At Lemna We:
decode & encode
the
interactions
of life
Biological interactions are at the core of health and disease. We are building AI models that explain how molecules interact, from atomic-level interfaces to biological networks.
We use these models to identify high-confidence disease targets, optimal engagement strategies, and drug molecules that act safely and effectively.
Geometric Transformer at the Core
Our models reason from first principles using atomic structure, guided by biological context. The result is explainable hypotheses that help drug discovery teams nominate targets, assess druggability, and find molecules that engage them safely.
Our platform builds on models published by our team
-
Pesto
Nature Communications, 2023Predicts protein interaction interfaces and molecular hotspots. Used by over 3000 researchers.
Read paper -
Carbonara
Nature Communications, 2024Protein sequence design, benchmarked by Novo Nordisk as one of the two top models.
Read paper
Built in Lausanne
A team of ML researchers, biophysicists, and protein designers on the shore of Lake Léman, Switzerland.
