MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202631044544 A) filed by Birla Institute Of Technology, Ranchi, Jharkhand, on April 7, for 'a system and a method for composite feature fusion-based prediction of enzyme kcat.'
Inventor(s) include Priyanka; Fahad, Md Shah; and Chandra, Ramesh.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The invention relates to a composite system and method for predicting enzyme catalytic turnover numbers (kcat) using feature fusion. The system and method receive an amino acid sequence of an enzyme and a representation of a substrate, divide the sequence into overlapping subsequences, and extract multi-scale features via a dilated convolutional stack with dilation rates of 1, 3, 5, 7, and 9. A hybrid feature-learning module comprising convolutional layers and attention-based interaction processing fuses enzyme and substrate features into composite representations, and a regression prediction module predicts the kcat value and a confidence flag. The system and method perform high-throughput batch processing of enzyme-substrate pairs for identifying rate-limiting enzymes in metabolic pathways, thereby facilitating pathway optimization."
Disclaimer: Curated by HT Syndication.
