def make_qualimap_plots(qmglobals=None, coverage_per_contig=None):
"""Make qualimap summary plots"""
retval = {
"fig": {"coverage_per_contig": None, "globals": None},
"file": {"coverage_per_contig": coverage_per_contig, "globals": qmglobals},
"uri": {"coverage_per_contig": data_uri(coverage_per_contig), "globals": data_uri(qmglobals)},
}
# Globals
if qmglobals is not None:
df_all = pd.read_csv(qmglobals)
df_all["Sample"] = df_all["Sample"].astype("str")
fig = figure(
y_range=[0, max(df_all["number of reads"])],
title="Mapping summary",
title_text_font_size="12pt",
plot_width=400,
plot_height=400,
x_range=sorted(list(set(df_all["Sample"]))),
)
mdotplot(
fig,
x="Sample",
size=10,
df=df_all,
alpha=0.5,
y=["number of reads", "number of mapped reads", "number of duplicated reads", "number of unique reads"],
)
xaxis(fig, axis_label="sample", major_label_orientation=np.pi / 3, axis_label_text_font_size="10pt")
yaxis(fig, axis_label="count", major_label_orientation=1, axis_label_text_font_size="10pt")
retval["fig"]["globals"] = fig
# Coverage per contig
if coverage_per_contig is not None:
df_all = pd.read_csv(coverage_per_contig, index_col=0)
df_all["Sample"] = df_all["Sample"].astype("str")
fig = figure(width=300, height=300)
points(
fig, x="chrlen_percent", y="mapped_bases_percent", df=df_all, glyph="text", text="chr", text_font_size="8pt"
)
main(fig, title_text_font_size="8pt")
xaxis(fig, axis_label="Chromosome length of total (%)", axis_label_text_font_size="8pt")
yaxis(fig, axis_label="Mapped bases of total (%)", axis_label_text_font_size="8pt")
gp = facet_grid(
fig,
x="chrlen_percent",
y="mapped_bases_percent",
df=df_all,
groups=["Sample"],
width=300,
height=300,
share_x_range=True,
share_y_range=True,
title_text_font_size="12pt",
)
for fig in [item for sublist in gp.children for item in sublist]:
abline(fig, x="chrlen_percent", y="mapped_bases_percent", df=df_all, slope=1)
retval["fig"]["coverage_per_contig"] = gp
return retval
def test_style(self):
points(self._fig,
"x",
"y",
self._data,
line_color='gray',
size=20,
color="red")
def mpoints(fig,
x,
y,
df=None,
source=None,
glyph='circle',
color=False,
legend=False,
**kwargs):
"""points: add points from multiple columns to a figure
Args:
fig (:py:class:`~bokeh.plotting.Plot`): bokeh Plot object
x (str): string for x component
y (str, list): string or list of strings for y component
df (:py:class:`~pandas.DataFrame`): pandas DataFram
source (:py:class:`~bokeh.models.sources.ColumnDataSource`): bokeh sources.ColumnDataSource object
glyph (str): glyph character to use
color (bool): set color
legend (bool): set legend
kwargs: keyword arguments to pass to glyph drawing function
Examples:
.. bokeh-plot::
:source-position: above
import pandas as pd
from bokeh.plotting import figure, show, hplot
from bokehutils.mgeom import mpoints
df = pd.DataFrame([[1,2,3], [2,5,2], [3,9,6]], columns=["x", "y", "z"])
f = figure(title="Points", plot_width=400, plot_height=400)
mpoints(f, "x", ["y", "z"], df, size=10, line_color="black")
show(f)
"""
logger.debug("Adding mpoints to figure {}".format(fig))
for i in range(len(y)):
points(fig=fig,
x=x,
y=y[i],
df=df,
source=source,
glyph=glyph,
**kwargs)
if color:
# Add color here
# color = brewer["PiYG"][min(max(3, len(y)), 10)]
pass
if legend:
# Add legend here via legend function
pass
def mpoints(fig, x, y,
df=None, source=None, glyph='circle', color=False,
legend=False, **kwargs):
"""points: add points from multiple columns to a figure
Args:
fig (:py:class:`~bokeh.plotting.Plot`): bokeh Plot object
x (str): string for x component
y (str, list): string or list of strings for y component
df (:py:class:`~pandas.DataFrame`): pandas DataFram
source (:py:class:`~bokeh.models.sources.ColumnDataSource`): bokeh sources.ColumnDataSource object
glyph (str): glyph character to use
color (bool): set color
legend (bool): set legend
kwargs: keyword arguments to pass to glyph drawing function
Examples:
.. bokeh-plot::
:source-position: above
import pandas as pd
from bokeh.plotting import figure, show, hplot
from bokehutils.mgeom import mpoints
df = pd.DataFrame([[1,2,3], [2,5,2], [3,9,6]], columns=["x", "y", "z"])
f = figure(title="Points", plot_width=400, plot_height=400)
mpoints(f, "x", ["y", "z"], df, size=10, line_color="black")
show(f)
"""
logger.debug("Adding mpoints to figure {}".format(fig))
for i in range(len(y)):
points(fig=fig, x=x, y=y[i], df=df, source=source,
glyph=glyph, **kwargs)
if color:
# Add color here
# color = brewer["PiYG"][min(max(3, len(y)), 10)]
pass
if legend:
# Add legend here via legend function
pass
def test_legend(self):
points(self._fig, "x", "y", self._data)
legend(self._fig, orientation="bottom_left")
def test_axis(self):
points(self._fig, "x", "y", self._data)
points(self._fig, "y", "x", self._data, color="red")
xaxis(self._fig, axis_label="x", major_label_orientation=np.pi / 3)
def test_axis_no_splat(self):
points(self._fig, "x", "y", self._data)
xaxis(self._fig, formatter=NumeralTickFormatter(format="0.0%"))
def test_axis_wrong_args(self):
points(self._fig, "x", "y", self._data)
xaxis(self._fig, foo="bar")
def test_style(self):
points(self._fig, "x", "y", self._data, line_color='gray', size=20, color="red")
def test_init(self):
points(self._fig, "x", "y", self._data)
def test_init(self):
points(self._fig, "x", "y", self._data)
def scrnaseq_pca_plots(pca_results_file=None, metadata=None, pcacomp=(1,2), pcaobjfile=None):
"""Make PCA QC plots for scrnaseq workflow
Args:
pca_results_file (str): pca results file
metadata (str): metadata file name
pcacomp (int): tuple of ints corresponding to components to draw
pcaobjfile (str): file name containing pickled pca object
Returns:
dict: dictionary with keys 'fig' pointing to a (:py:class:`~bokeh.models.GridPlot`) Bokeh GridPlot object and key 'table' pointing to a (:py:class:`~bokeh.widgets.DataTable`) DataTable
"""
if not metadata is None:
md = pd.read_csv(metadata, index_col=0)
if not pcaobjfile is None:
with open(pcaobjfile, 'rb') as fh:
pcaobj = pickle.load(fh)
df_pca = pd.read_csv(pca_results_file, index_col="sample")
df_pca['color'] = ['red'] * df_pca.shape[0]
df_pca['x'] = df_pca['0']
df_pca['y'] = df_pca['1']
source = ColumnDataSource(df_pca)
TOOLS = "pan,wheel_zoom,box_zoom,box_select,resize,reset,save,hover"
# Add radio button group
cmap = colorbrewer(datalen = df_pca.shape[0], palette="RdYlBu")
callback_rbg = CustomJS(args=dict(source=source), code="""
var data = source.get('data');
var active = cb_obj.get('active')
var label = cb_obj.get('label')[active]
var RdYlBu = {
3: ["#fc8d59","#ffffbf","#91bfdb"],
4: ["#d7191c","#fdae61","#abd9e9","#2c7bb6"],
5: ["#d7191c","#fdae61","#ffffbf","#abd9e9","#2c7bb6"],
6: ["#d73027","#fc8d59","#fee090","#e0f3f8","#91bfdb","#4575b4"],
7: ["#d73027","#fc8d59","#fee090","#ffffbf","#e0f3f8","#91bfdb","#4575b4"],
8: ["#d73027","#f46d43","#fdae61","#fee090","#e0f3f8","#abd9e9","#74add1","#4575b4"],
9: ["#d73027","#f46d43","#fdae61","#fee090","#ffffbf","#e0f3f8","#abd9e9","#74add1","#4575b4"],
10: ["#a50026","#d73027","#f46d43","#fdae61","#fee090","#e0f3f8","#abd9e9","#74add1","#4575b4","#313695"],
11: ["#a50026","#d73027","#f46d43","#fdae61","#fee090","#ffffbf","#e0f3f8","#abd9e9","#74add1","#4575b4","#313695"]};
var colormap = {};
var j = 0;
for (i = 0; i < data['sample'].length; i++) {
if (data[label][i] in colormap) {
} else {
colormap[data[label][i]] = j;
j++;
}
}
var nfac = Object.keys(colormap).length;
if (nfac > 11) {
nfac = 11;
}
if (nfac < 3) {
nfac = 3;
}
var colors = RdYlBu[nfac];
for (i = 0; i < data[label].length; i++) {
data['color'][i] = colors[colormap[data[label][i]]]
}
source.trigger('change');
""")
callback = CustomJS(args=dict(source=source), code="""
var data = source.get('data');
var active = cb_obj.get('active');
var label = cb_obj.get('label');
var RdYlBu = {
3: ["#fc8d59","#ffffbf","#91bfdb"],
4: ["#d7191c","#fdae61","#abd9e9","#2c7bb6"],
5: ["#d7191c","#fdae61","#ffffbf","#abd9e9","#2c7bb6"],
6: ["#d73027","#fc8d59","#fee090","#e0f3f8","#91bfdb","#4575b4"],
7: ["#d73027","#fc8d59","#fee090","#ffffbf","#e0f3f8","#91bfdb","#4575b4"],
8: ["#d73027","#f46d43","#fdae61","#fee090","#e0f3f8","#abd9e9","#74add1","#4575b4"],
9: ["#d73027","#f46d43","#fdae61","#fee090","#ffffbf","#e0f3f8","#abd9e9","#74add1","#4575b4"],
10: ["#a50026","#d73027","#f46d43","#fdae61","#fee090","#e0f3f8","#abd9e9","#74add1","#4575b4","#313695"],
11: ["#a50026","#d73027","#f46d43","#fdae61","#fee090","#ffffbf","#e0f3f8","#abd9e9","#74add1","#4575b4","#313695"]};
var colormap = {};
if (!active) {
var j = 0;
for (i = 0; i < data['sample'].length; i++) {
if (data[label][i] in colormap) {
} else {
colormap[data[label][i]] = j;
j++;
}
}
var nfac = Object.keys(colormap).length;
if (nfac > 11) {
nfac = 11;
}
if (nfac < 3) {
nfac = 3;
}
var colors = RdYlBu[nfac];
for (i = 0; i < data[label].length; i++) {
data['color'][i] = colors[colormap[data[label][i]]]
}
source.trigger('change');
}
""")
if not md is None:
# Waiting for callbacks to be implemented upstream in bokeh
# rbg = RadioButtonGroup(labels=list(md.columns),
# callback=callback)
toggle_buttons = [Toggle(label=x, callback=callback) for x in list(md.columns)]
else:
toggle_buttons = []
# rbg = RadioButtonGroup()
# PC components
xcallback = CustomJS(args=dict(source=source), code="""
var data = source.get('data');
var active = cb_obj.get('active')
var value = cb_obj.get('value')
x = data['x']
for (i = 0; i < x.length; i++) {
x[i] = data[value][i]
data['sample'][i] = value
data['FileID'][i] = active
}
source.trigger('change');
""")
ycallback = CustomJS(args=dict(source=source), code="""
var data = source.get('data');
var value = cb_obj.get('value')
y = data['y']
for (i = 0; i < y.length; i++) {
y[i] = data[value][i]
}
source.trigger('change');
""")
pca_components = sorted([int(x) + 1 for x in source.column_names if re.match("\d+", x)])
menulist = [(str(x), str(x)) for x in pca_components]
component_x = Dropdown(label = "PCA component x", menu = menulist, default_value="1",
callback=xcallback)
component_y = Dropdown(label = "PCA component y", menu = menulist, default_value="2",
callback=ycallback)
# Make the pca plot
kwfig = {'plot_width': 400, 'plot_height': 400,
'title_text_font_size': "12pt"}
p1 = figure(title="Principal component analysis",
tools=TOOLS, **kwfig)
points(p1, 'x', 'y', source=source, color='color', size=10,
alpha=.7)
kwxaxis = {'axis_label': "Component {} ({:.2f}%)".format(
pcacomp[0], 100.0 * pcaobj.explained_variance_ratio_[pcacomp[0] - 1]),
'axis_label_text_font_size': '10pt',
'major_label_orientation': np.pi/3}
kwyaxis = {'axis_label': "Component {} ({:.2f}%)".format(
pcacomp[1], 100.0 * pcaobj.explained_variance_ratio_[pcacomp[1] - 1]),
'axis_label_text_font_size': '10pt',
'major_label_orientation': np.pi/3}
xaxis(p1, **kwxaxis)
yaxis(p1, **kwyaxis)
tooltiplist = [("sample", "@sample")] if "sample" in source.column_names else []
if not md is None:
tooltiplist = tooltiplist + [(str(x), "@{}".format(x)) for x
in md.columns]
tooltips(p1, HoverTool, tooltiplist)
# Detected genes, FPKM and TPM
p2 = figure(title="Number of detected genes",
x_range=list(df_pca.index), tools=TOOLS,
**kwfig)
kwxaxis.update({'axis_label': "Sample"})
kwyaxis.update({'axis_label': "Detected genes"})
dotplot(p2, "sample", "FPKM", source=source)
xaxis(p2, **kwxaxis)
yaxis(p2, **kwyaxis)
tooltips(p2, HoverTool, [('sample', '@sample'),
('# genes (FPKM)', '@FPKM')])
return {'fig':vform(*(toggle_buttons + [gridplot([[p1, p2]])]))}
def test_legend(self):
points(self._fig, "x", "y", self._data)
legend(self._fig, orientation="bottom_left")
def test_axis(self):
points(self._fig, "x", "y", self._data)
points(self._fig, "y", "x", self._data, color="red")
xaxis(self._fig, axis_label="x", major_label_orientation=np.pi/3)
def test_axis_no_splat(self):
points(self._fig, "x", "y", self._data)
xaxis(self._fig, formatter=NumeralTickFormatter(format="0.0%"))
def test_axis_wrong_args(self):
points(self._fig, "x", "y", self._data)
xaxis(self._fig, foo="bar")
