Publications & Media

Research & News

We tackle the most challenging frontiers in computational drug discovery, advancing the field through innovative AI architectures and groundbreaking research that transforms how medicines are discovered.

Research Papers

AI-Designed Family of Dual COX-2/mPGES-1 Inhibitors to Treat Inflammation with Greater Precision and Effectiveness
ChemRxivOctober 30, 2025

AI-Designed Family of Dual COX-2/mPGES-1 Inhibitors to Treat Inflammation with Greater Precision and Effectiveness

Prashant S Kharkar, Aarshit Mittal, Ranbir Singh Saluja, Shobhan Shah

Traditional COX-2 selective inhibitors face cardiovascular risks and limited efficacy. We demonstrate an AI-driven computational pipeline that compressed drug design from years to one month, generating a novel family of dual COX-2/mPGES-1 inhibitors. Our hybrid reinforcement learning-generative adversarial network (RL-GAN) explored beyond known chemical space, producing ~50,000 de novo molecules and yielding 23 high-confidence candidates with superior predicted binding affinities.

Key Contributions

  • AI pipeline reduced design-to-candidate timeline from years to one month
  • Generated 23 novel dual inhibitors with binding affinities exceeding rofecoxib
  • Achieved >100-fold predicted selectivity over COX-1 with concurrent mPGES-1 engagement
  • 92.9% of candidates structurally dissimilar to known inhibitors across 44.3 million patent records
Read Full Paper

In the News

India's Artificial Intelligence Leap: AI Platform Delivers Drug Candidates in Weeks
International Business TimesNovember 10, 2025

India's Artificial Intelligence Leap: AI Platform Delivers Drug Candidates in Weeks

By Alexander Maxwell

India has taken a major step toward leadership in high-value pharmaceutical innovation. Researchers at the Institute of Chemical Technology (ICT), Mumbai, in partnership with OCSR.ai, have designed a new set of anti-inflammatory drug candidates using an entirely AI-driven process. At the heart of this breakthrough is OCSR.ai, a chemical intelligence engine featuring the world's largest database of 1.3 trillion commercially accessible small molecules.

Key Highlights

  • AI-driven design of next-generation anti-inflammatory drug candidates
  • Candidate discovery cycle reduced from 3 years to 3 weeks
  • Patent-clean space of molecules identified for further development
  • Strong potential for safer therapies addressing a $90 billion global market
Read Full Article

Stay Updated with Our Research

Follow our journey as we push the boundaries of AI-driven drug discovery and share our findings with the scientific community.