20240029820. COMPUTING AFFINITY FOR PROTEIN-PROTEIN INTERACTION simplified abstract (NANT HOLDINGS IP, LLC)
Contents
COMPUTING AFFINITY FOR PROTEIN-PROTEIN INTERACTION
Organization Name
Inventor(s)
Bing Song of La Canada CA (US)
Shiho Tanaka of Redondo Beach CA (US)
Clifford Anders Olson of Long Beach CA (US)
Phillip Yang of Los Angeles CA (US)
Patrick Soon-shiong of Los Angeles CA (US)
COMPUTING AFFINITY FOR PROTEIN-PROTEIN INTERACTION - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240029820 titled 'COMPUTING AFFINITY FOR PROTEIN-PROTEIN INTERACTION
Simplified Explanation
The patent application describes techniques for computing the affinity for protein-protein interaction using deep learning models and energy scoring. Here is a simplified explanation of the abstract:
- The first and second protein parts are used to generate 3D structure models using a trained deep learning model.
- A 3D structure model of a protein-protein complex is generated using another trained deep learning model.
- Low energy score states are determined for the 3D structure models of each protein part and the protein-protein complex.
- A relax algorithm is applied to the 3D structure models to determine low energy score states.
- An energy score is generated for the 3D structure models based on the low energy score states.
- A score difference is determined between the energy scores, which defines a binding affinity score.
Potential applications of this technology:
- Drug discovery: The ability to accurately compute the affinity for protein-protein interaction can aid in identifying potential drug targets and designing drugs that can effectively bind to specific proteins.
- Protein engineering: Understanding the affinity for protein-protein interaction can help in designing proteins with desired binding properties for various applications, such as biosensors or therapeutic agents.
Problems solved by this technology:
- Accurate prediction of protein-protein interaction affinity: Traditional methods for predicting protein-protein interaction affinity may be time-consuming and less accurate. This technology provides a more efficient and accurate approach.
- Identification of potential drug targets: By accurately computing the affinity for protein-protein interaction, this technology can help in identifying proteins that can be targeted for drug development.
Benefits of this technology:
- Improved drug discovery process: By accurately predicting protein-protein interaction affinity, this technology can aid in the development of more effective and targeted drugs.
- Time and cost savings: The use of deep learning models and energy scoring techniques can potentially reduce the time and cost involved in predicting protein-protein interaction affinity compared to traditional methods.
Original Abstract Submitted
techniques are provided for computing affinity for protein-protein interaction. 3d structure models of the first and second protein parts are generated using a trained first deep learning model. a 3d structure model of a protein-protein complex comprising the first and the second protein parts is generated using a trained second deep learning model. a low energy score state is determined for the 3d structure models of each of the first and second protein parts, and the protein-protein complex. a relax algorithm applied to amino acid side chain and backbone 3d structure models determines a low energy score state for the 3d structure models. based on the low energy score states, an energy score is generated for the 3d structure models, and a score difference is determined between the energy scores, where the score difference defines a binding affinity score.
