def dotplot(df, cutoff=0.05, figsize=(3.5, 6), top_term=10, scale=1):
"""Visualize enrichr results.
:param df: GSEApy DataFrame results.
:param cutoff: p-adjust cut-off.
:param top_term: number of enriched terms to show.
:param scale: dotplot point size scale.
:return: a dotplot for enrichr terms.
"""
if 'fdr' in df.columns:
#gsea results
df.rename(columns={
'fdr': 'Adjusted P-value',
}, inplace=True)
df['hits_ratio'] = df['matched_size'] / df['gene_set_size']
else:
#enrichr results
df['Count'] = df['Overlap'].str.split("/").str[0].astype(int)
df['Background'] = df['Overlap'].str.split("/").str[1].astype(int)
df['hits_ratio'] = df['Count'] / df['Background']
# pvalue cut off
df = df[df['Adjusted P-value'] <= cutoff]
if len(df) < 1:
logging.warning("Warning: No enrich terms when cuttoff = %s" % cutoff)
return None
#sorting the dataframe for better visualization
df = df.sort_values(by='Adjusted P-value', ascending=False)
df = df.head(top_term)
# x axis values
padj = df['Adjusted P-value']
combined_score = df['Combined Score'].round().astype('int')
x = -padj.apply(np.log10)
# y axis index and values
y = [i for i in range(0, len(df))]
labels = df.Term.values
area = np.pi * (df['Count'] * scale)**2
#creat scatter plot
if hasattr(sys, 'ps1'):
#working inside python console, show figure
fig, ax = plt.subplots(figsize=figsize)
else:
#If working on commandline, don't show figure
fig = Figure(figsize=figsize)
canvas = FigureCanvas(fig)
ax = fig.add_subplot(111)
vmin = np.percentile(combined_score.min(), 2)
vmax = np.percentile(combined_score.max(), 98)
sc = ax.scatter(x=x,
y=y,
s=area,
edgecolors='face',
c=combined_score,
cmap=plt.cm.RdBu,
vmin=vmin,
vmax=vmax)
ax.set_xlabel("-log$_{10}$(Adjust P-value)", fontsize=16)
ax.yaxis.set_major_locator(plt.FixedLocator(y))
ax.yaxis.set_major_formatter(plt.FixedFormatter(labels))
ax.set_yticklabels(labels, fontsize=16)
#ax.set_ylim([-1, len(df)])
ax.grid()
#colorbar
cax = fig.add_axes([0.93, 0.20, 0.07, 0.22])
cbar = fig.colorbar(
sc,
cax=cax,
)
cbar.ax.tick_params(right='off')
cbar.ax.set_title('Com-\nscore', loc='left', fontsize=12)
#for terms less than 3
if len(df) >= 3:
# find the index of the closest value to the median
idx = [
area.argmax(),
np.abs(area - area.mean()).argmin(),
area.argmin()
]
idx = unique(idx)
x2 = [0] * len(idx)
else:
x2 = [0] * len(df)
idx = df.index
#scale of dots
ax2 = fig.add_axes([0.93, 0.55, 0.09, 0.06 * len(idx)])
#s=area[idx]
l1 = ax2.scatter([], [], s=10, edgecolors='none')
l2 = ax2.scatter([], [], s=50, edgecolors='none')
l3 = ax2.scatter([], [], s=100, edgecolors='none')
labels = df['Count'][idx]
leg = ax.legend([l1, l2, l3],
labels,
nrow=3,
frameon=True,
fontsize=12,
handlelength=2,
loc=8,
borderpad=1.8,
handletextpad=1,
title='Gene\nRatio',
scatterpoints=1)
#canvas.print_figure('test', bbox_inches='tight')
return fig
def dotplot(df,
column='Adjusted P-value',
title='',
cutoff=0.05,
top_term=10,
sizes=None,
norm=None,
legend=True,
figsize=(6, 5.5),
cmap='RdBu_r',
ofname=None,
**kwargs):
"""Visualize enrichr results.
:param df: GSEApy DataFrame results.
:param column: which column of DataFrame to show. Default: Adjusted P-value
:param title: figure title
:param cutoff: terms with 'column' value < cut-off are shown.
:param top_term: number of enriched terms to show.
:param ascending: bool, the order of y axis.
:param sizes: tuple, (min, max) scatter size. Not functional for now
:param norm: maplotlib.colors.Normalize object.
:param legend: bool, whether to show legend.
:param figsize: tuple, figure size.
:param cmap: matplotlib colormap
:param ofname: output file name. If None, don't save figure
"""
colname = column
# sorting the dataframe for better visualization
if colname in ['Adjusted P-value', 'P-value']:
# check if any values in `df[colname]` can't be coerced to floats
can_be_coerced = df[colname].map(isfloat)
if np.sum(~can_be_coerced) > 0:
raise ValueError(
'some value in %s could not be typecast to `float`' % colname)
else:
df.loc[:, colname] = df[colname].map(float)
df = df[df[colname] <= cutoff]
if len(df) < 1:
msg = "Warning: No enrich terms when cutoff = %s" % cutoff
return msg
df = df.assign(logAP=lambda x: -x[colname].apply(np.log10))
colname = 'logAP'
df = df.sort_values(by=colname).iloc[-top_term:, :]
#
temp = df['Overlap'].str.split("/", expand=True).astype(int)
df = df.assign(Hits=temp.iloc[:, 0], Background=temp.iloc[:, 1])
df = df.assign(Hits_ratio=lambda x: x.Hits / x.Background)
# x axis values
x = df.loc[:, colname].values
combined_score = df['Combined Score'].round().astype('int')
# y axis index and values
y = [i for i in range(0, len(df))]
ylabels = df['Term'].values
# Normalise to [0,1]
# b = (df['Count'] - df['Count'].min())/ np.ptp(df['Count'])
# area = 100 * b
# control the size of scatter and legend marker
levels = numbers = np.sort(df.Hits.unique())
if norm is None:
norm = Normalize()
elif isinstance(norm, tuple):
norm = Normalize(*norm)
elif not isinstance(norm, Normalize):
err = ("``size_norm`` must be None, tuple, " "or Normalize object.")
raise ValueError(err)
min_width, max_width = np.r_[20, 100] * plt.rcParams["lines.linewidth"]
norm.clip = True
if not norm.scaled():
norm(np.asarray(numbers))
size_limits = norm.vmin, norm.vmax
scl = norm(numbers)
widths = np.asarray(min_width + scl * (max_width - min_width))
if scl.mask.any():
widths[scl.mask] = 0
sizes = dict(zip(levels, widths))
df['sizes'] = df.Hits.map(sizes)
area = df['sizes'].values
# create scatter plot
if hasattr(sys, 'ps1') and (ofname is None):
# working inside python console, show figure
fig, ax = plt.subplots(figsize=figsize)
else:
# If working on commandline, don't show figure
fig = Figure(figsize=figsize)
canvas = FigureCanvas(fig)
ax = fig.add_subplot(111)
vmin = np.percentile(combined_score.min(), 2)
vmax = np.percentile(combined_score.max(), 98)
sc = ax.scatter(x=x,
y=y,
s=area,
edgecolors='face',
c=combined_score,
cmap=cmap,
vmin=vmin,
vmax=vmax)
if column in ['Adjusted P-value', 'P-value']:
xlabel = "-log$_{10}$(%s)" % column
else:
xlabel = column
ax.set_xlabel(xlabel, fontsize=14, fontweight='bold')
ax.yaxis.set_major_locator(plt.FixedLocator(y))
ax.yaxis.set_major_formatter(plt.FixedFormatter(ylabels))
ax.set_yticklabels(ylabels, fontsize=16)
# ax.set_ylim([-1, len(df)])
ax.grid()
# colorbar
cax = fig.add_axes([0.95, 0.20, 0.03, 0.22])
cbar = fig.colorbar(
sc,
cax=cax,
)
cbar.ax.tick_params(right=True)
cbar.ax.set_title('Combined\nScore', loc='left', fontsize=12)
# for terms less than 3
if len(df) >= 3:
# find the index of the closest value to the median
idx = [
area.argmax(),
np.abs(area - area.mean()).argmin(),
area.argmin()
]
idx = unique(idx)
else:
idx = range(len(df))
label = df.iloc[idx, df.columns.get_loc('Hits')]
if legend:
handles, _ = ax.get_legend_handles_labels()
legend_markers = []
for ix in idx:
legend_markers.append(ax.scatter([], [], s=area[ix], c='b'))
# artist = ax.scatter([], [], s=size_levels,)
ax.legend(legend_markers, label, title='Hits')
ax.set_title(title, fontsize=20, fontweight='bold')
if ofname is not None:
# canvas.print_figure(ofname, bbox_inches='tight', dpi=300)
fig.savefig(ofname, bbox_inches='tight', dpi=300)
return
return ax
