John Jumper​

Research

Proteins perform a variety of vital roles inside cells. Their diverse functions are closely linked to the forms they take after they fold from linear amino acid chains into three-dimensional (3D) structures. Predicting their 3D structure from the sequence of their amino acids has been the grand challenge in biology for over 50 years and central to understanding the workings of life. Conventional methods that have taken years and millions of dollars are being replaced by novel AI-driven technologies. Dr Jumper has been at the forefront of these efforts.

Dr Jumper joined Hassabis in Google DeepMind in late 2017 to work on the nascent AlphaFold project. In 2018, he became the research lead, with the goal of redesigning the system with a completely new architecture. The advent of AlphaFold2 has presented unparalleled progress in protein structure prediction. This highly accurate system has made structure predictions for over 200 million proteins; they cover almost all documented proteins – not only of humans but also of animals, plants, fungi, bacteria, and viruses.

DeepMind has made these structure predictions freely available through the AlphaFold Protein Structure Database. Designed in partnership with the European Molecular Biology Laboratory-European Bioinformatics Institute (EMBL-EBI), the AlphaFold public database serves as a “google search” for protein structures, providing researchers and pharmaceutical companies with instant access to accurate predicted models of the proteins they are studying. Professor Ewan Birney, EMBL-EBI Director, states that it will be “one of the most important datasets since the mapping of the Human Genome”. Since its launch, it has been accessed by over a million researchers and users across 190 countries.

The AlphaFold2 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 of biology. This research will help to better our understanding of disease and to accelerate the development of new targeted drugs. Furthermore, this work is being used to accelerate progress on important real-world problems, ranging from antibiotic resistance to plastic pollution and food insecurity.