MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611112811 A) filed by Noida Institute Of Engineering And Technology Pharmacy Institute on September 21, 2026, for Ai-Driven Closed-Loop Platform For Predictive Formulation Optimization And Real-Time Stability Assessment Of Aav Gene Therapies.
Inventors include Dr. Sharad Sharma; and Ms. Aparna Gupta.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: An integrated autonomous physical platform for predictive formulation optimization and real-time stability assessment of adeno-associated virus gene therapy products, comprising a robotic liquid handling apparatus preparing up to 384 formulation conditions per cycle, multi-modal analytical instruments including spectrophotometry, dynamic and static light scattering, differential scanning fluorimetry and flow imaging microscopy apparatus, a Bayesian optimization engine employing Gaussian process regression with composite Matern-categorical kernels for autonomous experiment design, and a predictive shelf-life modelling module combining Arrhenius kinetics with Gaussian process regression. The orchestration software implements autonomous design-build-test-learn cycles on the physical platform converging within three to five cycles spanning seven days, achieving the tangible technical effects of eighty percent material savings, fifteen-fold larger design space exploration and identification of optimally stable formulations validated under refrigerated, room-temperature, freeze-thaw and agitation stress conditions. Transfer learning across serotypes via multi-task Gaussian processes accelerates optimization for new capsid variants by forty percent.
Disclaimer: Curated by HT Syndication.
