DRaW: An Objection on Using Matrix Factorization for Drug-Repurposing– Prediction of Covid-19 Antivirals by Deep Learning as a Case Study

Abstract

Background: Due to the high resource consumption of introducing a new drug, drug repurposing plays an essential role in drug discovery. To do this, researchers examine the current drug-target interaction (DTI) to predict new interactions for the approved drugs. Matrix factorization methods have had much attention and utilization in DTIs. However, They suffer from some drawbacks. Methods: We explain why matrix factorization is not the best for DTI prediction. Then, we propose a deep learning model (DRaW) to predict DTIs without input data leakage. We compare our model with several matrix factorization methods and a deep model on the Coivd-19 dataset. In addition, to ensure the validation of DRaW, we evaluate it on benchmark datasets. Moreover, we do a docking study as external validation on the recommended drugs for Covid-19. Results: For all cases, the results confirm that DRaW outperforms the matrix factorization and deep models. The docking approves the top-ranked mode’s recommendations for Covid-19. Conclusions: In this paper, we show that it may not be the best choice to use matrix factorization in the DTI prediction. Matrix factorization methods suffer from some intrinsic issues, e.g., sparsity in the domain of bioinformatics applications and fixed-unchanged size of the matrix-related paradigm. Therefore, we propose an alternative method (DRaW) that uses feature vectors rather than matrix factorization and demonstrates better performance than other famous methods on four benchmark datasets.