plt.xlabel('TCGA cancer type')
plt.ylabel('cindex(signal) - cindex(shuffled)')
plt.title('Survival prediction, {}'.format(me_results_desc))
plt.ylim(-0.5, 0.5)
plt.tight_layout()
# ### Heatmap
#
# This is similar to the heatmaps we plotted in the results script in `02_classify_mutations` for the mutation prediction problem. We want to compare data types for predicting survival in different cancer types.
# In[10]:
me_all_results_df = au.compare_all_data_types(
me_results_df[~me_results_df.cancer_type.isin(drop_cancer_types)],
SIG_ALPHA,
identifier='cancer_type',
metric='cindex')
me_all_results_df.rename(columns={'gene': 'cancer_type'}, inplace=True)
me_all_results_df.sort_values(by='p_value').head(10)
# In[11]:
me_heatmap_df = (me_all_results_df.pivot(
index='training_data', columns='cancer_type',
values='delta_mean').reindex(sorted(me_compare_df.training_data.unique())))
me_heatmap_df.iloc[:, :5]
# In[12]:
hue_order = ['Control', 'Drop target', 'Only target']
sns.boxplot(data=plot_df,
x='identifier',
y='aupr',
hue='experiment',
hue_order=hue_order)
# ### Correct for shuffled baseline + plot signal AUPR - shuffled AUPR
# In[5]:
# now correct for shuffled baseline
results_df = (results_df.drop(columns='training_data').rename(
columns={'experiment': 'training_data'}))
all_results_df = au.compare_all_data_types(results_df,
0.05,
filter_genes=False,
compare_ind=True)
all_results_df = all_results_df.rename(columns={'training_data': 'experiment'})
all_results_df.head()
# In[6]:
sns.set({'figure.figsize': (13, 6)})
sns.set_style('whitegrid')
sns.set_palette('Set2')
sns.boxplot(data=all_results_df,
x='gene',
y='delta_aupr',
hue='experiment',
hue_order=hue_order)
if _y > 0:
ax.text(_x, _y + 0.01, val, ha="center")
else:
ax.text(_x, _y - 0.02, val, ha="center")
show_values_on_bars(plt.gca())
plt.gca().get_xaxis().set_visible(False)
plt.ylabel('{} difference'.format(metric.upper()))
plt.title('Performance difference between new and old shuffling scheme',
size=14)
# In[8]:
old_all_results_df = au.compare_all_data_types(old_results_df,
0.05,
metric='aupr')
old_all_results_df.head()
# In[9]:
new_all_results_df = au.compare_all_data_types(new_results_df,
0.05,
metric='aupr')
new_all_results_df.head()
# In[10]:
compare_results_df = new_all_results_df.copy()
compare_results_df[
'mean_diff'] = new_all_results_df.delta_mean - old_all_results_df.delta_mean
sns.boxplot(data=plot_df, x='identifier', y='auroc', hue='training_data', ax=axarr[1])
axarr[1].set_title('MSI prediction performance, AUROC')
axarr[1].set_xlabel('Cancer type')
axarr[1].set_ylabel('AUROC')
axarr[1].set_ylim(0.35, 1.05)
axarr[1].legend(title='Data type')
# ### Plot results per cancer type, corrected for permuted labels baseline
# In[5]:
compare_df = au.compare_all_data_types(results_df,
sig_alpha=0.05,
filter_genes=False,
compare_ind=True,
metric='auroc')
compare_df.rename(columns={'gene': 'cancer_type'}, inplace=True)
compare_aupr_df = au.compare_all_data_types(results_df,
sig_alpha=0.05,
filter_genes=False,
compare_ind=True,
metric='aupr')
compare_aupr_df.rename(columns={'gene': 'cancer_type'}, inplace=True)
print(compare_df.shape)
print(compare_df.training_data.unique())
compare_df.head()
print(results_df.shape)
training_data_map = {
'expression': 'gene expression',
'me_27k': '27k methylation',
'me_450k': '450k methylation',
'rppa': 'RPPA',
'mirna': 'microRNA',
'mut_sigs': 'mutational signatures',
}
results_df.training_data.replace(to_replace=training_data_map, inplace=True)
results_df.head()
# In[6]:
all_results_df = au.compare_all_data_types(results_df,
SIG_ALPHA,
metric=plot_metric)
cfg.sig_genes_dir.mkdir(exist_ok=True)
all_results_df.to_csv(cfg.sig_genes_all, index=False, sep='\t')
all_results_df.sort_values(by='p_value').head(10)
# In[7]:
sns.set({'figure.figsize': (22, 5)})
sns.set_style('whitegrid')
fig, axarr = plt.subplots(1, 3)
# plot mutation prediction from expression, in a volcano-like plot
# and that we have data for two replicates (two random seeds)
print(random_50_df.shape)
print(random_50_df.seed.unique())
print(random_50_df.training_data.unique())
random_50_df.head()
# In[6]:
# combine results dataframes
results_df = (pd.concat(
(vogelstein_df, top_50_df,
random_50_df)).drop(columns=['training_data', 'experiment']).rename(
columns={'gene_set': 'training_data'}))
all_results_df = au.compare_all_data_types(results_df,
SIG_ALPHA,
filter_genes=False,
metric=plot_metric)
all_results_df['nlog10_p'] = -np.log10(all_results_df.corr_pval)
all_results_df.sort_values(by='p_value').head(10)
# In[7]:
sns.set({'figure.figsize': (24, 6)})
sns.set_style('whitegrid')
fig, axarr = plt.subplots(1, 3)
gene_set_map = {
'random_50': 'random',
'top_50': 'most mutated',
'vogelstein': 'Vogelstein et al.'
adjust_text(text_labels,
ax=ax,
expand_text=(1., 1.),
lim=5)
plt.suptitle('Mutation prediction, raw vs. compressed results', size=16)
plt.tight_layout(w_pad=2, h_pad=2)
plt.subplots_adjust(top=0.94)
# In[6]:
raw_compare_df = au.compare_all_data_types(raw_results_df,
SIG_ALPHA,
filter_genes=False,
compare_ind=True,
metric=plot_metric)
raw_compare_df.sort_values(by=['training_data'], inplace=True)
raw_compare_df.head(5)
# In[7]:
raw_compare_all_df = au.compare_all_data_types(raw_results_df,
SIG_ALPHA,
filter_genes=False,
metric=plot_metric)