I was a beta tester for the Nobel Prize-winning AI AlphaFold – it will revolutionize health research

Deep learning machine AlphaFoldwhich was created by the Google AI research lab Deep Mindis already changing our understanding of the molecular biology underlying health and disease.

One half Nobel Prize 2024 in Chemistry went to David Baker from the University of Washington, USA, and the other half awarded jointly Demis Hassabis AND John M. Jumperboth from London-based Google DeepMind.

If you haven’t heard of AlphaFold, it may be tough to appreciate how essential it is becoming to researchers. However, as a beta tester of the software, I had the opportunity to see firsthand how this technology could reveal the molecular structures of various proteins in a matter of minutes. It would take researchers months or even years to separate these structures in laboratory experiments.

Read more: Google Deepmind founder shares Nobel Chemistry prize for artificial intelligence that unlocks protein shape

This technology could pave the way for modern, revolutionary therapies and drugs. But first, it’s essential to understand what AlphaFold does.

Proteins are created as a result of a series molecular “beads”created from the selection of the human body 20 different amino acids. These beads form a long chain that folds into mechanical shape this is crucial for the functioning of the protein.

Their sequence is determined by DNA. And although DNA testing means that we know the order of the beads that make up most proteins, predicting how the chain will assemble into each “3D machine” has always been a challenge.

These protein structures form the basis of all biology. Scientists study them in the same way that you might take a clock apart to understand how it works. Understand the parts and put the whole together: it’s the same with the human body.

Proteins are small, and there are huge numbers of them in each of them our 30 trillion cells. This meant that for decades the only way to determine their shape was through laborious experimental methods – research that could take years.

Throughout my career, like many other scientists, I have been engages in such activities. Every time we solve a protein structure, we put it into a global database called Protein Data Bankwhich everyone can operate for free.

AlphaFold was trained on these structures, most of which were used X-ray crystallography. In this technique, proteins are tested in thousands of different chemical states, with changes in temperature, density and pH. Scientists operate a microscope to determine the conditions under which each protein assembles into a specific formation. They are then exposed to X-rays to determine the spatial arrangement of all the atoms in the protein.

After being trained in these designs, AlphaFold can now do just that predict the structure of a protein at speeds that were previously impossible.

I started at the beginning of my career, in the overdue 1990s, developing protein structures using the magnetic properties of their nuclei. I did this using a technology called nuclear magnetic resonance (NMR), which uses a huge magnet similar to an MRI scanner. This method started to fall out of favor due to some technical limitations, but now it is is experiencing a rebirth thanks AlphaFold.

NMR is one of the few techniques that can study molecules in motion, rather than holding them stationary in a crystal or on an electron microscope grid.

An addictive experience

In March 2024, DeepMind researchers asked me to test the beta version of AlphaFold3, the latest incarnation of the software that was close to release at the time.

I’ve never been a gamer, but I got a taste of the addictive experience because once I gained access, all I wanted to do was spend hours trying out molecular combinations. In addition to lightning-fast speed, this modern version introduced the ability to incorporate larger and more diverse molecules, including DNA and metals, as well as the ability to modify amino acids to mimic chemical signaling in cells.

Our laboratory at King’s College London used X-ray crystallography predict the structure formed by two bacterial proteins that are loosely involved in hospital superbugs when they interact. Previous incarnations of AlphaFold predicted individual components but could never solve the problem correctly – and yet the modern version solved the problem the first time.

Understanding the moving parts and dynamics of proteins is the next frontier now that we can predict the inert shapes of proteins using AlphaFold. Proteins come in a huge variety of shapes and sizes. They can be inflexible or versatile, or made of carefully structured units connected by versatile loops.

Dynamics are vital for protein function. As another Nobel Prize winner – said Richard Feynman: “Everything that living things do can be understood in terms of the oscillations and vibrations of atoms.”

Another great feature of magnetic resonance techniques is the ability to precisely measure the distances between atoms. So, after some carefully designed experiments, AlphaFold’s results can be verified in the laboratory.

In other cases, the results are still inconclusive. This is a work in progress between experimental structural biologists like my team and computational scientists.

The recognition that comes with a Nobel Prize will only spur the pursuit of understanding the entire molecular machinery and hopefully change the landscape when it comes to drugs, vaccines and human health.