A Review on Deep Learning-driven Drug Discovery: Strategies, Tools and Applications

Abstract

It takes an average of 10-15 years to uncover and develop a new drug, and the process is incredibly time-consuming, expensive, difficult, and ineffective. In recent years the dramatic changes in the field of artificial intelligence (AI) have helped to overcome the challenges in the drug discovery pipeline. Artificial intelligence (AI) has taken root in various pharmaceutical sectors, from lead compound identification to clinical trials. Deep learning (DL) is a component of artificial intelligence (AI) that has excelled in many fields of Artificial intelligence (AI) research over the past decades. Its numerous applications in the realms of science and technology, especially in biomedicine and bioinformatics, are witnessed deep learning (DL) applications significantly accelerate drug discovery and pharmaceutical research in recent years, and their usefulness has exceeded expectations and shown good promise in tackling a range of issues with drug discovery. Deep learning (DL) holds great potential for drug development since it allows for sophisticated image interpretation, molecular structure and function prediction, and the automated creation of novel chemical entities with specific features. In the process of drug discovery, deep learning (DL) can be incorporated at all stages like identification of targets, prognostic biomarkers, drug designing and development, synergism and antagonism prediction, etc. This review summarizes various approaches of deep learning (DL) in drug discovery like deep generative models for drug discovery, deep learning (DL) tools for drug discovery, synergy prediction, and precision medicine.

Keywords: Deep learning (DL); artificial intelligence; drug discovery; drug targets; neural networks; precision medicine.