Rivercell raises $25M to build an AI virtual cell
Paris-based Rivercell has raised $25 million (about €22 million) in seed funding to generate experimental data and build AI models that predict how human cells respond to drugs and genetic changes.
Who’s investing: German investor HV Capital led the round, with participation from HCVC, Alven and Bpifrance Digital Venture. The financing will support Rivercell’s data generation platform, expansion of its automated wet lab in Paris and development of its AI Virtual Cell program.
Why it matters: Rivercell’s bet is that better cellular predictions require purpose-built experiments. The company plans to build both the infrastructure that produces the training data and the AI model that learns from it, with the eventual goal of reducing the experiments needed in drug discovery.
What they’re saying: “The missing piece is data: how cells change over time and under treatment, seen through multiple lenses and at multiple layers, captured at scale,” said co-founder and CEO Yann Fleureau.
How it works: Rivercell’s platform measures individual cells after experimental interventions, such as drug treatment or genetic changes. It combines different types of biological measurements and tracks responses over time, rather than relying only on snapshots.
- Those datasets will train its “virtual cell”: a model intended to simulate how cells respond to treatments before researchers test them physically. Rivercell says existing laboratory instruments were not designed to generate this training data at the required scale. It is therefore developing its own platform, describing the equipment as the “GPU for the bio data center” of the future.
The big picture: The company wants its model to work across diseases, including oncology, immunology, rare diseases and cardiometabolic conditions. Its premise is that learning the underlying rules of cellular responses could support discovery across multiple therapeutic areas.
- “Understanding how cells respond to perturbations, over time rather than in snapshots, is one of the big open problems in biology,” said scientific adviser Fabian Theis, director of the Computational Health Center at Helmholtz Munich. Theis also joins Rivercell’s scientific advisory board alongside Charlotte Bunne, an assistant professor of artificial intelligence in molecular medicine at EPFL.
Who’s behind it: Fleureau started Rivercell in summer 2025 after co-founding and leading Cardiologs, the AI cardiac diagnostics company acquired by Philips in 2021. Eric Durand joined in 2026 as co-founder and chief scientific officer. He previously led oncology data science at Novartis, served as chief data science officer at Paris-based AI biotech Owkin and co-founded the biology foundation-model company Bioptimus.
What to watch: Rivercell has not disclosed the size of its dataset, prediction benchmarks or a launch date for its virtual cell model. Its next challenge is to show that the experimental platform can produce useful training data at scale, and that the resulting predictions can reliably guide drug discovery.
