Improving prediction of drug-target interactions based on fusing multiple features with data balancing and feature selection techniques
Predicting drug-target interaction (DTI) is an important research area in the field of drug discovery. It means identifying the interaction between chemical compounds and protein targets. Wet lab experiments to explore these interactions are expensive as well as time-consuming. On the contrary, a dry lab environment focusing more on computational methods of interaction prediction can be helpful to limit the search space for the wet lab experiments and give clues before developing a new medicine. This paper proposes a novel drug-target interaction prediction method called SRX-DTI. First, we extract various descriptors from protein sequences, and the drug is encoded as FP2 fingerprint. Besides, we present the One-SVM-US technique to deal with imbalanced data. We also developed the FFS-RF algorithm, a forward feature selection algorithm, and coupled it with a random forest (RF) classifier to maximize the predictive performance. This feature selection algorithm removes the irrelevant features to obtain the best optimal features. Finally, the balanced dataset with optimal features is given to the XGBoost classifier to identify DTIs. The experimental results demonstrate that our proposed approach SRX-DTI achieves significantly higher performance than other existing methods in predicting DTIs. The experimental results demonstrate that our proposed approach SRX-DTI achieves significantly higher performance than other existing methods in predicting DTIs. The datasets and source code are available at: https://github.com/Khojasteh-hb/SRX-DTI.