Drug Discovery using Generative Adversarial Network with Reinforcement Learning
Ganesh R. Padalkar, Shivani Patil, Mukta Mallikarjun Hegadi, Nikita Kailash Jaybhaye
Abstract
A large amount of medical data is available to many of us and along with well-established deep learning algorithms, so the design of automated drug development pipelines has increased. The pipeline speeds up the drug discovery process and helps us better understand the disease. They help in planning pre-clinical lab experiments. This reduces the low productivity rate that the pharmaceutical companies are facing currently. Accurate predictions and insights are obtained by using deep learning techniques. So, this increases the need for deep learning approaches that have the potential to speed up the process, decision making, and reduce failure rates in drug discovery and development. With the fast development of computing power and enormous medical data, the project involving drug discovery have been benefited from artificial intelligence. The deep learning model knows as Generative Adversarial Network (GAN) with reinforcement learning is used to solve the problem.