Artificial city

An artificial intelligence has predicted the shape of almost every known protein

For sharper, insightful business and economic news, subscribe to
The daily advantage newsletter. It’s completely free and we guarantee you’ll learn something new every day.

Everyone knows the sci-fi movie cliche of an artificial intelligence program inevitably sliding down a villainous path. Luckily, when not scripted by a Hollywood screenwriter, super-intelligent AI isn’t all that bad.

On Thursday, Alphabet-owned British artificial intelligence company DeepMind revealed that its AlphaFold algorithm has effectively predicted the shape of nearly every protein known to science, which could rapidly accelerate drug discovery and breakthroughs in science. biology. They give the database to anyone for free.

The 0.01%

The human mind is amazing, or at least Isaac Newton and Albert Einstein were. But with all the tools available to the best and brightest of our species, determining the shape of a protein can take months or years of laboratory study. In fact, humans have only discovered the shape of about 0.01%, or 190,000, of the known proteins.

Cracking the shape of proteins, which are essential for life, is key to understanding a protein’s function, and understanding the inner workings gives scientists the ability to alter its DNA sequence or identify drugs that could s attach to it. In the case of malaria, for example, studying the proteins of the parasite can reveal how antibodies bind to it and open up pathways to fight it. By doing work that could have taken humans decades, DeepMind’s AI is giving scientists a roadmap to a new world of discovery:

  • Last year, DeepMind said AlphaFold predicted the shape of all human proteins, around 350,000, which is crucial for understanding human health and disease. This database now contains more than 200 million predicted protein structures, affecting nearly every living organism whose genomes scientists have sequenced.
  • The structures are available on a public database maintained by the European Bioinformatics Institute of the European Molecular Biology Laboratory (EMBL-EBI). Over half a million researchers have already used the database to visualize 2 million structures.

“Nearly every drug that has come to market in recent years has been partly engineered through knowledge of protein structures,” said Janet Thornton, senior scientist at EMBL-EBI. FinancialTimes.

Effective : Human scientists aren’t out of a job, they have yet to confirm protein structures in experiments, but they’ve basically been given years of work. Plus, they can apply for a job at Isomorphic Labs, the UK-based company that Alphabet cleverly created to use DeepMind’s technology to accelerate drug discovery.

The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.