def saveFig(fig_fileprefix, bbox=True):
PL.rcParams['svg.fonttype'] = 'none'
for ftype in ['svg', 'png']:
if FIG_TYPE == 'both' or FIG_TYPE == ftype:
if bbox:
PL.savefig(getPlotDir() + '/' + fig_fileprefix + '.' + ftype,
bbox_inches='tight')
else:
PL.savefig(getPlotDir() + '/' + fig_fileprefix + '.' + ftype)
def plotPercScatterAnalysis(data, label='test', y_axis = 'Percent Non-Null Reads', plot_scatters=False, plot_regr_lines=False, scatter_mh_lens=[], mh_lens=[9]):
plot_dir = getPlotDir()
regr_lines = {}
for mh_len in mh_lens:
mh_data = data.loc[data['MH Len'] == mh_len]
mh_rdata = mh_data.loc[(mh_data['MH Dist'] >= 0) & (mh_data['MH Dist'] < (30-mh_len)) ]
regr = linear_model.LinearRegression()
rx, ry = mh_rdata[['MH Dist']], mh_rdata[[y_axis]] #np.log(mh_rdata[[y_axis]])
regr.fit(rx, ry)
corr = scipy.stats.pearsonr(rx, ry)
min_x, max_x = rx.min()[0], rx.max()[0]
x_pts = [min_x, max_x]
regr_lines[mh_len] = (x_pts,[regr.predict(x)[0] for x in x_pts],corr[0])
if plot_scatters and mh_len in scatter_mh_lens:
fig = PL.figure(figsize=(5,5))
PL.plot( mh_data['MH Dist'], mh_data[y_axis], '.', alpha=0.4 )
PL.plot(regr_lines[mh_len][0],regr_lines[mh_len][1],'dodgerblue',linewidth=3)
PL.xlabel('Distance between nearest ends of\nmicrohomologous sequences',fontsize=14)
PL.ylabel('Percent of mutated reads of corresponding\nMH-mediated deletion',fontsize=14)
PL.tick_params(labelsize=14)
PL.xlim((0,20))
PL.title('Microhomology of length %d (r=%.2f)' % (mh_len,corr[0]),fontsize=14)
PL.show(block=False)
saveFig('mh_scatter_len%d_%s' % (mh_len,label.split('/')[-1]))
if plot_regr_lines:
fig = PL.figure()
output_data = {}
for mh_len in mh_lens:
fit_data = regr_lines[mh_len]
if mh_len > 15:
continue
lsty = '--' if mh_len < 9 else '-'
PL.plot(fit_data[0], fit_data[1], linewidth=2, linestyle=lsty, label='MH length %d (R=%.1f)' % (mh_len, fit_data[2]))
PL.title(label,fontsize=18)
PL.xlabel('Distance between nearest ends of\nmicrohomologous sequences',fontsize=14)
PL.ylabel('Percent of mutated reads of corresponding\nMH-mediated deletion',fontsize=14)
PL.tick_params(labelsize=18)
PL.legend()
PL.ylim((0,100))
PL.show(block=False)
saveFig(plot_dir + '/mh_scatter_all_len_%s' % label.split('/')[-1])
return regr_lines
def plotVerticalHistSummary(all_result_outputs,
label='',
data_label='',
y_label='',
plot_label='',
hist_width=1000,
hist_bins=100,
oligo_id_str='Oligo ID',
val_str='Cut Rate',
total_reads_str='Total Reads'):
datas = [x[0][data_label][0] for x in all_result_outputs]
sample_names = [shortDirLabel(x[1]) for x in all_result_outputs]
merged_data = pd.merge(datas[0],
datas[1],
how='inner',
on=oligo_id_str,
suffixes=['', ' 2'])
for i, data in enumerate(datas[2:]):
merged_data = pd.merge(merged_data,
data,
how='inner',
on=oligo_id_str,
suffixes=['', ' %d' % (i + 3)])
suffix = lambda i: ' %d' % (i + 1) if i > 0 else ''
xpos = [x * hist_width for x in range(len(sample_names))]
PL.figure(figsize=(12, 8))
for i, label1 in enumerate(sample_names):
dvs = merged_data[val_str + suffix(i)]
PL.hist(dvs,
bins=hist_bins,
bottom=i * hist_width,
orientation='horizontal')
PL.xticks(xpos, sample_names, rotation='vertical')
PL.ylabel(y_label)
PL.title(label)
PL.show(block=False)
PL.savefig(getPlotDir() + '/%s_%s.png' %
(plot_label, label.replace(' ', '_')),
bbox_inches='tight')
def plotBoxPlotSummary(all_result_outputs,
label='',
data_label='',
y_label='',
plot_label=''):
data_values = [x[0][data_label][0].values for x in all_result_outputs]
sample_names = [
shortDirLabel(x[1]) + ' (%d)' % x[0][data_label][1]
for x in all_result_outputs
]
PL.figure(figsize=(12, 8))
for i, dvs in enumerate(data_values):
PL.boxplot([dvs], positions=[i], showfliers=True, sym='.', widths=0.8)
PL.xticks(range(len(sample_names)), sample_names, rotation='vertical')
PL.ylabel(y_label)
PL.title(label)
PL.show(block=False)
PL.savefig(getPlotDir() + '/%s_%s.png' %
(plot_label, sanitizeLabel(label)),
bbox_inches='tight')
def plotCorrelations(all_result_outputs,
label='',
data_label='',
y_label='',
plot_label='',
plot_scatters=False,
oligo_id_str='Oligo ID',
val_str='Cut Rate',
total_reads_str='Total Reads',
scatter_samples={},
sdims=(0, 0),
scatter_fig=None,
add_leg=True):
datas = [x[0][data_label][0] for x in all_result_outputs]
sample_names = [shortDirLabel(x[1]) for x in all_result_outputs]
merged_data = pd.merge(datas[0],
datas[1],
how='inner',
on=oligo_id_str,
suffixes=['', ' 2'])
for i, data in enumerate(datas[2:]):
merged_data = pd.merge(merged_data,
data,
how='inner',
on=oligo_id_str,
suffixes=['', ' %d' % (i + 3)])
suffix = lambda i: ' %d' % (i + 1) if i > 0 else ''
N = len(sample_names)
if plot_scatters:
if scatter_fig is None: PL.figure()
else: PL.figure(scatter_fig.number)
s_dims = (N, N) if len(scatter_samples) == 0 else sdims
pcorrs, scorrs = np.zeros((N, N)), np.zeros((N, N))
for i, label1 in enumerate(sample_names):
for j, label2 in enumerate(sample_names):
dvs1, dvs2, ids = merged_data[val_str + suffix(i)], merged_data[
val_str + suffix(j)], merged_data[oligo_id_str]
pcorrs[i, j] = pearsonr(dvs1, dvs2)[0]
scorrs[i, j] = spearmanr(dvs1, dvs2)[0]
if plot_scatters:
if (label1, label2) in scatter_samples:
idx = scatter_samples[(label1, label2)]
elif len(scatter_samples) == 0:
idx = i * N + j + 1
else:
continue
PL.subplot(s_dims[0], s_dims[1], idx)
trs1, trs2 = merged_data[
total_reads_str + suffix(i)], merged_data[total_reads_str +
suffix(j)]
for thr in [20, 50, 100, 500, 1000]:
thr_dvs = [(dv1, dv2, id)
for (dv1, dv2, tr1, tr2,
id) in zip(dvs1, dvs2, trs1, trs2, ids)
if (tr1 >= thr and tr2 >= thr)]
pcorrs[i, j] = pearsonr([x[0] for x in thr_dvs],
[x[1] for x in thr_dvs])[0]
PL.plot([x[0] for x in thr_dvs], [x[1] for x in thr_dvs],
'.',
label='>%d Reads' % thr)
PL.plot([0, 100], [0, 100], 'k--')
PL.xlabel('K562 Replicate A')
PL.ylabel('K562 Replicate B')
if add_leg: PL.legend()
PL.title('%s (%.2f)' % (y_label, pcorrs[i, j]))
if plot_scatters:
PL.subplots_adjust(left=0.05,
right=0.95,
top=0.9,
bottom=0.1,
hspace=0.4)
PL.show(block=False)
saveFig(plot_label)
if not plot_scatters:
PL.figure()
PL.subplot(1, 2, 1)
PL.imshow(pcorrs,
cmap='hot',
vmin=0.0,
vmax=1.0,
interpolation='nearest')
PL.xticks(range(N), sample_names, rotation='vertical')
PL.yticks(range(N), sample_names)
PL.title(y_label + ': Pearson')
PL.colorbar()
PL.subplot(1, 2, 2)
PL.imshow(scorrs,
cmap='hot',
vmin=0.0,
vmax=1.0,
interpolation='nearest')
PL.xticks(range(N), sample_names, rotation='vertical')
PL.yticks(range(N), sample_names)
PL.title(y_label + ': Spearman')
PL.colorbar()
PL.show(block=False)
PL.savefig(getPlotDir() + '/%s_%s.png' %
(plot_label, sanitizeLabel(label)),
bbox_inches='tight')