AlphaFold: The Life Database aims to enable scientific breakthroughs

There is not a single cell in our body that can do without it: proteins are the basic building blocks of living organisms. Your blueprint is embedded in the DNA. Proteins include components of the immune system, such as antibodies, as well as hormones such as insulin or enzymes that break down lactose in the small intestine and make milk compatible.

Exactly how a protein functions in the body depends not only on the arrangement of the atoms from which it is made, but also on its structure: the long chains of amino acids that make up proteins wind up into complex three-dimensional structures. Their decoding is often considered tedious and time-consuming; The X-ray crystal structure analysis method is mainly used.

At the end of last year, researchers from the British company DeepMind, a subsidiary of Google holding company Alphabet, had Reported success with a new approach. Thus, the artificial intelligence (AI) developed by those called AlphaFold can accurately predict the structures of molecules.

Now the team about Catherine Tunyasofonakul, John Jumper and Demis Hassabis from DeepMind has an application of the method in a dedicated article. im ‘nature’ magazine to come. The result is a freely accessible database containing several thousand protein structures. They should be used for breakthroughs in medical research, but also in plant breeding — or to develop bacteria that can break down plastic in the environment.

Almost the full amount is covered for all of the 20,000 proteins that occur in humans, called proteomes, but with varying levels of precision. In addition, there are tens of thousands of other proteins that play a role in other model organisms important for research, such as mice, fruit flies and E. coli bacteria.

Knowing the structure is very important because it can be used to predict how other molecules will bind to a protein – that is, what effect a particular substance will have in practice.

“We believe this is the most complete and accurate picture of the human proteome to date,” says Hases, who is also the head of DeepMind. His company also sees “this work as the most important contribution that artificial intelligence has made to the advancement of scientific knowledge.”

“This will revolutionize our understanding of how life works.” Says Edith Hurd of the European Molecular Biology Laboratory (EMBL) in Heidelberg. “Possible applications are only limited by our imagination.” The database of protein structures in EMBL will be maintained in the future. and Jeera Bhabha, who studies cell biology at New York University, praise Time saved for projects in different areas of research: “No matter if you study neuroscience or immunology – whatever your field of biology – this can be helpful.”