Invention:
This invention centers on creating a database and algorithms to explore protein functionality and interactions. The aim is to enable significant scientific discoveries, novel drug targeting, and the engineering of synthetic receptors like chimeric antigen receptors (CARs). By studying proteins involved in T cell activation over 450 million years of evolution, the project will develop machine learning and deep learning algorithms to identify critical functional networks within and between proteins. The technology leverages evolutionary data to find previously unknown intra- and inter-protein signaling networks that influence cellular responses. This method will help uncover key protein interactions and regions that drive these responses, guiding the development of new therapies and enhancing our understanding of protein functionality. The ultimate goal is to use this evolutionary-guided approach to inform the design of advanced synthetic receptors and expand therapeutic possibilities.
Background:
This technology addresses the challenge of understanding complex protein interactions and their roles in cellular responses, which is crucial for developing targeted therapies and synthetic receptors. Current solutions often rely on limited datasets and traditional experimental methods that may miss subtle yet critical interactions within and between proteins. These methods can be time-consuming, costly, and may not capture the full range of functional networks due to their scope and resolution limitations. The new approach leverages extensive evolutionary data and advanced algorithms to identify protein networks that have evolved over millions of years. By using machine learning and deep learning, this technology can uncover non-obvious functional networks that traditional methods might overlook. This enables more precise targeting for drug development and the creation of synthetic receptors like CARs with improved functionality. It offers a more comprehensive and efficient way to study protein interactions and may potentially lead to more effective treatments.
Applications:
- Immunology research
- Drug discovery
- Synthetic protein engineering
Advantages:
- Enhanced discovery
- Cost effective
- Leverages advanced computing to find connections faster
