British scientists have used artificial intelligence (AI) to create a database of the “entire protein universe” that could help pave the way for a cure for Parkinson’s as well as other scientific advances.
DeepMind, a London-based company owned by Alphabet, the Silicon Valley tech giant that owns Google, first revealed its AlphaFold technology last year when it contained the 3D shape and structure of about 350,000 proteins
The database has now expanded to more than 200 million proteins, which is almost every protein known to science and covers animals, proteins, bacteria and everything in between.
By discovering precisely what proteins actually look like from their genetic code, scientists can predict how they will interact with other proteins, antibodies and drugs.
“When we launched last July it was recognized as a huge leap forward for biology,” said Dr. Demis Hassabis, CEO and founder of DeepMind.
“It was also a great demonstration of how AI can be used to advance scientific discovery and has provided structural biologists with this powerful new tool to look up the 3D structure of a protein almost as easily as doing a keyword search on Google and, as we know, the 3D structure of proteins is vital to understanding their function.
“You can think [AlphaFold] as covering the whole protein universe”.
He added that more than half a million scientists have already used the ever-expanding directory for a myriad of projects.
“A whole universe in one click”
Professor Ewan Birney, deputy director-general of the European Molecular Biology Laboratory (EMBL), which helped develop AlphaFold with DeepMind, added that it was “remarkable” that the entire protein universe is now available with just one or two clicks.
“It will make many researchers around the world think about what experiments they could do,” he said.
AlphaFold has been touted as one of the most important scientific breakthroughs in recent years and has the potential to revolutionize several fields, including pharmacology, agronomy and vaccine manufacturing. It is also used to address the existential problems of plastic pollution and antibiotic resistance.
An important avenue that is being helped by AlphaFold’s technological vision is that of disease treatment.
Scientists from Duke University and the National University of Singapore published a paper in May based on the results made possible by AlphaFold.
They focused on a protein called phosphoprotein 1 (STIP1) that they were able to identify as something that helps protect the brain, but is targeted and destroyed by the immune system in Parkinson’s patients.
Before now, the structure of this protein was never known in detail, and AlphaFold was able to accurately predict the structure based on the DNA and amino acid arrangement of the protein.
This, the researchers said, was in “excellent agreement” with the blurrier picture of the protein made by experiments.
By enabling researchers to overcome their technological and laboratory obstacles, AlphaFold has elevated almost every field of biology. It is a watershed moment for the life sciences and will bear fruit in many different fields in the coming years.
“AlphaFold was transformative”
Professor Matt Higgins, professor of molecular parasitology at the University of Oxford, is using AlphaFold to fight malaria by creating new vaccines against the mosquito-borne parasite.
His protein of interest had always been “fuzzy,” despite years of lab work, he said.
“Using AlphaFold was truly transformative, giving us a very sharp view of this maaria surface protein,” said Professor Higgins.
This has led to the production of new vaccine candidates and they are now being tested, Professor Higgins said.
“I’ve never seen anything like it”
“AlphaFold has sent ripples through the molecular biology community. In the past year alone, there have been over a thousand scientific papers on a wide range of research topics using AlphaFold structures; I’ve never seen anything like it” , said Dr. Sameer Velankar, team leader of the EMBL-EBI Protein Data Bank in Europe.
“And that’s just the impact of a million predictions; Imagine the impact of having more than 200 million protein structure predictions openly accessible in the AlphaFold database.”