Inbizzy, LONDON & SAN FRANCISCO – Latent Labs, a frontier AI research lab headquartered in London and San Francisco, today officially launched Latent-X, a cutting-edge generative AI model for lab-ready protein binder design. The model is accessible through a no-code, web-based platform that enables push-button protein design.
Latent-X significantly accelerates drug discovery by generating cyclic peptides and mini-binders at all-atom resolution. In wet-lab experiments across seven therapeutic targets, Latent-X demonstrated 91–100% hit rates for macrocycles and 10–64% for mini-binders—consistently outperforming prior models in both computational evaluation and lab validation. The model also achieved picomolar-level binding affinities for mini-binders.
Through Latent’s intuitive platform, scientists from all backgrounds can upload protein targets and automatically generate, visualize, and rank binder designs directly in the browser—no AI or coding expertise required. A free tier is available for both commercial and non-commercial users.
Traditional drug discovery involves screening millions of random molecules with success rates below 1%, often taking months and costing thousands of dollars per experiment. In contrast, Latent-X can achieve similar or better results by testing just 30 candidates per target, drastically reducing time and cost.
“We envision a future where effective therapeutics can be designed entirely in a computer, much like how space missions or semiconductors are designed today,” said Simon Kohl, CEO and founder of Latent Labs. “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-X is a general-purpose AI model capable of designing de novo binders for novel or previously untargeted proteins. It solves the geometric binding puzzle at the atomic level and generates results 10x faster than previous methods. By co-sampling sequence and structure in real time, Latent-X enables virtual experimentation in seconds.
The technology opens the door to new therapeutic modalities that depend on high-specificity binding, including nanobodies and antibodies. Macrocycles, which are compact and potentially orally bioavailable, combined with the flexibility and specificity of mini-binders, position Latent-X as a revolutionary tool in pharmaceutical and biotech research.
This launch follows Latent Labs’ $50 million funding round announced in early 2025, co-led by Radical Ventures and Sofinnova Partners, with participation from major tech leaders including Jeff Dean (Chief Scientist at Google), Dario Amodei (CEO of Anthropic), and Mati Staniszewski (CEO of Eleven Labs). The Latent Labs team includes AI and biotech veterans from DeepMind (AlphaFold 2), Microsoft, Apple, Stability AI, Exscientia, Mammoth Bio, Altos Labs, and Zymergen.
