A year ago, DeepMind caused a stir by announcing it could solve the main puzzle in biology – predicting the structure of any protein. At the same time, DeepMind created an open database with data on 350,000 proteins whose shape was predicted by the AlphaFold package. The company today informed about the disclosure of the forms of almost all proteins known to terrestrial science – this is over 200 million proteins from all areas of life known on Earth. This is a real revolution in biology.
Proteins are sequences of amino acids. Depending on the combinations of the amino acids, proteins fold into very bizarre spatial shapes. These shapes determine how proteins interact with one another and ultimately regulate biological processes in living organisms: they interact when the shapes fit together like a key in a lock, and remain indifferent to one another when the shapes do not have compatible spatial structures.
Knowing the spatial shape of a protein can help find the perfect cure for disease and many other discoveries in biology. Before the advent of AI algorithms, scientists used to experimentally determine the shape of proteins, which is very, very difficult and time-consuming. The algorithm proposed by DeepMind determines the spatial shape of a protein from 10 to 20 seconds. Thanks to this, the company was able to increase the database of spatial forms of proteins from 350 thousand to more than 200 million in one year.
It should be made clear that predicting the shape of a protein does not mean being 100% accurate. However, AlphaFold showed significant accuracy in determining shapes, which is enough to start with. All the routine work was done by a computer, and it took all of the world’s scientists 50 years to unravel only about 10% of protein structures.
About half a million scientists from all over the world have already used the open database on proteins, according to the company. The disclosure of the complete database of proteins will activate this process many times over and lead to amazing discoveries in biology in the foreseeable future.