select search filters
briefings
roundups & rapid reactions
before the headlines
Fiona fox's blog
Scientists comment on the Nobel Prize in Chemistry, awarded for computational protein design and protein structure prediction.
Prof Charlotte Deane, Executive Chair of the UKRI Engineering and Physical Sciences Research Council; and Professor of Structural Bioinformatics, University of Oxford, said:
“Proteins are the functional components in every living organism so being able to predict their shape and design them with a specific shape and function has ramifications across all of medicine, biology and many other areas.
“For example, proteins are the target of most drugs (they are also some of those drugs) so these AI algorithms are already fundamentally changing the way we discover and design new medicines.
“It is an exciting time to be working in science, particularly in these interdisciplinary areas, as AI not only starts solving really hard problems but is also changing the way we do science.”
Prof Andy Cooper, Director of the Materials Innovation Factory and Leverhulme Centre for Functional Materials Design, University of Liverpool; and co-director of the UKRI AI for Chemistry Hub, said:
“The use of AI to predict protein structure is a huge advance with a myriad of uses in biology, medicine, and beyond. AI will impact other areas of chemistry, too, but the protein field has some special features. First, there is a large amount of well-curated training data.
“Second, proteins are structurally complex but compositionally fairly simple — they are built from a quite small selection of building blocks. A challenge for AI in chemistry more broadly is to deal with areas where data are sparse, less systematized, and where compositional diversity is much greater – energy materials is one such example.”
Dr Tom Burnley, Computational Scientist, STFC Scientific Computing, said:
“Today’s Nobel Prize announcement computational protein design and protein structure prediction caps the winners impressive work in structural biology and provides important insights that will help accelerate the development of the next generation of pharmaceuticals and biomaterials. For me, the most exciting thing is this will help us solve many more advanced questions to fully understand the molecular basis of life: how do simple proteins form larger functional complexes, how do proteins move and how do proteins interact in their natural cellular environment. We can predict what an individual looks like but how does it interact with others, how does it dance and where does it go to work?”
Dr Martyn Winn, Computational Biology Theme Leader, STFC Scientific Computing, said:
“AlphaFold has had an incredible effect on research activities in the biomedical sciences over the last few years. The AI model that has been developed builds on the collective effort of the structural biology community over several decades, an effort to which STFC has made an essential contribution via large scale user facilities such as the SRS and Diamond, and community software projects such as CCP4 and CCP-EM. We are now in a new era of structural biology in which, with the ready availability of predicted structures, scientists can ask more sophisticated questions about how these structures function and adapt in living organisms.”
Prof Rivka Isaacson, Professor of Molecular Biophysics at King’s College London, who was an early beta tester of Alphafold, said:
“Anything that brings 3D protein shapes into the limelight makes me happy, so I’m glad to hear that this year’s Nobel in chemistry has gone to protein design and the amazing AlphaFold protein predictor. It has opened up the world of molecular shapes to those looking at the fundamental science underpinning the human body, with the hope of creating possible treatments for disease.
“Proteins do all kinds of important jobs inside our bodies, such as supporting the immune system, and are built by snapping 20 different chemical ‘beads’ or amino acids of a variety of shapes and sizes together. This creates chains which can then fold up into 3D machines with specific capabilities, moving parts, and potential to stick to other proteins to collaborate on complex functions. AlphaFold allows anyone to predict the shapes and interactions of proteins from just knowing the order of their beads, which allows researchers to study how they are linked to health and disease, and what kind of drugs might work with them. People have been trying to do this for years but, using machine learning, DeepMind were able to make great strides in improving and democratising this process.
“I was lucky to be a beta tester for AlphaFold3, a new version which allows us to look at much bigger proteins and a wide variety of molecules with which they can bind, including DNA and metals, than the previous versions of the software did. Scientists like me have traditionally solved protein shapes using laborious experimental methods which can take years. It was these solved structures, which the experimental world deposits for public use, that were used to train AlphaFold. Thanks to this technology, we are better able to skip ahead to probe deeper into protein function and dynamics, asking different questions and potentially opening up whole new areas of research.”
Ilan Gur, Founding CEO of The Advanced Research and Invention Agency, said:
“Huge congrats to ARIA advisor Demis Hassabis. Breaking through the barrier of winning a Nobel outside academia is rare, but this may be the first case in history of the award going to an entrepreneur whose Nobel work was done in the company they founded. Hopefully first of many!”
Prof Ewan Birney, Deputy Director General of EMBL and Director of EMBL-EBI, said:
“Huge congratulations to David Baker, Demis Hassabis, John Jumper and the teams that supported them for this fantastic honour. Tools such as AlphaFold help us understand protein structure, helping us decode how life works; being able to design proteins to our own needs shows how deep our understanding has reached. Such tools are built on decades of experimental work and made possible thanks to a culture inside molecular biology of openly sharing data worldwide. There is a vast treasure trove of public data available in databases such as the ones managed by EMBL. We hope to see these data informing yet more discoveries. The potential of big data alongside AI and technology developments is limitless – and this is the start.”
— Comments below are gathered by the Pilot SMC in Ireland —
Dr Meilan Huang, Senior Lecturer at the School of Chemistry and Chemical Engineering, Queen’s University Belfast, said:
“It’s really exciting news David Baker’s Rosetta and Google Deepmind’s Alphafold has brought a new era for protein structure predictions which many areas would benefit from. It sets a robust cornerstone for addressing further challenges such as rational design or de novo discovery of protein biocatalysts with desired functions for industrially important chemical transformations, using renewable resources from nature.”
https://www.nobelprize.org/uploads/2024/10/press-chemistryprize2024.pdf
Declared interests
Prof Andy Cooper “No conflicts.”
Prof Charlotte Deane “Was a reviewer on AlphaFold and knows all three laureates personally.”
Dr Tom Burnley: None
Dr Martyn Winn: None
Prof Rivka Isaacson: None
Prof Ewan Birney “is the Deputy Director General of the European Molecular Biology Laboratory (EMBL) and the Director of EMBL’s European Bioinformatics Institute (EMBL-EBI), which hosts the AlphaFold Protein Structure Database. He is also a Non-Executive Director at Genomics England. EMBL-EBI collaborated with Google DeepMind to develop and disseminate the AlphaFold Protein Structure Database, making AlphaFold’s predictions freely and openly accessible to the scientific community.”
Ilan Gur: “Demis is an unpaid advisor to ARIA, but otherwise none”
Dr. Meilan Huang: None