DeepMind AI cracks 50-year-old problem that could revolutionise the way we treat disease

The solution to the so-called 'protein folding problem' could lead to new treatments for cancer, dementia and even COVID-19.

Published: November 30, 2020 at 4:36 pm

A problem dating back five decades may have been cracked by Google's DeepMind artificial intelligence team, paving the way for faster development of treatments and drug discoveries.

The so-called 'protein-folding problem' has long been one of biology’s biggest challenges because there are so many proteins and their 3D shapes are difficult to map out.

Almost all diseases, including cancer, dementia and even infectious diseases such as COVID-19, are related to the way these proteins function.

DeepMind is planning to submit a paper detailing its system to a peer-reviewed journal to be scrutinised by the wider scientific community.

Read more about artificial intelligence:

Google-owned AI lab DeepMind, based in London, says its AlphaFold programme has solved the 50-year-old issue and is capable of predicting the shape of many proteins.

There are 200 million known proteins at present but only a fraction have actually been unfolded to fully understand what they do and how they work.

They say the system is able to determine highly accurate structures in a matter of days.

DeepMind has worked on the AI project with the 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), a group of scientists who have been looking into the matter since 1994.

“Proteins are extremely complicated molecules, and their precise three-dimensional structure is key to the many roles they perform, for example the insulin that regulates sugar levels in our blood and the antibodies that help us fight infections,” Dr John Moult, chair of CASP14, said.

“Even tiny rearrangements of these vital molecules can have catastrophic effects on our health, so one of the most efficient ways to understand disease and find new treatments is to study the proteins involved.

“There are tens of thousands of human proteins and many billions in other species, including bacteria and viruses, but working out the shape of just one requires expensive equipment and can take years.”

During the latest test, DeepMind said AlphaFold determined the shape of around two-thirds of the proteins with accuracy comparable to laboratory experiments.

But researchers behind the project say there is still more work to be done, including figuring out how multiple proteins form complexes and how they interact with DNA.

“This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology,” said Prof Venki Ramakrishnan, Nobel Laureate and president of the Royal Society.

“It has occurred decades before many people in the field would have predicted.

“It will be exciting to see the many ways in which it will fundamentally change biological research.”

Reader Q&A: When we start uploading our brains to computers, will our sense of self be uploaded too?

Asked by: Cian McCarthy, Cork, Ireland

Our sense of self emerges from the activity of a poorly understood network of neurons, glial cells and blood vessels in the brain, which together produce the electrical and chemical processes that give us our thoughts and consciousness.

One day, it might be possible to scan all of this activity with perfect fidelity – this would be a hugely intensive process, involving recording the activity of every cell and chemical at an atomic level. This digital scan could be turned into a computer simulation, essentially allowing you to go on living after death. In theory, the simulated version of your brain would believe that its sense of self had been successfully uploaded, transferred from a biological body to an artificial one.

However, it’s not quite as simple as that. If scientists can develop a way to perfectly scan the brain without destroying it (which isn’t a given), then your original brain (and sense of self) would still exist, trapped in a body that will eventually fail. Your digital self might come to the realisation that it’s a copy, triggering an existential crisis.

And what if someone decides to make a hundred copies of this digital self? Now there are a hundred digital versions of ‘you’, each with its own sense of self. Is each of these selves equally valid? Does the second sense of self know that it’s the original copy, and thus expect a higher status? Could the separate selves decide to share their experiences and become a super-intelligent ‘hive mind’?

We don’t yet know the answers, but one way to limit any potential complications might be to become immortal piece by piece. We naturally change as we age, so if you slowly replaced failing biological tissue with computerised prostheses, then by the time all of your body and brain had been replaced, your sense of self will have been transferred without leaving behind a biological remnant.

Just watch out for the delete key… a digital brain is much easier to wipe than an organic one!

Read more: