def atacseq_qualimap_plot_coverage_per_contig(df, **kwargs):
p = points(
df=df,
x="chrlen_percent",
y="mapped_bases_percent",
glyph="circle",
return_source=True,
legend="top_right",
tools=DEFAULT_TOOLS,
size=6,
alpha=0.9,
color="SM",
plot_height=600,
plot_width=800,
)
p.xaxis.axis_label = "chrlen (% of genome)"
p.yaxis.axis_label = "mapped reads (% of total)"
tooltips(p, HoverTool, [("Sample", "@SM"), ("Chromosome", "@chr")])
return p
def atacseq_qualimap_plot_coverage_per_contig(df, **kwargs):
"""Plot qualimap coverage per contig.
Args:
df(:class:`~pandas.DataFrame`): data frame holding summary of qualimap results. The summary is provided by :meth:`snakemakelib.odo.qualimap.resource_genome_results`.
kwargs(dict): keyword arguments
Returns:
:class:`bokeh.plotting.figure`: bokeh scatter plot
Examples:
.. bokeh-plot::
:source-position: above
import pandas as pd
from bokeh.plotting import show
from snakemakelib_workflows.atacseq.app import atacseq_qualimap_plot_coverage_per_contig
df = pd.DataFrame([['S1', 'chr1', 4e6, 8e6, 2, 5, 80, 40],
['S1', 'chr2', 1e6, 12e6, 12, 20, 20, 60],
['S2', 'chr1', 4e6, 12e6, 3, 5, 80, 60],
['S2', 'chr2', 1e6, 8e6, 8, 20, 20, 40]],
columns=['SM', 'chr','chrlen', 'mapped_bases', 'mean_coverage', 'sd', 'chrlen_percent','mapped_bases_percent'])
p = atacseq_qualimap_plot_coverage_per_contig(df)
show(p)
"""
p = points(df=df, x="chrlen_percent",
y="mapped_bases_percent", glyph="circle",
return_source=True, legend="top_right",
tools=DEFAULT_TOOLS, size=6, alpha=.9,
color="SM", plot_height=600, plot_width=800)
p.xaxis.axis_label = "chrlen (% of genome)"
p.yaxis.axis_label = "mapped reads (% of total)"
tooltips(p, HoverTool, [('Sample', '@SM'),
('Chromosome', '@chr')])
return p
def plot_pca(pcaobjfile, pca_results_file=None, metadata=None, taptool_url=None, **kwargs):
"""Make PCA plot
Args:
pcaobjfile (str): file name containing pickled pca object
pca_results_file (str): pca results file
metadata (str): metadata file name
taptool_url (str): url prefix that is attached to taptool; typically a link to ensembl
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
"""
with open(pcaobjfile, 'rb') as fh:
pcaobj = pickle.load(fh)
md = None
if not metadata is None:
md = pd.read_csv(metadata, index_col=0)
df_pca = pd.read_csv(pca_results_file, index_col=kwargs.get('index_col', "SM"))
df_pca['color'] = [kwargs.get('color', 'red')] * df_pca.shape[0]
df_pca['x'] = df_pca['0']
df_pca['y'] = df_pca['1']
df_pca['size'] = [kwargs.get('size', 10)] * df_pca.shape[0]
pca_source = ColumnDataSource(df_pca)
cmap = colorbrewer(datalen = df_pca.shape[0])
callback = CustomJS(args=dict(source=pca_source),
code="""pca_callback(source, cb_obj, "SM");""")
xcallback = CustomJS(args=dict(source=pca_source),
code="""pca_component(source, cb_obj, "x");""")
ycallback = CustomJS(args=dict(source=pca_source),
code="""pca_component(source, cb_obj, "y");""")
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) + ["TPM", "FPKM"]]
else:
toggle_buttons = []
pca_components = sorted([int(x) + 1 for x in pca_source.column_names if re.match("\d+", x)])
menulist = ["{} ({:.2f}%)".format(x, 100.0 * p) for x, p in zip(pca_components, pcaobj.explained_variance_ratio_)]
component_x = Select(title = "PCA component x", options = menulist, value=menulist[0],
callback=xcallback)
component_y = Select(title = "PCA component y", options = menulist, value=menulist[1],
callback=ycallback)
# Make the pca plot
kwargs = {'plot_width': 400, 'plot_height': 400,
'title_text_font_size': "12pt",
'title': "Principal component analysis",
'tools': TOOLS,
'x_axis_label_text_font_size': '10pt',
'x_major_label_orientation': np.pi/3,
'y_axis_label_text_font_size': '10pt',
'y_major_label_orientation': np.pi/3,
}
fig = points('x', 'y', df=pca_source, color='color', size='size', alpha=0.7, **kwargs)
tooltiplist = [("sample", "@SM")] if "SM" in pca_source.column_names else []
if not md is None:
tooltiplist = tooltiplist + [(str(x), "@{}".format(x)) for x
in md.columns] + \
[("Detected genes (TPM)", "@TPM"), ("Detected genes (FPKM)", "@FPKM")]
tooltips(fig, HoverTool, tooltiplist)
# Loadings
loadings = pd.DataFrame(pcaobj.components_).T
loadings.columns = [str(x) for x in loadings.columns]
loadings['x'] = loadings['0']
loadings['y'] = loadings['1']
try:
loadings["gene_id"] = pcaobj.features
except:
smllogger.warn("failed to set gene_id")
raise
try:
loadings["gene_name"] = [pcaobj.labels[x] for x in loadings["gene_id"]]
except:
smllogger.warn("failed to set gene_name")
raise
loadings_source = ColumnDataSource(loadings)
kwargs.update({'title': "Loadings"})
loadings_fig = points(x='x', y='y', df=loadings_source,
**kwargs)
tooltips(loadings_fig, HoverTool, [('gene_id', '@gene_id'), ('gene_name', '@gene_name')])
x_loadings_callback = CustomJS(args=dict(source=loadings_source),
code="""pca_loadings(source, cb_obj, "x");""")
y_loadings_callback = CustomJS(args=dict(source=loadings_source),
code="""pca_loadings(source, cb_obj, "y");""")
menulist = ["{} ({:.2f}%)".format(x, 100.0 * p) for x, p in zip(pca_components, pcaobj.explained_variance_ratio_)]
loadings_component_x = Select(title = "PCA loading x", options = menulist, value=menulist[0],
callback=x_loadings_callback)
loadings_component_y = Select(title = "PCA loading y", options = menulist, value=menulist[1],
callback=y_loadings_callback)
# Add taptool url if present
if taptool_url:
loadings_fig.add_tools(TapTool(callback=OpenURL(url=taptool_url)))
# Detected genes, FPKM and TPM
kwargs.update({'title': 'Number of detected genes',
'xlabel': "Sample",
'ylabel': "Detected genes",
'x_range': list(pca_source.data["SM"])})
n_genes_fig = dotplot(df=pca_source, x="SM", y="TPM", **kwargs)
tooltips(n_genes_fig, HoverTool, [('sample', '@SM'),
('# genes (TPM)', '@TPM'),
('# genes (FPKM)', '@FPKM')])
buttons = toggle_buttons + [component_x, component_y] + [loadings_component_x, loadings_component_y]
return {'pca' : vform(*(buttons + [gridplot([[fig, loadings_fig, n_genes_fig]])]))}
