An ensemble-based drug–target interaction prediction approach using multiple feature information with data balancing

Abstract

Background Recently, drug repositioning has received considerable attention for its advantage to pharmaceutical industries in drug development. Artificial intelligence techniques have greatly enhanced drug reproduction by discovering therapeutic drug profiles, side effects, and new target proteins. However, as the number of drugs increases, their targets and enormous interactions produce imbalanced data that might not be preferable as an input to a prediction model immediately. Methods This paper proposes a novel scheme for predicting drug–target interactions (DTIs) based on drug chemical structures and protein sequences. The drug Morgan fingerprint, drug constitutional descriptors, protein amino acid composition, and protein dipeptide composition were employed to extract the drugs and protein’s characteristics. Then, the proposed approach for extracting negative samples using a support vector machine one-class classifier was developed to tackle the imbalanced data problem feature sets from the drug–target dataset. Negative and positive samplings were constructed and fed into different prediction algorithms to identify DTIs. A 10-fold CV validation test procedure was applied to assess the predictability of the proposed method, in addition to the study of the effectiveness of the chemical and physical features in the evaluation and discovery of the drug–target interactions. Results Our experimental model outperformed existing techniques concerning the curve for receiver operating characteristic (AUC), accuracy, precision, recall F-score, mean square error, and MCC. The results obtained by the AdaBoost classifier enhanced prediction accuracy by 2.74%, precision by 1.98%, AUC by 1.14%, F-score by 3.53%, and MCC by 4.54% over existing methods.

BindingSiteDTI: differential-scale binding site modelling for drug–target interaction prediction

“…Representation learning based methods aim to improve the DTI prediction performance by extracting a rich feature of drugs and targets. Recent trends include combining different representations ( El-Behery et al 2022 , Khojasteh et al 2023 ) or modelling the feature with multimodalities ( Xia et al 2023 ) to further boost the performance. However, several studies have demonstrated that representation learning-based models often attain high prediction accuracy by overfitting specific representational features ( Bai et al 2023 ).…”