MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202621096779 A) filed by Mrs. Kauthale Shubhangi Manohar; Mr. Kale Sunil Manmath; Miss Shinde Sarika Dattatray; Mrs. Ashwini Rameshrao Maka; Mrs. Nabha Rahul Vyavahare; Mr. Deepak K. Kokare; and Mr. Patil Mahesh B. on August 11, 2026, for Artificial Intelligence-Based Chemical Data Prediction And Visualization System.
Inventors include Mrs. Kauthale Shubhangi Manohar; Mr. Kale Sunil Manmath; Miss Shinde Sarika Dattatray; Mrs. Ashwini Rameshrao Maka; Mrs. Nabha Rahul Vyavahare; Mr. Deepak K. Kokare; and Mr. Patil Mahesh B..
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The present invention relates to an artificial intelligence-based chemical data prediction and visualization system configured to acquire heterogeneous chemical data from databases, laboratory instruments, electronic laboratory notebooks, experimental records, computational chemistry platforms, and other chemical information sources. The system normalizes and validates the received chemical data and generates molecular, reaction, physicochemical, spectral, or learned representations for processing by an artificial intelligence prediction engine. The prediction engine employs one or more machine learning models including graph-based models, transformer-based models, deep learning models, ensemble models, or probabilistic models to predict chemical properties or chemical outcomes. An uncertainty estimation module determines prediction confidence and applicability-domain information, while an explainability module identifies chemical features contributing to generated predictions. A visualization engine generates interactive chemical-space maps, molecular overlays, similarity networks, property plots, confidence representations, and analytical dashboards integrating predicted and experimentally observed information. An adaptive learning module receives validated experimental results and selectively updates prediction models based on uncertainty, novelty, prediction disagreement, or chemical-space coverage. The system thereby provides an integrated platform for chemical data harmonization, artificial intelligence-based prediction, uncertainty assessment, explainable analysis, adaptive learning, and interactive visualization for chemical research, discovery, development, and industrial applications. Accompanied Drawing [FIGS. 1-2]
Disclaimer: Curated by HT Syndication.
