The developers of AlphaFold, an artificial intelligence system for predicting the three-dimensional structure of proteins, are among the winners of the 2023 Lasker Foundation awards. The awards also honored the inventors of optical coherence tomography, a technology that has transformed the field of ophthalmology, and a scientist with a long and storied career who has made important discoveries in multiple fields including oncology and parasitology.
The Lasker Foundation has awarded more than 410 prizes since 1945 recognizing scientists whose contributions have advanced the understanding of human health and biology and improved the diagnosis, treatment, and prevention of human disease.
That long list of winners now includes Demis Hassabis and John Jumper of Google DeepMind, who won the Albert Lasker Basic Medical Research award for the development of AlphaFold, an AI system for predicting protein’s 3D structure from their amino acid sequences. Their work solved the long-standing structure prediction problem that has plagued protein studies for decades. The complexity of 3D protein structures and the sheer number of possible conformations meant scientists had to use time-consuming experimental approaches to try to determine the correct architecture of the proteins they studied.
Computational methods developed to help with structure prediction had some success. One approach developed by David Baker at the University of Washington, for example, used short protein segments from the Protein Data Bank to predict protein architecture but the strategy was slow and not broadly applicable across proteins.
Things changed in 2018 when Hassabis, Jumper, and their team released AlphaFold. Their first iteration of the solution, AlphaFold1, outperformed other computational protein prediction approaches in the 13th edition of the Critical Assessment of Structure Prediction competition, a biannual community initiative that challenges participants to use their methods to predict protein structures directly from amino acid sequences. The challenge used proteins whose structures have been solved experimentally but not yet made public. Judges compared the submitted structures to the experimental answer and ranked them.
Following their early success, Hassabis, Jumper, and their team continued improving AlphaFold using a combination of computational strategies and collective wisdom on proteins and protein structure. The changes they made included allowing the underlying network to adjust calculations at any point during the predictive process. They also prioritized three-dimensional relationships between amino acids and protein subunits over linear proximity.
These changes paid off handsomely as the updated system, AlphaFold2, made more precise structure predictions even for proteins that lack a template. Once again, it bested other methods during CASP14 in 2020. And the DeepMind team did not stop there. By 2021, they had predicted structures for 350,000 proteins including the roughly 20,000 proteins that make up the human proteome. That same year, they published details of the method in a paper in Nature. Even more impressive is that the scientists have now used AlphaFold2 to predict structures for about 200 million proteins gleaned from all of the organisms sequenced to date. All of this data is publicly available and has been accessed by more than a million investigators worldwide for vaccine and drug design projects as well as to develop gene therapies among other uses.
The Lasker Foundation is also honoring James G. Fujimoto, PhD, David Huang, MD, PhD, and Eric A. Swanson this year. The trio are sharing the 2023 Lasker-DeBakey Clinical Medical Research award for inventing optical coherence tomography (OCT), a technology that uses light beams to visualize microscopic structures in body tissue.
The technology has had its biggest impact in the field of ophthalmology where it is used to rapidly detect conditions that lead to impaired vision including diabetic retinopathy, glaucoma, and macular degeneration often before patients experience physical symptoms. Beyond ophthalmology, the technology is also used to assess medical conditions in the heart, brain, skin, and digestive tract. Increasingly, cardiovascular specialists use OCT to evaluate plaque buildup and guide stent placement inside blocked arteries. OCT has also been used to diagnose skin cancer and measure neurodegeneration from multiple sclerosis and other neurologic conditions.
OCT’s development grew out of Fujimoto’s interest in finding practical applications for ultrafast lasers that generate extremely short pulses of light. He recruited Huang and Swanson to work with him on possible applications of these lasers in eye surgery and for measuring the thickness of eye structures. Together, they developed what would become the first OCT system, which scanned a beam of light across tissue structures to develop images that could reveal microscopic structures inside the retina and the coronary artery. They published their first paper on the technique in 1991.
The technology has come a long way since its early days. An important application is its use in stratifying patients with age-related macular degeneration for treatment with an anti-VEGF antibody. The treatment blocks the inappropriate blood vessel formation that characterizes the condition and can cause blindness but it does not work for all patients. OCT helps doctors identify which patients would best benefit from the therapy and when additional treatment is needed.
“It’s a great honor to receive the Lasker-DeBakey Award with my fellow OCT co-inventors,” Huang, now director of research and associate director of the OHSU Casey Eye Institute, and professor of ophthalmology and biomedical engineering in the OHSU School of Medicine, said in a statement. He continues to improve the technology through research at the Center for Ophthalmic Optics and Lasers at OHSU. Swanson and Fujimoto are both at the Massachusetts Institute of Technology.
“OCT may not be as well-known as other major imaging modalities, such as MRI or CT scans, but if you have a serious eye condition, chances are that you received an OCT scan to help diagnose and manage your condition,” Huang said. “I am proud that millions of people have benefited from a technology that I helped invent three decades ago.”
The final award, the Lasker-Koshland Special Achievement Award in Medical Science, went to Pier Borst, former group leader and scientific director at the Netherlands Cancer Institute in recognition of his 50-year career of scientific discovery, mentorship, and leadership. Among other discoveries, his research has helped reveal how the parasite that causes African sleeping sickness evades the immune system and provided insights into the activity of molecular pumps in cancer drug resistance.
The winners will receive their awards at a gala ceremony in New York City on September 29.