After mathematics, biology may become artificial intelligence’s next big testing ground. Mark Zuckerberg and Priscilla Chan’s Biohub has expanded its Virtual Biology Initiative from $500 million to a combined $1.8 billion effort, bringing in the US government, Meta, Google DeepMind and drug-discovery firm Isomorphic Labs. The ambition is to create AI systems that can understand how a living cell reacts to disease, drugs and genetic changes.
The goal is a “virtual cell” — a digital model that can predict a cell’s behaviour before scientists begin costly and time-consuming laboratory experiments. If such predictions become reliable, researchers could quickly identify promising medicines, understand why a treatment fails in some patients, and test many possibilities on computers before taking only the best candidates into real-world trials.
The building blocks are enormous datasets, advanced computing power and new ways of measuring cells under different conditions. The US Department of Energy plans to put more than $500 million over five years into measurement, modelling and computation, while Meta, Google DeepMind and Isomorphic Labs are collectively investing $300 million. The National Institutes of Health will also contribute datasets built through earlier federal investment.
AlphaFold has already shown what AI can do by predicting the structures of nearly all known proteins; that breakthrough helped earn the 2024 Nobel Prize in Chemistry for Demis Hassabis, John Jumper and David Baker. But modelling an entire living cell is far harder than studying one protein: cells constantly change, communicate and react to their environment. The next few years may not deliver a fully mastered human cell, but they could make drug discovery faster, more targeted and less dependent on trial and error.
WHEN AI LEARNS THE LANGUAGE OF CELLS, MEDICINE MAY STOP GUESSING AND START PREDICTING.
Sanjay Sahay
Have a nice evening.