Fig. 4From: Empowering the discovery of novel target-disease associations via machine learning approaches in the open targets platformNewly computed features improve prediction accuracy. Prediction scores correspond to Testing set target-disease clinical trial stage (a). Feature importance scores indicate the feature types we generated strongly predict known drug therapeutic status (b). Target-disease arrays computed using target-target similarity reveal druggable target-disease pairs (c). Significant overlap between predicted indications and literature findings by text mining (d)Back to article page