Google DeepMind Solves 50 Year Old Folding Protein Problem

Breakthrough at Google’s AI unit DeepMind allow researchers to determine a protein’s 3D shape from its amino-acid sequence

Researchers at Google-owned Artificial Intelligence (AI) company DeepMind have solved a “50-year-old grand challenge” in biology known as the ‘protein folding problem.’

The ‘major scientific advance’ with the latest version of the DeepMind AI system (AlphaFold) reveals what shapes proteins fold into. This achievement has been officially recognised as a solution by the organisers of the biennial protein-structure prediction challenge called Critical Assessment of protein Structure Prediction (CASP).

“This breakthrough demonstrates the impact AI can have on scientific discovery and its potential to dramatically accelerate progress in some of the most fundamental fields that explain and shape our world,” blogged the UK-based firm.

healthcare

Scientific breakthrough

“Proteins are essential to life, supporting practically all its functions,” explained DeepMind. “They are large complex molecules, made up of chains of amino acids, and what a protein does largely depends on its unique 3D structure.”

“Figuring out what shapes proteins fold into is known as the ‘protein folding problem’, and has stood as a grand challenge in biology for the past 50 years,” the firm stated.

But why is this development so important?

Well, a protein’s shape is closely linked with its function, and the ability to predict this structure unlocks a greater understanding of what it does and how it works.

According to DeepMind, many of the world’s greatest challenges, like developing treatments for diseases or finding enzymes that break down industrial waste, are fundamentally tied to proteins and the role they play.

“We have been stuck on this one problem – how do proteins fold up – for nearly 50 years,” explained Professor John Moult, co-founder and chair of CASP, University of Maryland.

“To see DeepMind produce a solution for this, having worked personally on this problem for so long and after so many stops and starts, wondering if we’d ever get there, is a very special moment,” he added.

Faster drug development

And the breakthrough has prompted reaction from AI experts.

“The Covid-19 pandemic has propelled artificial intelligence (AI) into the limelight,” said Nikolas Kairinos, CEO at Soffos.ai. “A phenomenon born out of necessity, machines have been pivotal in ensuring sick patients get the medical care that they need, and that the virus can be controlled as much as possible.”

“DeepMind’s latest breakthrough has highlighted the huge potential of AI systems in the medical space going forward,” said Kairinos. “Not only is AI a temporary solution to stem the tide of infections, but it can deliver improvements across all areas of healthcare. The protein structure problem is a challenge researchers have been working on for many years, and which held the promise of opening up new opportunities for drug development.”

“DeepMind’s discovery will advance our understanding of fundamental scientific problems, and enable us to develop better, and faster, treatments for a whole host of medical ailments – from infectious diseases to cancer,” said Kairinos.

“With the right combination of human and artificial intelligence, machines are a powerful force for good,” Kairinos concluded. “The challenge is to build public trust in AI and showcase its enormous potential to improve our lives; DeepMind’s breakthrough will undoubtedly help that cause.”