Supervised Probabilistic Approach for Drug Target Prediction

Abstract

Bayesian ranking based drug-target relationship prediction has achieved good results, but it ignores the relationship between drugs of the same target, which affects the accuracy. Aiming at this problem, a new method is proposed—drug-target relationship prediction based on grouped Bayesian ranking. According to the reality that the drugs interacting with a specific target have similarities, a grouping strategy is introduced to make these similar drugs interact. A theoretical model based on the grouping strategy is derived. The method is compared with five typical methods on five publicly available datasets and produces results superior to the compared methods.