John Jumper

John Jumper received his PhD in Chemistry from the University of Chicago, where he developed machine learning methods to simulate protein dynamics. Prior to that, he worked at D.E. Shaw Research on molecular dynamics simulations of protein dynamics and supercooled liquids. He also holds an MPhil in Physics from the University of Cambridge and a B.S. in Physics and Mathematics from Vanderbilt University. At DeepMind, John is leading the development of new methods to apply machine learning to protein biology.

The Work:

Proteins are essential to life, supporting practically all its functions. They are large complex molecules, made up of chains of amino acids, and what a protein does largely depends on its unique 3D structure. Figuring out what shapes proteins fold into from their amino acid sequence is known as the ‘protein structure prediction problem’ and has stood as a grand challenge in biology for the past 50 years. With their team at DeepMind, Demis Hassabis and John Jumper have developed the artificial intelligence (AI) system AlphaFold, which today can predict the structure of a protein, at scale and in minutes, down to atomic accuracy.

Hassabis had long suspected that protein structure prediction might be the perfect problem for AI to tackle. He was the project leader on the AlphaFold project from its inception in 2016 to its conclusion, and recruited Jumper to the project in late 2017. In 2018 the team was expanded, with Jumper becoming the new research lead, with the goal to re-design the system with a completely new architecture into what would become AlphaFold2. Together they co-supervised the subsequent projects to create the most accurate and complete picture of the human proteome and predict the structures of nearly all known proteins, and released an open-access database to make all of AlphaFold’s predictions freely available to the scientific community.     

In a major scientific advance, in 2020 AlphaFold2 was recognized as a solution to the 50-year grand challenge of protein structure prediction by the organizers of the biennial Critical Assessment of Protein Structure Prediction (CASP).

The Impact:

AlphaFold has culminated in the creation of structure predictions for over 200 million proteins - nearly every protein known to science - which DeepMind has made freely available through the AlphaFold Protein Structure Database (AlphaFold DB).

Designed in partnership with European Molecular Biology Laboratory - European Bioinformatics Institute (EMBL-EBI), the AlphaFold DB serves as a ‘google search’ for protein structures, providing researchers with instant access to predicted models of the proteins they're studying, which has the potential to accelerate every field of study in biology.

Since launch, the AlphaFold DB has already been accessed by 1 million researchers and users in 190 countries. The program dramatically reduces the time scientists typically spend determining protein structure and demonstrates the impact AI can have on scientific discovery and its potential to accelerate progress in some of the most fundamental fields that explain and shape our world. Further, this research will help to better our understanding of disease, and accelerate the development of new targeted drugs.