Nominated by: UK BioIndustry Association
Organisation in nomination: DeepMind
An artificial intelligence (AI) network developed by Google AI offshoot DeepMind made a gargantuan leap in solving one of biology’s grandest challenges — determining a protein’s 3D shape from its amino-acid sequence.
DeepMind’s program, called AlphaFold, outperformed around 100 other teams in a biennial protein-structure prediction challenge called CASP, Critical Assessment of Structure Prediction. The results were announced on 30 November 2020.
AlphaFold can predict the shape of proteins to within the width of an atom. The breakthrough will help scientists design drugs and understand disease.
This is a once in a generation advance, predicting protein structures with incredible speed and precision. This leap forward demonstrates how computational methods are poised to transform research in biology and hold much promise for accelerating the drug discovery process.
The ability to accurately predict protein structures from their amino-acid sequence will be a huge boon to life sciences and medicine. It will vastly accelerate efforts to understand the building blocks of cells and enable quicker and more advanced drug discovery.
The AlphaFold program has already helped solve a protein structure that may lead to a better understanding of how signals are transmitted across cell membranes.
The DeepMind team, based in the UK, also hopes to help identify proteins that misfold, leading to malfunctions that cause disease, and to deliver computer models that may speed up drug discovery and development.
- Improved protein structure prediction using potentials from deep learning, Nature, 15 January 2020
- DeepMind AI cracks 50-year-old problem of protein folding, The Guardian, 30 November 2020
- AlphaFold: Using AI for scientific discovery, Blog article
- ‘It will change everything’: DeepMind’s AI makes gigantic leap in solving protein structures, Nature, 30 November 2020
- DeepMind’s protein-folding AI has solved a 50-year-old grand challenge of biology, MIT Technology Review, 30 November 2020