In the recent past, discerning the exact 3D structure of a single protein took around five years. Today the same task is possible in seconds thanks to the machine learning program AlphaFold, developed by Alphabet subsidiary DeepMind. In July, the company announced that AlphaFold had predicted the structures of 200 million proteins—nearly all known to humankind. And in what CEO Demis Hassabis described as a “gift to humanity,” DeepMind made the structures, along with AlphaFold’s underlying code, freely available to all. That will likely accelerate the work of scientists around the world trying to solve humanity’s toughest problems. The company says AlphaFold is now being used in efforts as diverse as fighting antibiotic resistance and Parkinson’s disease, and tackling plastic pollution.
- L.A. Fires Show Reality of 1.5°C of Warming
- Home Losses From L.A. Fires Hasten ‘An Uninsurable Future’
- The Women Refusing to Participate in Trump’s Economy
- Bad Bunny On Heartbreak and New Album
- How to Dress Warmly for Cold Weather
- We’re Lucky to Have Been Alive in the Age of David Lynch
- The Motivational Trick That Makes You Exercise Harder
- Column: No One Won The War in Gaza
