A 50-year-old science problem has been solved remarkably early with artificial intelligence, researchers have announced. The news could now fast-track how diseases are both treated and cured.
Scientists have long been hampered by an issue known as “protein folding”.
This involves mapping the 3D shapes of the proteins identified as responsible for diseases ranging from coronavirus to cancers.
Google’s Deepmind claims to have created an artificially intelligent program called ‘AlphaFold’ capable of solving those problems within days.
If all goes according to plan, experts suggest the solution has come “decades” earlier than expected, potentially leading to revolutionary ways diseases are treated.
Although 200 million proteins are known to exist, only a fraction have actually been unfolded to fully understand how they work.
And the minority that are understood have relied upon on expensive and time-intensive techniques.
These often involved scientists spending years and millions unfailing each structure.
Google DeepMind worked on the AI project with 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), scientists investigating the matter since 1994.
Dr John Moult, chair of CASP14, said “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.
“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.”
DeepMind has announced AlphaFold understood the shape of around two-thirds of the proteins with accuracy comparable to laboratory experiments.
Asteroid danger: 100% certainty of impact warns space expert [INTERVIEW]
Hubble snaps galaxy ‘like a portal to another dimension’ [PICTURES]
Scientists build ‘self-aware’ robot able to REPAIR ITSELF [ANALYSIS]
DeepMind has published the results of those tests on its website, allowing verification to be made by external scientists.
The team behind the AlphaFold project will next focus on determining how multiple proteins form complexes and their interaction with human DNA.
Professor Venki Ramakrishnan, Nobel Laureate and president of the Royal Society, said: “This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology.
“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.”
Among other revelations, Google DeepMind noted predicted protein structures could play an important role in responding to future pandemics.
Such machine learning technology has already been used on the protein structures of the SARS-CoV-2 virus, responsible for Covid-19.