BE-DTI': Ensemble framework for drug target interaction prediction using dimensionality reduction and active learning. (October 2018)

• Record Type: Journal Article
• Authors: Sharma, Aman; Rani, Rinkle
• Is Part Of: Computer methods and programs in biomedicine. Volume 165(2018)
• Page Start: 151
• Page End: 162
• Publication Date: 2018-10
• Subjects: Drug-Target interaction prediction -- Ensemble learning -- Dimensionality reduction -- Active learning -- Bagging -- Gene expression; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2018.08.011
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Proposed framework consists of bagging based ensemble learning which adds diversity in the classifier. Drug features are prepared using Rcpi package and target features are prepared using PROFEAT web server. The issue caused due to class imbalance is resolved using Active Learning. High dimensionality of data is addressed in this paper. The performance of our proposed framework is compared with five existing feature-based approaches on the basis of AUC, AUPR, Sensitivity, Specificity, G-mean. Abstract: Background and objective: Drug-target interaction prediction plays an intrinsic role in the drug discovery process. Prediction of novel drugs and targets helps in identifying optimal drug therapies for various stringent diseases. Computational prediction of drug-target interactions can help to identify potential drug-target pairs and speed-up the process of drug repositioning. In our present, work we have focused on machine learning algorithms for predicting drug-target interactions from the pool of existing drug-target data. The key idea is to train the classifier using existing DTI so as to predict new or unknown DTI. However, there are various challenges such as class imbalance and high dimensional nature of data that need to be addressed before developing optimal drug-target interaction model. Methods: In this paper, we propose a bagging based ensemble framework named BE-DTI' for drug-target interaction prediction using dimensionality reduction and active learning to deal with class-imbalanced data. Active learning helps to improve under-sampling bagging based ensembles. Dimensionality reduction is used to deal with high dimensional data. Results: Results show that the proposed technique outperforms the other five competing methods in 10-fold cross-validation experiments in terms of AUC=0.927, Sensitivity=0.886, Specificity=0.864, and G-mean=0.874. Conclusion: Missing interactions and new interactions are predicted using the proposed framework. Some of the known interactions are removed from the original dataset and their interactions are recalculated to check the accuracy of the proposed framework. Moreover, validation of the proposed approach is performed using the external dataset. All these results show that structurally similar drugs tend to interact with similar targets.