Drug–target interaction prediction from PSSM based evolutionary information

• The bi-gram PSSM features are firstly used for drug-target interaction prediction.
• The bi-gram PSSM features are compared with the PAAC features of proteins.
• The AUC of PSSM-based model is better or comparable with the other methods.
• We investigate the impact of sampling method on the accuracy of model.

The labor-intensive and expensive experimental process of drug–target interaction prediction has motivated many researchers to focus on in silico prediction, which leads to the helpful information in supporting the experimental interaction data. Therefore, they have proposed several computational approaches for discovering new drug–target interactions. Several learning-based methods have been increasingly developed which can be categorized into two main groups: similarity-based and feature-based. In this paper, we firstly use the bi-gram features extracted from the Position Specific Scoring Matrix (PSSM) of proteins in predicting drug–target interactions. Our results demonstrate the high-confidence prediction ability of the Bigram-PSSM model in terms of several performance indicators specifically for enzymes and ion channels. Moreover, we investigate the impact of negative selection strategy on the performance of the prediction, which is not widely taken into account in the other relevant studies. This is important, as the number of non-interacting drug–target pairs are usually extremely large in comparison with the number of interacting ones in existing drug–target interaction data. An interesting observation is that different levels of performance reduction have been attained for four datasets when we change the sampling method from the random sampling to the balanced sampling.