Recent studies in artificial intelligence (AI) have shown promise in predicting protein clustering, an important step in understanding how proteins interact with each other and how they can be used for drug development. Researchers at the University of California San Diego, have developed a new base of tools to help improve the accuracy of these predictions.

The team used a combination of deep learning and graph-based algorithms to create the new base of tools. Deep learning is a form of AI that uses algorithms to learn from data and make predictions; while graph-based algorithms are algorithms that use graphs and nodes to represent relationships between data points. By combining the two, the researchers were able to create a more accurate prediction model. The model was tested on a database of more than 1,000 proteins, and the results showed that the new method was more accurate than existing methods. This could lead to a better understanding of how proteins interact and could potentially improve the development of new drugs.

Read Full Article Here

source: Phys.org