Proteins are the doers of biology. In the human body, they do most of the work in cells and are necessary for the structure, function, and regulation of the body’s tissues and organs. Each protein is made of a precise sequence of amino acids that allows it to fold into a three-dimensional shape that determines its function. In the past, the all-important structure of a protein could only be established through difficult and time-consuming laboratory analyses. Now comes a dramatic new twist – a window into the fundamental building blocks of life.
DeepMind, a UK-based company that is part of Alphabet, the parent company of Google, has developed an artificial intelligence and machine learning system that can predict the three-dimensional structure of proteins and decode the amino acids that make up each protein. Last year, the system had 350,000 registrations. On July 28, DeepMind co-founder and chief executive Demis Hassabis announced the expansion of the company’s database of folded proteins to more than 200 million — nearly all of the cataloged proteins known to science, including those in humans, plants, bacteria, animals, and the like. other organisms – and that the company makes them publicly and freely accessible with no more effort than a Google search. The database is called AlphaFold and is the biology equivalent of a James Webb Space Telescope, providing amazing new images of a world beyond.
Proteins don’t fold neatly like dish towels. Many look like a skein of yarn after a cat has played with it. They often have precisely designed moving parts that relate to chemical events and, most importantly, bind to other molecules. For example, antibodies are proteins produced by the immune system that bind to foreign molecules, such as those on the surface of an invading virus, such as the spikes on the coronavirus. Scientists have spent decades looking for the exact folding of proteins and their functions. Researchers have long used a technique known as X-ray crystallography to better understand the structure of proteins, and the field’s central repository contains some 185,000 experimentally resolved structures.
Then came artificial intelligence. AlphaFold algorithms learned to predict protein folding based on the underlying amino acid sequence, leading to an explosion of new information. Another project called RoseTTAFold from the University of Washington’s Institute for Protein Design is on a similar quest. The predictions of protein folding need to be verified, in some cases through real-world experiments. But for drug and vaccine developers who want to know what a protein looks or behaves like, the prediction itself — a visual representation — can provide a remarkable edge. Both the journals Science and Nature Methods named the breakthrough as the most important of 2021.
Using these new methods, researchers have been able to explore the nuclear pore complex, which acts as a kind of gatekeeper for everything that goes in and out of the cell nucleus. It contains more than 1,000 protein subunits woven together, so it is a difficult puzzle for scientists. AlphaFold allowed researchers to create a model almost twice as complete as the old one, which covers two-thirds of the complex.
AlphaFold doesn’t reveal all the mysteries of biology, nor is it the only advancement needed to develop drugs or fight disease. But the views are truly stunning.