Latent Labs, a UK drug discovery startup launched by former Google DeepMind scientist Simon Kohl, has launched its first AI model, with claims it can outperform top competitors.
AI drug discovery is quickly becoming an intensively competitive market, with dozens of startups pulling in tens of millions – and in the case of DeepMind spinout Isomorphic Labs, hundreds of millions – in investment.
But the recently launched Latent Labs, which closed a $50m (£37m) Series A round in February, claims to be ahead of the curve with the launch its frontier AI model Latent-X.
Available for early access, Latent-X is an AI model for push button protein design with which users can upload protein targets and generate cyclic peptides and mini-binders directly in the browsers.
Releasing a working model is an achievement in itself, however, the company has made bold claims about its performance, suggesting that in head-to-head testing, it outperforms the model developed by Isomorphic Labs, the work of which earned its founder Sir Demis Hassabis a Nobel Prize.
“We envision a future where effective therapeutics can be designed entirely in a computer, like semiconductors or space missions,” said Kohl.
“Our platform empowers scientists with lab-validated protein binder design at their fingertips, whether they’re experts or new to AI-powered drug design, and without needing AI infrastructure. This is the first step on our mission toward making biology programmable in order to make drug design instantaneous.”
Latent Labs said its model generates designs over 10 times faster than previous methods. Latent-X can be accessed by commercial and non-commercial users via a free and premium tier.