Latent Labs Unveils Latent-Y: A Revolutionary Drug Design Tool for Researchers

Today, Latent Labs announced the launch of Latent-Y, its innovative lab-validated drug design agent, now accessible to researchers globally via the Latent Labs Platform. All approved researchers will receive a complimentary daily quota of 250 designs, with additional credits available for larger campaigns.

Latent-Y functions as an AI agent for drug design, processing therapeutic goals articulated in written language or scientific publications. By mimicking the decision-making of a structural biologist, it identifies suitable sites on targets and selects candidates, delivering lab-ready sequences. The agent can operate autonomously or pause for researcher input, ensuring complete control over the design process. In published results, Latent-Y achieved a remarkable 67% target-level success rate across nine targets, with binding affinities in the single-digit nanomolar range, streamlining what typically takes weeks into mere hours—an impressive 56x increase in efficiency.

Prior to this launch, select academic groups were granted access to the Latent Labs Platform, covering fields such as ion channel structural biology, cancer immunotherapy, and infectious diseases, even including labs without prior computational design expertise. Notably, at UC Davis, Prof. Vladimir Yarov-Yarovoy's team successfully designed nanobodies against a human ion channel, with four out of five blocking the channel’s electrical current—remarkably, the most effective did so at a low concentration of 30 nM, a level usually achieved only after extensive laboratory refinement. Furthermore, Dr. Daria Briukhovetska's group at LMU University Hospital developed CAR-T cells that effectively killed tumor cells in vitro and have advanced to animal studies. Additionally, Prof. John Altin's team at the Translational Genomics Research Institute confirmed numerous high-affinity binders against a conserved site on a malaria parasite protein, crucial for preventing severe disease.

Latent-Y serves as the reasoning and natural-language interface to the Latent Labs Platform, utilizing the same models and tools that produced these significant results. The entire system runs in the browser, negating the need for infrastructure setup or pipeline maintenance, allowing researchers to commence large-scale design efforts immediately. This capability enables a single researcher to tackle targets that would otherwise be unattainable.

To celebrate the launch, Latent Labs is hosting a live demonstration and scientific presentation in London on July 15, 2026. Attendees will witness a live design campaign and hear firsthand results from the beta program. The event will conclude with a panel discussion titled “Frontier protein design, now in every researcher’s hands,” featuring Stefan Oschmann, former CEO of Merck KgaA. Registration is available at www.luma.com/latent-y-launch.

"We built Latent-Y to be a force multiplier for researchers. Just as coding agents are accelerating software development, Latent-Y accelerates drug development: one person running dozens of design campaigns in parallel, each progressing with expert-level biological reasoning. Researchers can now design antibodies, nanobodies, and macrocycles at unprecedented scale, all from a natural language prompt," said Simon Kohl, CEO and founder of Latent Labs.

Researchers retain ownership of the sequences they create, and Latent Labs does not utilize user data or outputs for training purposes. Access can be obtained at platform.latentlabs.com, where applicants need to provide their affiliation and research use case. Commercial partnerships are available through a separate enterprise tier via partnerships@latentlabs.com.