Deepmind technologies limited (20240321386). TRAINING A NEURAL NETWORK TO PREDICT MULTI-CHAIN PROTEIN STRUCTURES simplified abstract
Contents
TRAINING A NEURAL NETWORK TO PREDICT MULTI-CHAIN PROTEIN STRUCTURES
Organization Name
Inventor(s)
Richard Andrew Evans of London (GB)
Michael James O'neill of London (GB)
Alexander Pritzel of London (GB)
Natasha Olegovna Antropova of London (GB)
Timothy Frederick Goldie Green of London (GB)
TRAINING A NEURAL NETWORK TO PREDICT MULTI-CHAIN PROTEIN STRUCTURES - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240321386 titled 'TRAINING A NEURAL NETWORK TO PREDICT MULTI-CHAIN PROTEIN STRUCTURES
Simplified Explanation: The patent application describes methods, systems, and apparatus for predicting the structure of a protein using a neural network based on the amino acid chains it comprises.
Key Features and Innovation:
- Prediction of protein structure using a neural network.
- Processing protein characteristics to generate a predicted structure.
- Determining the predicted structure based on the network output.
Potential Applications: This technology can be used in bioinformatics, drug discovery, and protein engineering.
Problems Solved: This technology addresses the challenge of accurately predicting protein structures, which is crucial for understanding their functions.
Benefits:
- Improved accuracy in predicting protein structures.
- Enhanced understanding of protein functions.
- Potential for advancements in drug development.
Commercial Applications: The technology can be applied in pharmaceutical research, personalized medicine, and biotechnology industries.
Prior Art: Researchers can explore existing literature on protein structure prediction methods and neural networks in bioinformatics.
Frequently Updated Research: Stay updated on advancements in protein structure prediction algorithms and neural network models for improved accuracy.
Questions about Protein Structure Prediction: 1. How does the neural network process protein characteristics to predict its structure? 2. What are the potential limitations of using neural networks for protein structure prediction?
Original Abstract Submitted
methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting a structure of a protein that comprises a plurality of amino acid chains using a protein structure prediction neural network, where each chain comprises a respective sequence of amino acids. in one aspect, a method comprises: receiving a network input for the protein structure prediction neural network, wherein the network input characterizes the protein; processing the network input characterizing the protein using the protein structure prediction neural network to generate a network output that characterizes a predicted structure of the protein; and determining the predicted structure of the protein based on the network output.
