An Indian scientist pioneering the research for fast pacing the development of new medicines is gaining attention internationally in the wake of Covid-19 pandemic. Pharmaceutical companies worldwide face immense hardships if a new drug has to be developed or improved. The margin of financial and ethical levels are so high that with the slightest of miscalculations or simply put forth, adverse fate can lead to the closure of the company. The process starts with the identification of the new drug molecule and ends with a clinical trial which may last up to 15 years.
Leading the research in developing a machine learning system, Raghavan B Sunoj and a team of researchers from IIT Bombay are aiming to reduce these risks associated with the development of a new drug. The researchers at IIT Bombay are exploring the possibilities of Machine learning for identifying asymmetric catalysts. They had successfully eased the complex task of identifying the molecular parameters including chirality with excellent predictive power using Machine learning techniques of Random forest and decision tree.
This approach as per the researchers can not only accelerate the process but also increase its throughput. In the proposed approach, an ML-based mathematical model is trained on known catalysts, which then helps to predict the effectiveness of other catalysts. After multiple such training runs with additional data of catalysts, the model was validated with some test sets. This process of the train-predict-train cycle accelerates the discovery of favorable catalysts.
Machine learning is a branch of Artificial intelligence and the new development is expected to speed up the identification of asymmetric catalysts in the making of a new drug. Raghavan B Sunoj hails from Trivandrum, Kerala and went on his academic streak after completing MSc in Chemistry from Kerala University. He is now a faculty in Chemistry in IIT Bombay.Professor Balamurugan is also partaking in this groundbreaking research which could ultimately save the lives of many in the meantime.