IIT Madras & Ohio State Researchers Develop AI Framework to Accelerate Drug Discovery

The new system, named ‘PURE’ (Policy-guided Unbiased REpresentations for Structure-Constrained Molecular Generation), has been designed to address major challenges in early-stage drug discovery, a process that typically takes years and requires significant investment.

Researchers from the Indian Institute of Technology (IIT) Madras’ Wadhwani School of Data Science and Artificial Intelligence (WSAI) and The Ohio State University, US, have developed an Artificial Intelligence (AI) framework that can rapidly generate drug-like molecules capable of real-world synthesis.

The new system, named ‘PURE’ (Policy-guided Unbiased REpresentations for Structure-Constrained Molecular Generation), has been designed to address major challenges in early-stage drug discovery, a process that typically takes years and requires significant investment.

According to the researchers, the framework could contribute to developing more effective drugs and tackling issues such as drug resistance in cancer and infectious diseases.

Unlike existing molecule-generation tools that rely on rigid scoring systems or statistical optimization, PURE mimics the real-world chemical synthesis process. It was evaluated using standard molecule-generation benchmarks, including QED (drug-likeness), DRD2 (dopamine receptor activity), and solubility tests. The results showed that PURE produced higher diversity and novelty in generated molecules while also suggesting possible synthetic routes — all without being trained on specific scoring metrics.

Highlighting the significance of this research, Prof. B. Ravindran, Head, Wadhwani School of Data Science and AI (WSAI), IIT Madras, said, “Artificial intelligence is increasingly reshaping how we think about discovery itself, and drug design offers a compelling example of that transformation. What’s unique about PURE is the way it uses reinforcement learning, not just to optimize specific metrics, but to learn how molecules transform. By treating chemical design as a sequence of actions guided by real reaction rules, PURE moves us closer to AI systems that can reason through synthesis steps much like a chemist would.”

The researchers noted that the system addresses one of the key gaps in AI-driven drug discovery — the difficulty of synthesizing molecules that appear promising in simulations but are impractical in laboratory conditions. PURE overcomes this limitation by grounding molecular generation in real synthesis pathways, automatically learning chemical similarities, and proposing viable synthetic routes alongside molecular structures.

According to the team, these capabilities can enable faster drug pipelines and support the creation of backup solutions for treatments that fail during trials.

Stay tuned for more such updates on Digital Health News