Skip to Content
Artificial intelligence

An AI system identified a potential new drug in just 46 days

September 3, 2019
A researcher working in a lab
A researcher working in a labGetty

The approach is based on two popular AI techniques: generative adversarial networks and reinforcement learning.

The news: A team from AI pharma startup Insilico Medicine, working with researchers at the University of Toronto, took 21 days to create 30,000 designs for molecules that target a protein linked with fibrosis (tissue scarring). They synthesized six of these molecules in the lab and then tested two in cells; the most promising one was tested in mice. The researchers concluded it was potent against the protein and showed “drug-like” qualities. All in all, the process took just 46 days. The research was published in Nature Biotechnology this week.

The method: The system examines previous research and patents for molecules known to work against the drug target, prioritizing new structures that could be synthesized in the lab. It’s similar to what a human chemist might do to seek new therapies—just much faster.

Context: Getting a new drug to market is hugely costly and time consuming: it can take 10 years and cost as much as $2.6 billion, with the vast majority of candidates failing at the testing stage, according to the Tufts Center for the Study of Drug Development. No wonder, then, that there’s so much work under way on using AI to expedite the process. DeepMind is among the companies exploring pharmaceutical research as a potential avenue for its algorithms.

A word of caution: Although the research looks promising, it’s still very much a proof of concept. We’re a long way from AI-designed drugs being created, let alone sold to patients. We explored the issue in this article from our TR10 issue earlier this year.

Sign up here for our daily newsletter The Download to get your dose of the latest must-read news from the world of emerging tech.

Deep Dive

Artificial intelligence

DeepMind’s cofounder: Generative AI is just a phase. What’s next is interactive AI.

“This is a profound moment in the history of technology,” says Mustafa Suleyman.

AI hype is built on high test scores. Those tests are flawed.

With hopes and fears about the technology running wild, it's time to agree on what it can and can't do.

You need to talk to your kid about AI. Here are 6 things you should say.

As children start back at school this week, it’s not just ChatGPT you need to be thinking about.

AI language models are rife with different political biases

New research explains you’ll get more right- or left-wing answers, depending on which AI model you ask.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.