MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202611100439 A) filed by Dr. Devendar Reddy Kommidi on August 19, 2026, for An Intelligent Chemical Compound Prediction Platform For Drug And Material Discovery.
Inventors include Dr. Devendar Reddy Kommidi; Dr. Chandra Sekar Vasam; Dr. Kalyani Paidikondala; Dr. Srinivas Nerella; Boya Palajonnala Narasaiah; and Dr. K. Surya Sagar.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to an intelligent chemical compound prediction platform for drug and material discovery that integrates artificial intelligence, graph neural networks, transformer-based molecular language models, deep learning, reinforcement learning, computational chemistry, and explainable artificial intelligence within a unified computational framework. The platform acquires and preprocesses molecular data from heterogeneous sources, constructs graph-based molecular representations, generates high-dimensional molecular embeddings, predicts multiple physicochemical and biological properties, and automatically generates novel chemical compounds satisfying predefined optimization objectives. Multi-objective optimization algorithms simultaneously optimize biological activity, toxicity, pharmacokinetic behavior, chemical stability, synthetic accessibility, environmental compatibility, and application-specific material properties while balancing competing design requirements. Explainable artificial intelligence modules identify influential molecular features responsible for prediction outcomes, thereby improving scientific interpretability and user confidence. The platform further incorporates uncertainty estimation, active learning, cloud computing, and continuous model retraining using experimentally validated data to enhance prediction accuracy and adaptability. The invention significantly reduces the time, computational resources, laboratory experimentation, and financial costs associated with conventional drug discovery and materials development while improving the identification of high-value candidate compounds. The disclosed platform is applicable to pharmaceutical research, biotechnology, chemical engineering, materials science, environmental chemistry, nanotechnology, and industrial research, providing a scalable, intelligent, transparent, and continuously learning solution for accelerated molecular discovery.
Disclaimer: Curated by HT Syndication.
