np.cumsum(Y1+Y2)), "k")
def barplot_count_ORF_CDS_by_frame(self,
alpha=0.5,
bins=40,
xlabel="Frame",
ylabel="#",
bar_width=0.35):
if self._ORF_pos is None:
self._find_ORF_CDS()
# number of ORF and CDS found by frame
frames = [-3, -2, -1, 1, 2, 3]
nb_res_ORF = []
nb_res_CDS = []
for fr in frames:
nb_res_ORF.append(self._ORF_pos[self._ORF_pos["frame"] == fr]
["len_ORF"].dropna().shape[0])
nb_res_CDS.append(self._ORF_pos[self._ORF_pos["frame"] == fr]
["len_CDS"].dropna().shape[0])
pylab.bar(np.array(frames) - (bar_width / 2),
nb_res_ORF,
bar_width,
alpha=alpha,
label="ORF N = %d" % sum(nb_res_ORF))
pylab.bar(np.array(frames) + (bar_width / 2),
nb_res_CDS,
bar_width,
alpha=alpha,
label="CDS N = %d" % sum(nb_res_CDS))
pylab.xlabel(xlabel)
pylab.ylabel(ylabel)
pylab.legend(loc=1)
pylab.title("Number of ORF and CDS by frame")
def plot_percentage_null_read_counts(self):
"""
Bars represent the percentage of null counts in each samples.
The dashed horizontal line represents the percentage of
feature counts being equal to zero across all samples.
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_percentage_null_read_counts()
"""
N = len(self.sample_names)
data = (self.df[self.sample_names]==0).sum()
data = data / len(self.df) * 100
all_null = (self.df[self.sample_names].sum(axis=1) == 0).sum()
pylab.clf()
pylab.bar(range(N), data)
pylab.axhline(all_null / len(self.df) * 100, lw=2, ls="--", color="k")
pylab.xticks(range(N), self.sample_names)
pylab.xlabel("Sample")
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 plot_count_per_sample(self, fontsize=12, sample_list=None):
""""Number of mapped reads per sample. Each color for each replicate
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_count_per_sample()
"""
sample_names = self.sample_names
N = len(sample_names)
dd = self.df[sample_names].sum()
pylab.clf()
colors = []
for sample in self.sample_names:
colors.append(self.colors[self.get_cond_from_sample(sample)])
pylab.bar(range(N), (dd/1000000).values,
color=colors, alpha=1,
zorder=10, lw=1, ec="k", width=0.9)
pylab.xlabel("Samples", fontsize=fontsize)
pylab.ylabel("Total read count (millions)", fontsize=fontsize)
pylab.grid(True, zorder=0)
pylab.title("Total read count per sample", fontsize=fontsize)
pylab.xticks(range(N), self.sample_names)
def hist_ZMW_subreads(self,
alpha=0.5,
hold=False,
fontsize=12,
grid=True,
xlabel="Number of ZMW passes",
logy=True,
ylabel="#",
label="",
title="Number of ZMW passes"):
"""Plot histogram of number of reads per ZMW (number of passes)
:param float alpha: transparency of the histograms
:param bool hold:
:param int fontsize:
:param bool grid:
:param str xlabel:
:param str ylabel:
:param bool logy: use log scale on the y axis (default to True)
:param str label: label of the histogram (for the legend)
:param str title:
.. plot::
:include-source:
from sequana.pacbio import BAMPacbio
from sequana import sequana_data
b = BAMPacbio(sequana_data("test_pacbio_subreads.bam"))
b.hist_ZMW_subreads()
"""
if self._nb_pass is None:
self._get_ZMW_passes()
max_nb_pass = max(self._nb_pass.keys())
k = range(1, max_nb_pass + 1)
val = [self._nb_pass[i] for i in k]
# histogram nb passes
if hold is False:
pylab.clf()
pylab.bar(k, val, alpha=alpha, label=label, log=logy)
if len(k) < 5:
pylab.xticks(range(6), range(6))
pylab.xlabel(xlabel, fontsize=fontsize)
pylab.ylabel(ylabel, fontsize=fontsize)
pylab.title(title, fontsize=fontsize)
if grid is True:
pylab.grid(True)
def bar_plot_contigs_length(self):
# show length of N contigs as compare to length of the reference
fref = FastA(self.reference)
Nref = len(fref.sequences)
N = len(self.fasta)
pylab.clf()
pylab.bar(range(0, N, int(pylab.ceil(N / Nref))),
sorted(fref.lengths),
width=Nref / 1.1,
label="Plasmodium chromosomes")
pylab.bar(range(0, N),
sorted(self.fasta.lengths),
width=1,
label="canu {} contigs".format(N))
pylab.legend()
def hist_average_quality(self, fontsize=16):
hq_qv = [
mean([phred.ascii_to_quality(X) for X in read['quality'].decode()])
for read in iso.hq_sequence
]
lq_qv = [
mean([phred.ascii_to_quality(X) for X in read['quality'].decode()])
for read in iso.lq_sequence
]
Y1, X = numpy.histogram(hq_qv, bins=range(0, 94))
Y2, X = numpy.histogram(lq_qv, bins=range(0, 94))
pylab.bar(X[1:], Y1, width=1, label="HQ")
pylab.bar(X[1:], Y2, bottom=Y1, width=1, label="LQ")
pylab.xlabel("Isoform average QV")
pylab.ylabel("# Isoform")
pylab.legend(fontsize=fontsize)
def barplot_count_ORF_CDS_by_frame(self, alpha=0.5, bins=40,
xlabel="Frame", ylabel="#", bar_width=0.35):
if self._ORF_pos is None:
self._find_ORF_CDS()
# number of ORF and CDS found by frame
frames = [-3, -2, -1, 1, 2, 3]
nb_res_ORF = []
nb_res_CDS = []
for fr in frames:
nb_res_ORF.append(self._ORF_pos[self._ORF_pos["frame"] == fr]["len_ORF"].dropna().shape[0])
nb_res_CDS.append(self._ORF_pos[self._ORF_pos["frame"] == fr]["len_CDS"].dropna().shape[0])
pylab.bar(np.array(frames)-(bar_width/2), nb_res_ORF, bar_width, alpha=alpha, label="ORF N = %d" %sum(nb_res_ORF))
pylab.bar(np.array(frames)+(bar_width/2), nb_res_CDS, bar_width, alpha=alpha, label="CDS N = %d" %sum(nb_res_CDS))
pylab.xlabel(xlabel)
pylab.ylabel(ylabel)
pylab.legend(loc=1)
pylab.title("Number of ORF and CDS by frame")
def barplot(self, filename="lane{}_status.png", lanes=None):
df = self.get_data_reads()
if lanes is None:
lanes = df.lane.unique()
for lane in lanes:
pylab.clf()
query = "lane==@lane and name!='Undetermined'"
counts = df.query(query)['count']
total = counts.sum()
L = len(counts)
query = "lane==@lane and name=='Undetermined'"
under = df.query(query)['count'].sum()
if total > 0:
pylab.bar(range(L), counts, color="b", label="reads")
if total == 0:
color = "red"
else:
if 100 * under / total < 20:
color = "green"
elif 100 * under / total < 50:
color = "orange"
else:
color = "red"
pylab.bar(range(L, L + 1),
under,
color=color,
label="undetermined")
pylab.xticks([])
pylab.ylabel("Number of reads")
try:
pylab.legend(loc="lower left")
except:
pass
pylab.title("Lane {}".format(lane))
pylab.savefig(filename.format(lane), dpi=200)
def plot_count_per_sample(self, fontsize=12, sample_list=None):
""""Number of mapped reads per sample. Each color for each replicate
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_count_per_sample()
"""
sample_names = [x for x in self.df.columns if x.startswith("norm")]
sample_names = [x.replace("norm.", "") for x in sample_names]
N = len(sample_names)
dd = self.df[sample_names].sum()
pylab.clf()
pylab.bar(range(N), (dd/1000000).values, color=['r']*3+['b']*3, alpha=1)
pylab.xlabel("Samples", fontsize=fontsize)
pylab.ylabel("Total read count (millions)", fontsize=fontsize)
pylab.grid(True)
pylab.title("Total read count per sample", fontsize=fontsize)
def plot_percentage_null_read_counts(self):
"""
Bars represent the percentage of null counts in each samples.
The dashed horizontal line represents the percentage of
feature counts being equal to zero across all samples.
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_percentage_null_read_counts()
"""
N = len(self.sample_names)
data = (self.df[self.sample_names]==0).sum()
data = data / len(self.df) * 100
all_null = (self.df[self.sample_names].sum(axis=1) == 0).sum()
colors = []
for sample in self.sample_names:
colors.append(self.colors[self.get_cond_from_sample(sample)])
pylab.clf()
pylab.bar(range(N), data,
color=colors, alpha=1,
zorder=10, lw=1, ec="k", width=0.9)
pylab.axhline(all_null / len(self.df) * 100, lw=2, ls="--", color="k",
zorder=20)
pylab.xticks(range(N), self.sample_names)
pylab.xlabel("Sample")
pylab.ylabel("Proportion of null counts (%)")
pylab.grid(True, zorder=0)
def plot_count_per_sample(self, fontsize=12, rotation=45):
"""Number of mapped and annotated reads (i.e. counts) per sample. Each color
for each replicate
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_count_per_sample()
"""
pylab.clf()
df = self.counts_raw.sum().rename("total_counts")
df = pd.concat([self.design_df, df], axis=1)
pylab.bar(
df.index,
df.total_counts / 1000000,
color=df.group_color,
lw=1,
zorder=10,
ec="k",
width=0.9,
)
pylab.xlabel("Samples", fontsize=fontsize)
pylab.ylabel("reads (M)", fontsize=fontsize)
pylab.grid(True, zorder=0)
pylab.title("Total read count per sample", fontsize=fontsize)
pylab.xticks(rotation=rotation, ha="right")
# pylab.xticks(range(N), self.sample_names)
try:
pylab.tight_layout()
except:
pass
def plot_percentage_null_read_counts(self):
"""Bars represent the percentage of null counts in each samples. The dashed
horizontal line represents the percentage of feature counts being equal
to zero across all samples
.. plot::
:include-source:
from sequana.rnadiff import RNADiffResults
from sequana import sequana_data
r = RNADiffResults(sequana_data("rnadiff/rnadiff_onecond_1"))
r.plot_percentage_null_read_counts()
"""
pylab.clf()
# how many null counts ?
df = (self.counts_raw == 0).sum() / self.counts_raw.shape[0] * 100
df = df.rename("percent_null")
df = pd.concat([self.design_df, df], axis=1)
pylab.bar(df.index,
df.percent_null,
color=df.group_color,
ec="k",
lw=1,
zorder=10)
all_null = (self.counts_raw
== 0).all(axis=1).sum() / self.counts_raw.shape[0]
pylab.axhline(all_null, ls="--", color="black", alpha=0.5)
pylab.xticks(rotation=45, ha="right")
pylab.ylabel("Proportion of null counts (%)")
pylab.grid(True, zorder=0)
pylab.tight_layout()
