On July 28, 2022, Google’s DeepMind released the structure of 200 million proteins, literally everything that exists. This is said to be the most important achievement of AI ever, namely a ‘solution’ to the protein-folding problem.
Proteins are composed of a linear chain of amino acids and their 3D structures determine their functions. Structure determination is laborious. One way to know the optimal folded structure of the protein computationally is to sample all its possible configurations, composed of specific angles between peptide bonds. However, this is an impossible task as a typical protein may have about 10300 configurations and even if a million of them were examined per second, the overall time needed will be unimaginable. That helped save about 1,000 million man-years.
DeepMind’s AlphaFold made an important breakthrough in 2020. It accurately predicted the structures of about 100 proteins to atomic resolution, and no other solution came close to this feat. Many believe that the protein-folding problem is over.
