Fig. 2
From: Machine learning prediction of oncology drug targets based on protein and network properties
Overview of the drug target druggability predictions. Our positive training set consisted of 102 approved oncology drug targets. We generated negative training sets of the same size as the positive set by random sampling without replacement all human proteins after excluding both the approved and clinical trial oncology targets. We built a large number of 10,000 random forest models using each of the random negative sets and made predictions based on each model. We then assign a drug target probability score to each protein by averaging the predictions of the 10,000 models. To evaluate the performance of our model we considered the independent set of 277 targets which had at least one oncology clinical trial drug targeting them, but no approved drugs