def loo_regressions(xs, ys, ft, dt, mt):
print '[INFO]', ft, dt
# Align matricies
x = xs.loc[:, ys.columns].dropna(axis=1).T
y = ys[x.index].T
# Define cross-validation
cv = LeaveOneOut(len(y))
# Run regressions
y_pred, y_betas = {}, {}
for m in y:
y_pred[m] = {}
betas = []
for train, test in cv:
lm = ElasticNet(alpha=0.01).fit(x.ix[train], y.ix[train, m])
y_pred[m][x.index[test][0]] = lm.predict(x.ix[test])[0]
betas.append(dict(zip(*(x.columns, lm.coef_))))
y_betas[m] = DataFrame(betas).median().to_dict()
y_pred = DataFrame(y_pred).ix[y.index, y.columns]
print '[INFO] Regression done: ', ft, dt
# Perform correlation with predicted values
metabolites_corr = [(ft, dt, f, mt, 'metabolites',
pearson(y[f], y_pred[f])[0]) for f in y_pred]
conditions_corr = [(ft, dt, s, mt, 'conditions',
pearson(y.ix[s], y_pred.ix[s])[0])
for s in y_pred.index]
return (metabolites_corr + conditions_corr), (ft, dt, mt, y_betas)
if df_type == 'Kinases/Phosphatases':
df = df[(df.count(1) / df.shape[1]) > .75]
# Conditions overlap
conditions = list(set(growth.index).intersection(df))
# PCA analysis
pca = PCA(n_components=n_components).fit(df.T.replace(np.nan, 0))
pca_pc = DataFrame(
pca.transform(df.T.replace(np.nan, 0)),
columns=['PC%d' % i for i in range(1, n_components + 1)],
index=df.columns)
# Plot correlation with PCA
ax = plt.subplot(gs[pos])
cor, pvalue, nmeas = pearson(growth[pca_pc.index], pca_pc[pc])
sns.regplot(growth[pca_pc.index], pca_pc[pc], ax=ax, color='#4c4c4c')
ax.axhline(0, ls='-', lw=0.1, c='black', alpha=.3)
ax.axvline(0, ls='-', lw=0.1, c='black', alpha=.3)
ax.set_title('%s - %s\n(Pearson: %.2f, p-value: %.1e)' %
(dataset_type, df_type, cor, pvalue))
ax.set_xlabel('Relative growth (centered)')
ax.set_ylabel(
'PC%d (%.1f%%)' %
(int(pc[-1:]), pca.explained_variance_ratio_[int(pc[-1:]) - 1] * 100))
sns.despine(trim=True, ax=ax)
ax = plt.subplot(gs[pos + 1])
plot_df = DataFrame(zip(['PC%d' % i for i in range(1, n_components + 1)],
pca.explained_variance_ratio_),
columns=['PC', 'var'])
for m in metabolomics_dyn_ng.index:
for c in conditions:
ys = y.ix[m, [i for i in y if not i.startswith(c)]]
xs = x[ys.index].T
yss = y.ix[m, [i for i in y if i.startswith(c)]]
xss = x[yss.index].T
lm = ElasticNet(alpha=0.01).fit(xs, ys)
pred = Series(lm.predict(xss), index=xss.index)
features = dict(zip(*(xs.columns, lm.coef_)))
for f in features:
lm_feat.append((feature_type, method_type, m, c, f, features[f]))
lm_res.append((feature_type, method_type, m, c, pearson(yss, pred)[0]))
lm_res = DataFrame(lm_res, columns=['feature', 'method', 'ion', 'condition', 'pearson'])
lm_res['metabolite'] = [met_name[i] for i in lm_res['ion']]
print lm_res.head()
lm_feat = DataFrame(lm_feat, columns=['feature_type', 'method', 'ion', 'condition', 'feature', 'coefficient'])
lm_feat['m_name'] = [met_name[i] for i in lm_feat['ion']]
lm_feat['f_name'] = [acc_name[i] for i in lm_feat['feature']]
print lm_feat.head()
# -- Plot
palette = {'TFs': '#34495e', 'Kinases': '#3498db'}
# Correlation boxplots
index_col=0)[k_activity_dyn_comb_gsea.columns]
metabolomics_dyn_comb = metabolomics_dyn_comb[
metabolomics_dyn_comb.std(1) > .4]
metabolomics_dyn_comb.index = ['%.4f' % i for i in metabolomics_dyn_comb.index]
kinases, ions, conditions = set(k_activity_dyn_comb_lm.index), set(
metabolomics_dyn_comb.index), set(metabolomics_dyn_comb)
# -- Define metabolic to analyse
m = '606.0736'
k_activities = [('gsea', k_activity_dyn_comb_gsea),
('lm', k_activity_dyn_comb_lm)]
# -- Kinase activities correlation
m_cor = [(k,
pearson(k_activity_dyn_comb_lm.ix[k, conditions],
metabolomics_dyn_comb.ix[m, conditions])[0],
pearson(k_activity_dyn_comb_gsea.ix[k, conditions],
metabolomics_dyn_comb.ix[m, conditions])[0])
for k in kinases]
m_cor = DataFrame(m_cor, columns=['kinase', 'lm_cor',
'gsea_cor']).set_index('kinase')
lm_top_features = list(m_cor['lm_cor'].abs().sort(
inplace=False, ascending=False).head(5).index)
gsea_top_features = list(m_cor['gsea_cor'].abs().sort(
inplace=False, ascending=False).head(5).index)
top_features = list(set(lm_top_features).union(gsea_top_features))
plot_df = [(m, k, c, method, metabolomics_dyn_comb.ix[m, c], df.ix[k, c])
for k in top_features for c in conditions
for method, df in k_activities]