CHENNAI: The researchers from Indian Institute of Technology Madras and The Ohio State University, US, have developed a breakthrough Artificial Intelligence (AI) system that can quickly create new drug-like molecules which are easier to produce in laboratories, said a statement issued by IIT Madras

The new framework, called PURE (Policy-guided Unbiased Representations for Structure-Constrained Molecular Generation) could drastically cut down the early stages of drug development – a process that currently takes years and costs billions of dollars.

Unlike most AI tools that rely on fixed scoring systems, PURE uses reinforcement learning to understand how molecules change and form.

Professor B Ravindran, head of the Wadhwani School of Data Science and AI at IIT Madras, said PURE represents “a major shift in how AI can reason through chemical synthesis”. Professor Karthik Raman added the system avoids bias by exploring the vast chemical space without being tied to specific metrics. According to professor Srinivasan Parthasarathy from Ohio State University, PURE could transform early-stage pharmaceutical research.