A Recommender System Approach for Predicting Drug Side Effects

The accurate identification of drug side effects represents a major concern for public health. We propose a collaborative filtering model for large-scale prediction of drug side effects. Our approach provides specific recommendations for side effects of medicines. The proposed latent factor model relies solely on the public drug-side effect relationships from safety data. Applied to 1,525 marketed drugs and 2,050 side effects, we achieved an AUPRC (area under the precision-recall curve) of 0.342 in a hold-out test set, with a sensitivity of 0.73 given a specificity of 0.95, providing state-of-the-art performance in side
effect prediction. Here we also show that our method provides good performance on drug-specific Anatomical Therapeutic and Chemical (ATC) category and side effect- specific medical category of disorders. Our findings suggest that latent factor models can be useful for predicting unknown adverse drug events.