Project Grant 2151679

This three-year Project Grant from the National Science Foundation's Mathematical and Physical Sciences program (CFDA 47.049) provides $163,901 to Saint Joseph's University to develop integrated moment-based descriptors and deep neural networks for screening three-dimensional biological data. The research aims to advance tools for analyzing large volumetric image datasets from multiple imaging modalities. It will extend mathematical moments to encompass fractional-order descriptors for more accurate 3D image representation and integrate the new moment-based approach into a deep neural network for high accuracy and efficiency in classifying 3D data. A publicly available biomolecular 3D image web server will be implemented for screening protein ligand-binding pockets, functional sites, and drug molecules. The techniques are expected to apply broadly to medical and other imaging disciplines and substantially influence machine learning domains. The funding also supports multidisciplinary education and research collaboration between Saint Joseph's University and Purdue University.