Artificial intelligence leads to a medical revolution in the understanding of proteins
Saturday – 14 Dhu al-Hijjah 1442 AH – 24 July 2021 AD Issue No. [
The structure of a human protein designed by a computer program (AFP)
London: «Middle East»
The researchers used a program called AlphaFold to predict the structures of 350,000 types of proteins belonging to humans and other organisms. The instructions for making human proteins lie in the human genome, and in the DNA found in the nucleus of human cells. There are about 20,000 of these proteins expressed in the human genome. Collectively, biologists refer to this complementary entity as a “proteome”.
Commenting on the results of the AlphaFold program, Dr. Demis Hassabis, CEO and co-founder of DeepMind Artificial Intelligence, said: “We believe it is the most complete and accurate picture of the human proteome to date.” He added, “We believe that this work represents the most important contribution made by artificial intelligence to the advancement of the state of scientific knowledge so far.”
“I also think it’s a great effort and an example of the kind of benefits that AI can bring to society,” he added. We are very excited to see what the community will do with this progress.” Proteins are made of chains of smaller micro-building blocks called amino acids. These chains are folded in countless different ways, forming a very unique 3D image. The shape of the protein determines its function in the human body.
The 350,000 protein structures predicted by AlphaFold include not only the 20,000 found in human proteins, but also those found in so-called model organisms used in scientific research, such as E. coli, yeast, fruit flies and mice. Researchers at DeepMind and a team from the European Molecular Biology Laboratory described this giant leap in scientific capabilities in the prestigious scientific journal Nature.