**Google AI’s AlphaFold Predicts the Structures of Nearly All Known Proteins**
**Breakthrough in protein folding could accelerate drug discovery and advance understanding of biology**
**London, UK – July 15, 2021** – DeepMind, a research laboratory owned by Google, has announced that its AlphaFold AI system has predicted the structures of nearly all proteins known to science. This is a major milestone in computational biology, as it could accelerate drug discovery and advance our understanding of biology.
Proteins are the building blocks of life, and their structure determines their function. Until now, scientists have only been able to determine the structures of a small fraction of proteins, a process that is time-consuming and expensive. AlphaFold has the potential to change this by rapidly and accurately predicting the structures of proteins, providing scientists with a valuable tool for understanding and treating diseases.
AlphaFold was developed by a team of scientists led by Demis Hassabis, DeepMind’s CEO. The system uses a deep neural network to predict the structure of a protein from its amino acid sequence. Amino acids are the building blocks of proteins, and their order determines the protein’s structure.
In a paper published in Nature, the DeepMind team showed that AlphaFold could predict the structures of proteins with a high degree of accuracy. The system was able to predict the structures of 98% of proteins in a database of 25,000 proteins, and the structures of 90% of proteins in a database of 1 million proteins.
This is a significant improvement over previous methods, which could only predict the structures of a small fraction of proteins with a low degree of accuracy. AlphaFold’s ability to predict the structures of nearly all known proteins is a major breakthrough in computational biology.
AlphaFold could have a major impact on drug discovery. By providing scientists with a rapid and accurate way to predict the structures of proteins, AlphaFold could help scientists to identify new drug targets and design new drugs more quickly and efficiently.
AlphaFold could also advance our understanding of biology. By providing scientists with a detailed understanding of the structures of proteins, AlphaFold could help scientists to understand how proteins function and how they interact with each other.
The development of AlphaFold is a major milestone in computational biology. This system has the potential to accelerate drug discovery and advance our understanding of biology. AlphaFold is a testament to the power of deep learning and the potential of AI to solve some of the most challenging problems in science.
**Additional Information**
* [DeepMind’s AlphaFold website](https://deepmind.com/research/alphafold/)
* [Nature paper](https://www.nature.com/articles/s41586-021-03828-1)
* [DeepMind’s blog post](https://deepmind.com/blog/article/alphafold-a-solution-to-a-50-year-old-grand-challenge-in-biology).
