Global Partnership Fuels AI Drug Discovery Tool

Researchers develop AI framework to rapidly generate drug-like molecules easier to synthesize in real-world labs.

Jan. 31, 2026 at 12:15am

Got story updates? Submit your updates here. ›

Researchers from The Ohio State University and the Indian Institute of Technology Madras have developed an artificial intelligence framework called PURE (Policy-guided Unbiased REpresentations for Structure-Constrained Molecular Generation) that promises to significantly cut down the early-stage timelines of drug development by generating drug-like molecules that are easier to synthesize in real-world laboratory settings.

Why it matters

The new AI system stands apart from existing molecule-generation tools by blending self-supervised learning with policy-based reinforcement learning to explore the chemical landscape more naturally, simulating step-by-step molecular changes using templates derived from real chemical reactions. This helps address a key problem in AI-driven drug discovery where most AI-generated molecules look promising on a computer but are nearly impossible to synthesize in reality.

The details

PURE draws inspiration from how drugs are actually synthesized in labs, using a template-driven approach to molecular simulations. By blending self-supervised learning - which lets the model learn patterns from data without labels - with a policy-based reinforcement learning setup, it explores the chemical landscape more naturally. PURE was evaluated on widely accepted molecule-generation benchmarks and delivered more diverse and original molecules while generating possible synthetic routes without ever being trained on those scoring metrics.

  • The findings were published in the Journal of Cheminformatics in January 2026.

The players

The Ohio State University

A public research university located in Columbus, Ohio.

Indian Institute of Technology Madras

A public technical and research university located in Chennai, India.

Srinivasan Parthasarathy

A professor in the Department of Computer Science and Engineering at The Ohio State University and a collaborator on the PURE project.

B. Ravindran

A professor at the Indian Institute of Technology Madras and a collaborator on the PURE project.

Sean Current

A recent PhD graduate from The Ohio State University and a collaborator on the PURE project.

Got photos? Submit your photos here. ›

What they’re saying

“This new framework offers game-changing benefits for early-stage pharmaceutical research, with the capability to identify alternative, more effective drug candidates in the face of resistance and hepatotoxicity.”

— Srinivasan Parthasarathy, Professor, Department of Computer Science and Engineering, The Ohio State University

“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.”

— B. Ravindran, Professor, Indian Institute of Technology Madras

What’s next

In addition to drug discovery, the researchers say the PURE framework also provides a promising foundation for accelerating the discovery of new materials, an important future research direction.

The takeaway

PURE's innovative approach to AI-driven drug discovery, blending self-supervised learning with policy-based reinforcement learning, holds the potential to significantly streamline the early-stage drug development process by generating more synthesizable drug candidates and addressing challenges like drug resistance and toxicity.