DeepMind scientists and biochemist win Nobel Prize for protein breakthrough

Three scientists, including two from Google DeepMind, have been awarded the 2024 Nobel Prize in Chemistry for revolutionary advancements in predicting and designing protein structures.

Their work has opened new doors in fields ranging from medicine to nanotechnology, showcasing the immense potential of artificial intelligence (AI) and computational methods in transforming modern science.

The prestigious award has been shared by Demis Hassabis, the founder of Google DeepMind, and John Jumper, a lead developer of the AlphaFold model.

AlphaFold is an AI model designed to predict the structure of proteins based on their chemical sequences, a monumental achievement that has reshaped the scientific understanding of proteins and their functions. The duo shares half of the Nobel prize.

The other half of the award was presented to Professor David Baker of the University of Washington. Baker’s work in computational protein design has led to the creation of entirely new kinds of proteins, which have significant applications in vaccines, nanomaterials, and tiny sensors.

His research marks a turning point in protein engineering, creating possibilities for designing custom proteins that do not naturally exist.

The Royal Swedish Academy of Sciences announced the winners in Stockholm, highlighting the shared prize of 11 million Swedish kronor (approximately £810,000) for their contributions to computational protein design and protein structure prediction.

The emotional announcement

Hassabis and Jumper learned about their Nobel Prize just minutes before the official announcement. Hassabis remarked, “I don’t think they had either of our numbers,” explaining how his wife missed multiple Skype calls from a Swedish number.

“It’s an unbelievable honour of a lifetime to receive the Nobel prize,” he expressed . “I spent my whole life working on AI, dreaming of this kind of impact … where we can use it for the benefit of society.”

Following the announcement, Baker shared insights into his 20-year journey to create entirely new proteins. He noted that recent advances in computing and scientific understanding have enabled this vision to come to fruition. This includes the design of novel vaccines for coronavirus.

“We glimpsed at the beginning that it might be possible to create a whole new world of proteins that address a lot of the problems faced by humans in the 21st century,” Baker said . “Now it’s becoming possible.”

The significance of protein discovery

Heiner Linke, chair of the Nobel committee for chemistry, emphasized the significance of their discoveries. “One of the discoveries being recognised this year concerns the construction of spectacular proteins. The other is about fulfilling a 50-year-old dream: predicting protein structures from their amino acid sequences. Both of these discoveries open up vast possibilities.”

Proteins are essential for life, playing critical roles in hormone production, immune response, and tissue formation. Baker’s mission is to design new proteins that do not occur in nature.

In 2003, he achieved this goal and has since created novel proteins with wide-ranging applications in medicine and materials science.

Proteins consist of 20 different amino acids linked in long chains that fold into complex three-dimensional structures. These structures, along with their chemical composition, determine how proteins will interact with other molecules, such as drugs.

For decades, scientists grappled with the “prediction problem,” which aimed to deduce a protein’s three-dimensional structure from its chemical sequence. This challenge seemed insurmountable, and progress was slow.

The breakthrough of AlphaFold 2

A breakthrough occurred four years ago when Hassabis and Jumper introduced the AI model AlphaFold 2. Jumper explained that deep learning models offered the necessary mathematical framework to address the “irreducible complexity of biology.”

AlphaFold 2 has enabled researchers to predict the structure of nearly all of the 200 million proteins identified. Since its launch, more than 2 million researchers from 190 countries have utilized AlphaFold 2 for various applications, including antibiotic resistance studies and the development of enzymes that can decompose plastic.

Hassabis highlighted AlphaFold as a demonstration of AI’s capacity to accelerate scientific discovery and benefit society. However, he cautioned that AI, as a “dual purpose technology,” also has the potential for misuse.

“I’ve always felt it would be one of the most transformative technologies in human history,” he stated. “We really have to think very hard … about how to empower the good use cases while mitigating … the bad use cases. It carries risks as well, and we need to be aware of those.”