AI Term of the Moment

Digital Optimus


Look Up Another Term


Redirected from: protein folding

Definition: AlphaFold


A Google DeepMind AI program that predicts protein structure. In 2018, AlphaFold 1 ranked first in Critical Assessment of Structure Prediction (CASP), a worldwide experiment every two years. In 2020, AlphaFold 2 was considered transformational and AlphaFold 3 showed at least a 50% improvement in 2024.

From Months to Minutes
Taking from minutes to hours instead of months and years, AlphaFold predicts the 3D shape of a protein from its one-dimensional amino acid sequence. Proteins are the building blocks of life or more accurately the "molecular machines of life," and the shape of a protein determines what drug molecules can lock onto it. Being able to quickly predict how proteins fold means new medicines can be created so much faster than the traditional mapping methods.

The Nobel Prize
Along with David Baker from the University of Washington, DeepMind founder Demis Hassabis and John Jumper were awarded the Nobel Prize in Chemistry in 2024 for their work in this field. See DeepMind and AI optimism.