A Drug-Target Interaction Prediction Based on Supervised Probabilistic Classification

Abstract

Bayesian ranking-based drug-target relationship prediction has achieved good results, but it ignores the relationship between drugs of the same target. A new method is proposed for drug-target relationship prediction based on groups by Appling Bayesian. According to the reality that drugs interacting with a specific target have similarities, a grouping strategy was introduced to make these similar drugs interact. A theoretical model based on the grouping strategy is derived in this study. The method is compared with five typical methods on five publicly available datasets and produces superior results to the compared methods. The impact of grouping interaction on the Bayesian ranking approach is examined in this study to create a grouped medication set; comparable pharmaceuticals that interact with the same target are first grouped based on this reality. Then, based on the grouped drug set, new hypotheses were put forth and the conceptual approach of grouped Bayesian ranking was constructed. Finally, to predict novel medications and targets, the article also includes neighbor information. The associated studies demonstrate that the strategy presented in this study outperforms the conventional performance techniques. Plans for further performance improvement through the creation of new comparable grouping objectives are included in future work.