HAI 2020 Nomination – DeepMind/AlphaFold

Towards the end of 2020, Google DeepMind announced that they developed an AI network (AlphaFold) that determines a protein’s 3D shape from its amino-acid sequence.

The ability to accurately predict protein structures from their amino-acid sequence would vastly accelerate efforts to understand the building blocks of cells and enable quicker and more advanced drug discovery. AlphaFold has been recognised as a solution to this grand challenge by the organisers of the biennial Critical Assessment of protein Structure Prediction (CASP).

CASP was founded in 1994 by Professor John Moult and Professor Krzysztof Fidelis as a biennial blind assessment to catalyse research, monitor progress, and establish the state of the art in protein structure prediction. It is considered the gold standard for assessing predictive techniques. After DeepMind’s revelation of its model and accuracy rate this year, Moult stated “In some sense the problem is solved.”

Professor Venki Ramakrishnan, the winner of the 2009 Nobel Prize for Chemistry said “this computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology. It has occurred decades before many people in the field would have predicted.”

Merve Hickok