18038333. Protein Structure Prediction simplified abstract (Microsoft Technology Licensing, LLC)
Contents
Protein Structure Prediction
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Protein Structure Prediction - A simplified explanation of the abstract
This abstract first appeared for US patent application 18038333 titled 'Protein Structure Prediction
Simplified Explanation
The patent application proposes a solution for predicting protein structures using a fragment library. Here are the key points:
- The solution determines multiple fragments for each residue position of a target protein from a fragment library.
- Each fragment consists of multiple amino acid residues.
- A feature representation of the structures of these fragments is generated for each residue position.
- Based on these feature representations, the solution predicts the structure or structural property of the target protein.
- This approach utilizes the structural information from fragment libraries to enhance protein structure prediction accuracy.
Potential Applications:
- Protein structure prediction in drug discovery and development.
- Understanding protein folding and misfolding in diseases.
- Designing and engineering proteins with specific functions.
Problems Solved:
- Protein structure prediction is a complex task due to the vast number of possible conformations.
- Existing methods may lack accuracy and rely on limited information.
- This solution addresses these issues by leveraging fragment libraries to provide additional structural information.
Benefits:
- Improved accuracy in protein structure prediction.
- Complementary information from fragment libraries enhances the prediction process.
- Enables better understanding of protein structures and their functions.
- Facilitates drug discovery and protein engineering efforts.
Original Abstract Submitted
According to implementations of the present disclosure, a solution is proposed for protein structure prediction. In this solution, from a fragment library for a target protein, a plurality of fragments is determined for each of a plurality of residue positions of the target protein. Each fragment comprises a plurality of amino acid residues. Then, a feature representation of structures of the plurality of fragments is generated for the each residue position. Next, a prediction of at least one of a structure and a structural property of the target protein is determined based on the respective feature representations generated for the plurality of residue positions. In this way, the solution can leverage structural information of fragment libraries to complement and complete information used in protein structure prediction, and the accuracy of protein structure prediction is thus improved.
