There are more than 200 million known proteins. As the building blocks of life, proteins underpin every biological process in every living thing. Each one has a unique 3D shape that determines how it works and what it does. For decades, scientists have been trying to find a method to reliably determine a protein's structure just from its sequence of amino acids, but figuring out the exact structure of a protein was an expensive and often time-consuming process — sometimes taking years and millions of dollars.

DeepMind, part of Alphabet, created an AI system called AlphaFold which can predict the shape of a protein, at scale and in minutes, down to atomic accuracy. In partnership with EMBL's European Bioinformatics Institute, the AlphaFold Protein Structure Database freely shares predictions for over 200 million proteins.

AlphaFold predictions have already been accessed by more than half a million researchers and are having a significant, direct impact on human health. Researchers at the European Society of Human Genetics revealed how important AlphaFold structures are to biologists and clinicians trying to unravel the causes of rare genetic diseases. In addition, AlphaFold is accelerating drug discovery by providing a better understanding of newly identified proteins that could be drug targets, and helping scientists to more quickly find potential medicines that bind to them.

- Professor Ewan Birney, European Molecular Biology Laboratory Deputy Director General and EMBL-EBI Director