Helical partners with OpenAI and Nebius to bring biological foundation models to researchers at unprecedented scale
Researchers can use and post-train models on their own data through the agentic tools they already use, with free compute credits for academic researchers.
London, October 27, 2026. Helical today announced the release of its Model Context Protocol (MCP) integration for OpenAI’s Codex. Together with OpenAI and Nebius, Helical is making biological foundation models available to the wider research community, so researchers can run in-silico experiments directly from the agentic tools they already use.
Using biological foundation models often requires researchers to configure infrastructure and build the workflows needed to run an experiment. Helical’s MCP brings those capabilities into Codex, allowing researchers to use and post-train models on their own data through natural-language instructions. The aim is to reduce the time spent setting up software and compute, giving researchers more time to explore their biology.
One of the models available at launch is PerturbGen, developed by Mo Lotfollahi and his lab at the Wellcome Sanger Institute to predict how perturbations reshape cellular trajectories. A joint quick-start example uses PerturbGen from Codex to predict how knocking out IL1B early in an LPS response alters inflammatory programs and cell states over time.
To help academic researchers get started, Helical and Nebius are providing free compute credits that can be requested through the research-credit application form.
The release extends access to Helical’s biological modelling capabilities beyond its existing pharmaceutical deployments and into the tools used by the wider research community.
Get started with Helical’s MCPAbout Helical
Helical adapts biological foundation models to proprietary data so pharmaceutical companies can build and own their biological intelligence for better target identification and biomarker discovery.