DeepMind, an artificial intelligence lab, revealed technology in 2020 that could predict the form of proteins – the tiny mechanics that control the activity of the human body and all other living things.
A year later, the researchers disclosed projected structures for more than 350,000 proteins, including all proteins encoded by the human genome, using the technology dubbed AlphaFold. It quickly changed the direction of biological research. Scientists who can determine the structures of proteins will be able to better comprehend illnesses, develop new medications, and investigate the secrets of life on Earth.
DeepMind has now predicted virtually every protein known to science. On Thursday, the London-based lab, which is owned by the same parent firm as Google, said that it has contributed more than 200 million predictions to an online database that is freely accessible to academics worldwide.
DeepMind scientists believe that this latest release will accelerate research into more esoteric creatures and spawn a new area called metaproteomics.
“Scientists may now scan this full database and seek for patterns — connections between species and evolutionary trends that may not have been apparent until now,” DeepMind CEO Demis Hassabis said over the phone.
Proteins start as chemical compound strings that twist and fold into three-dimensional forms that dictate how these molecules bind to one another. Scientists can figure out how a protein works if they can identify its form.
This information is frequently essential in the battle against illness and disease. Bacteria, for example, resist drugs by expressing certain proteins. If scientists can figure out how these proteins work, they will be able to combat antibiotic resistance.
Previously, determining the structure of a protein required lengthy testing on a lab bench using X-rays, microscopes, and other equipment. AlphaFold can now estimate the structure of a protein based on the string of chemical molecules that make it up.
Technology is not without flaws. According to independent benchmark testing, it can predict the structure of a protein with an accuracy that rivals physical experiments around 63 percent of the time. With a forecast in hand, scientists can swiftly verify its correctness.
The technology has “supercharged” this effort, according to Kliment Verba, a researcher at the University of California, San Francisco, who utilizes it to comprehend the coronavirus and prepare for comparable pandemics. This frequently saves months of testing time. Others have employed the gadget in their battles against Parkinson’s illness, malaria, and gastroenteritis.
The advancement of technology has also pushed study into areas other than the human body, such as efforts to enhance honeybee health. An even bigger group of scientists can gain comparable advantages from DeepMind’s extended database.