Out of the lab
Google DeepMind: The Podcast
Using Machine Learning to Predict Proteins
A i is perfectly placed to cut through that complexity. The fact that proteins are so diverse can help you constrain the problem. Proteins, like organisms, have a long evolutionary history. There can sometimes be small, random mutations in the string of amino acids. Every now and then, a mutant protein will differ from its normal version on just one of its corners. If we unravelled it back into the ribbon of amino acids, the markers of that mutation would show up in more than one spot. You know that however the protein ends up being folded, you've found a big clue.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
