Google’s AI Could Soon Help Design Personalized Drugs to Treat Disease

Google’s artificial intelligence division DeepMind said its AI tool AlphaFold can now predict nearly all the molecules in the Protein Data Bank (PDB), the world’s largest open access database of biological molecules. The breakthrough could help AlphaFold herald in a new era of drug discovery and a massive leap in medicine.

The company announced the update in a company blog post published Tuesday.

DeepMind has been tinkering with AlphaFold for the last five years. Now the company believes AlphaFold can not only predict how proteins fold — an essential tool for understanding the most fundamental processes in a cell and how they can go awry in disease — but also other molecules, including DNA and RNA.

“These different structure types and complexes are essential for understanding the biological mechanisms within the cell, and have been challenging to predict with high accuracy,” DeepMind said in its blogpost.

Google believes AlphaFold could ultimately usher in the “next era of digital biology.” But for clinicians and patients, the promise is also great: AlphaFold could be used to pinpoint targets in molecules for novel drugs to treat various medical conditions tied to genetics, from cancer to mitochondrial disease, and by letting researchers test drugs more efficiently before moving to clinical trials. It could also be used to design drugs specific to a person’s particular medical need.

DeepMind said it is already working with another Google-owned enterprise, Isomorphic Labs, to build other AI models that can tackle a range of biologically-relevant molecules beyond protein.

“Our model’s dramatic leap in performance shows the potential of AI to greatly enhance scientific understanding of the molecular machines that make up the human body — and the wider world of nature,” DeepMind said in a statement.