Google’s sister company DeepMind has developed an artificial intelligence program that is able to accurately predict the structure in which proteins will form within days, solving a 50-year-old challenge, and may pave the way for a better understanding of diseases and drug discovery.

Every living cell contains thousands of different proteins that keep them alive and healthy. Predicting what form proteins will turn into is important because it determines their function, knowing that nearly all diseases, including cancer and dementia, are related to how proteins work.

Professor Dame Janet Thornton of the European Institute of Computational Biology told reporters: “Proteins are the most beautiful, most wonderful structure, and being able to accurately predict how they form is really a very difficult challenge, and it has occupied a lot of people for many years.”

The AI ​​system AlphaFold of the British research laboratory DeepMind entered a competition organized by a group called Critical Assessment for Structure Prediction. It is a community experiment organization whose mission is to accelerate solutions to one problem: how to calculate the three-dimensional structure of protein molecules.

The CASP – which has been monitoring progress in the field for 25 years – is comparing competition entries to what is called the (experimental gold standard). On Monday, it said DeepMind’s AlphaFold system has achieved unparalleled levels of accuracy in predicting protein structure.

“DeepMind has made the leap,” said Professor John Molt – President of CASP – in a press call before the announcement. “The great 50-year-old challenge in computer science has largely been solved,” he added. He also added that there are major implications to come in the field of drug design and in the newly emerging field of protein design.

It is noteworthy that DeepMind – a subsidiary of Alphabet, which has nearly 1,000 employees – has emerged in recent years as a leader in the global race in the field of artificial intelligence, along with companies such as Facebook and Microsoft.