Scientists from Google DeepMind have received a $3 million award for developing an artificial intelligence (AI) system that predicts how to fold nearly every known protein into its 3D shape.
One of the Life Sciences Breakthrough Awards this year went to Demis Hassabis, co-founder and CEO of DeepMind, which created the protein prediction program known as AlphaFold, and John Jumper, a senior research scientist at DeepMind, the Breakthrough Prize Foundation. announce (Opens in a new tab) Thursday (September 22).
The open source software makes its predictions based on the amino acid sequence of a protein, or the molecular units that make up the protein, Live Science previously reported. These individual units are linked in a long chain and then “folded” into a three-dimensional shape. The 3D structure of a protein determines what that protein can do, whether that’s cutting DNA or tagging dangerous pathogens for destruction, so the ability to infer what proteins look like from their amino acid sequences is very powerful.
Breakthrough Awards are given to leading researchers in the fields of fundamental physics, life sciences, and Maths. Each award comes with a $3 million prize pool, provided by founding sponsors Sergey Brin; Priscilla Chan and Mark Zuckerberg; Yuri and Julia Milner; Ann Wojcicki.
Related: Two scientists win $3 million ‘breakthrough prize’ for mRNA technology behind COVID-19 vaccines
The foundation’s statement reads: “Proteins are the nanomachines that run cells, and predicting their three-dimensional structure from their amino acid sequences is fundamental to understanding how life works.” “With their team at DeepMind, Hassabis and Jumper have created a deep learning system that accurately and rapidly models the structure of proteins.”
Using AlphaFold, the DeepMind team has assembled a database of nearly 200 million protein structures, including those produced by plants, bacteria, fungi and animals, Live Science previously reported. This database includes almost all indexed proteins known to science.
The AI system “learns” to assemble these shapes by studying known protein structures that have been assembled in existing databases. These protein structures have been painstakingly visualized using a technique called X-ray crystallography, which involves refraction of protein crystal structures using X ray Then measure how diffracted those rays.
Within these existing databases, AlphaFold identified patterns between the amino acid sequences of proteins and their final 3D shapes. Then, using a neural network – an algorithm loosely inspired by how neurons process information in a brain Artificial intelligence has used this information to iteratively improve its ability to predict protein structures, known and unknown.
“It has been so inspiring to see the countless ways the research community has taken AlphaFold, using it for everything from understanding diseases, to protecting honeybees, to deciphering biological mysteries, to researching scientifically deeper into the origins of life itself. statement (Opens in a new tab) Posted in July.
“As pioneers in the emerging field of ‘digital biology,’ we are excited to see the enormous potential of artificial intelligence beginning to be realized as one of humanity’s most useful tools to advance scientific discovery and understanding the fundamental mechanisms of life,” he wrote. .
Originally published on Live Science.
#DeepMind #scientists #won #million #breakthrough #prize #predicts #structure #protein