Latent Labs Launches Latent-Y, First Lab-Validated AI Drug Design Agent, to Researchers Worldwide
核心洞察
Latent Labs (搜索) launched Latent-Y (搜索), an AI drug design agent achieving a 67% target-level success rate across nine targets with single-digit nanomolar binding affinities.
The platform compresses weeks of expert workflow into hours, delivering a 56x acceleration in drug design efficiency.
Academic beta users at UC Davis, LMU University Hospital, and TGen produced validated results including ion channel inhibitors, tumor-killing CAR-T cells, and malaria (搜索) protein binders.
Latent Labs (搜索) today announced the global launch of Latent-Y (搜索), the first lab-validated AI agent for drug design, now accessible to researchers worldwide through the Latent Labs Platform. The agent translates therapeutic goals expressed in natural language or scientific publications into lab-ready protein sequences, achieving a 67% target-level success rate across nine targets with binding affinities in the single-digit nanomolar range. The platform compresses workflows that typically require weeks of expert effort into mere hours — a 56-fold increase in efficiency.
"We built Latent-Y (搜索) 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," said Simon Kohl, CEO and founder of Latent Labs (搜索). "Researchers can now design antibodies, nanobodies and macrocycles at unprecedented scale, all from a natural language prompt."
How Latent-Y (搜索) Works
Latent-Y (搜索) functions by mimicking the decision-making process of a specialist structural biologist. It identifies suitable binding sites on target proteins, selects candidate molecules, and refines them — delivering sequences ready for laboratory testing. The agent can operate autonomously or pause at each stage for researcher review, ensuring users retain full control over every design decision.
The entire system runs in a browser, eliminating the need for infrastructure setup or pipeline maintenance. This design allows a single researcher to pursue targets that would otherwise remain out of reach, running dozens of design campaigns in parallel.
Access Model and Commercial Terms
Every approved researcher receives a complimentary daily quota of 250 designs, with additional credits available on demand for larger campaigns. Researchers retain full ownership of the sequences they generate, and Latent Labs (搜索) does not train on user data or outputs. Access is available at platform.latentlabs.com, where applicants provide their affiliation and research use case. Commercial partnerships are offered through a separate enterprise tier.
Beta Program Results Across Three Therapeutic Areas
Prior to the public launch, select academic groups gained early access to the Latent Labs (搜索) Platform, spanning ion channel structural biology, cancer immunotherapy, and infectious disease — including laboratories with no prior computational design experience.
At UC Davis, Professor Vladimir Yarov-Yarovoy's team designed nanobodies from scratch against a human ion channel. Of five candidates taken into the laboratory, four successfully blocked the channel's electrical current. The most potent achieved an IC50 of 30 nM — a potency level typically reached only after multiple rounds of laboratory refinement, but achieved here on the first attempt.
At LMU University Hospital, Dr. Daria Briukhovetska's group incorporated designed binders into CAR-T cells that efficiently killed tumor cells in vitro. These constructs have since advanced to animal studies.
At the Translational Genomics Research Institute (TGen), Professor John Altin's laboratory confirmed dozens of high-affinity binders against a conserved site on a malaria (搜索) parasite protein — a site the parasite cannot mutate without losing its ability to cause severe disease, making it a critical target for therapeutic intervention.
Launch Event
To mark the launch, Latent Labs (搜索) will host a live demonstration and scientific presentation in London on July 15, 2026. Attendees will witness a live design campaign and hear results from the beta program directly from the research teams. The evening will conclude with a panel discussion titled "Frontier protein design, now in every researcher's hands," featuring Stefan Oschmann, former CEO of Merck KGaA.