Google's DeepMind has introduced the third major version of its AlphaFold AI model, aiming to help scientists in designing drugs and targeting diseases more effectively.
As per Reuters, in 2020, DeepMind achieved a significant advance in molecular biology by using AI to accurately predict how tiny proteins behave.
In collaboration with Isomorphic Labs, overseen by co-founder Demis Hassabis, DeepMind has expanded AlphaFold's capabilities to map the behavior of all life's molecules, including human DNA.
However, understanding how proteins interact with other molecules, such as enzymes vital for human metabolism or antibodies that combat diseases, is crucial for discovering and developing new drugs.
Meanwhile, DeepMind's recent research, published in the journal Nature, suggests that these findings could speed up the process of creating life-changing treatments by reducing both time and costs.
Hassabis said in a press briefing on Tuesday, noting, “With these new capabilities, we can design a molecule that will bind to a specific place on a protein, and we can predict how strongly it will bind."
He added, “It's a critical step if you want to design drugs and compounds that will help with disease.”
However, to facilitate research, DeepMind has also released the AlphaFold server, a free online tool that simplifies hypothesis testing for scientists.
DeepMind said the new server required less computing knowledge, allowing researchers to run tests with just a few clicks of a button.
Moreover, John Jumper, a senior research scientist at DeepMind, said, "It’s going to be really important how much easier the AlphaFold server makes it for biologists – who are experts in biology, not computer science – to test larger, more complex cases."
