MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541123042 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'ai-driven molecular generation system for dengue drug discovery.'
Inventor(s) include Dr. Gunavathi C; Mr. Arnav Goenka; Mr. Asad Aziz; and Mr. Kshitiz Goel.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method for generating and evaluating molecular compounds for dengue drug discovery. The method includes collecting a dataset of dengue-related drug compounds represented as SMILES strings, generating synthetic SMILES strings by applying structural modifications to the collected SMILES strings, training a transformer-based machine learning model on the collected SMILES strings to learn molecular representations, processing the synthetic SMILES strings through the trained model to generate molecular embeddings, computing similarity scores between the molecular embeddings of the synthetic and collected SMILES strings, predicting severity scores for the synthetic SMILES strings based on the similarity scores where severity scores indicate potential adverse effect profiles, filtering the synthetic SMILES strings based on predetermined severity score thresholds to identify low-risk molecular candidates, and outputting the filtered synthetic SMILES strings as potential dengue drug candidates."
Disclaimer: Curated by HT Syndication.
