TRENDING SCIENCE: Cutting-edge AI to radically change scientific research

Proteins are present in all living organisms and include numerous key biological compounds such as enzymes, hormones and antibodies. To advance medicine, it’s crucial to understand how protein structures operate. To date, only a small percentage of these have been worked out.

Researchers at London-based DeepMind used AI technology called AlphaFold to predict the structures of almost every protein made by our bodies. Together with the European Molecular Biology Laboratory (EMBL), they presented their achievement in the journal ‘Nature’.“We believe it’s the most complete and accurate picture of the human proteome to date. We believe this work represents the most significant contribution AI has made to advancing the state of scientific knowledge to date,” DeepMind co-founder and CEO Dr Demis Hassabis told the ‘BBC’. “And I think it’s a great illustration and example of the kind of benefits AI can bring to society. We’re just so excited to see what the community is going to do with this.” EMBL Director General Prof. Edith Heard stated: “This will be transformative for our understanding of how life works.”

The research team released the most exhaustive and precise online database containing 20 000 proteins expressed by the human genome. It also includes over 350 000 proteins belonging to humans and other organisms, from bacteria and yeast to mice. This number will expand to millions of proteins in the near future. AlphaFold accurately predicted the 3D shape of proteins based on their amino acid sequences. Amino acids are organic compounds that combine to form proteins.Over the years, analysing nearly every protein encoded in the human genome and predicting its likely 3D structure has been both time-consuming and expensive. What’s more, software has lacked accuracy. Until now, we possessed structural information for only 17 % of the complete set of human proteins. AlphaFold made a prediction of the structural positions for 58 % of the proteome’s amino acids. The positions of nearly 36 % were predicted with great certainty.

The 3D structure can provide important information about the protein, like how it interacts with other proteins and chemicals. By using this structure, the scientific community learns how specific mutations change the protein’s function.

From neuroscience to medicine, scientists will be able to speed up their work thanks to the sophisticated AI system. “Making AlphaFold predictions accessible to the international scientific community opens up so many new research avenues, from neglected diseases to new enzymes for biotechnology and everything in between,” commented EMBL Deputy Director General and EMBL-EBI Director Ewan Birney in a press release. “This is a great new scientific tool, which complements existing technologies, and will allow us to push the boundaries of our understanding of the world.”

“The applications are actually limited only by our imagination … the AlphaFold database will increase our understanding of how proteins function, and their role in the fundamental processes of life,” Prof. Heard told ‘The Guardian’. “This understanding means we can be better equipped to unravel the molecular mechanisms of life and accelerate our pursuits to protect and treat human health, as well as the health of our planet ...”