The companies will integrate the Genialis Supermodel with Inventia’s RASTRUM 3D cell model platform to study pancreatic ductal adenocarcinoma (PDAC) and test therapeutic hypotheses.
Initial findings from the collaboration are due to be presented on 25 September at the Pancreatic Cancer Action Network (PanCAN)’s 2026 Scientific Summit in San Diego.
The study examined 644 pancreatic cancer tumours from PanCAN SPARK’s “Know Your Tumor” cohort.
Genialis identified PDAC patients with poor prognosis using the composition and activity of the tumour microenvironment.
Researchers then mapped the resulting patient profiles to tumour-fibroblast co-culture models produced using RASTRUM.
The approach is intended to allow investigation of biological features associated with poorer outcomes and the testing of potential therapeutic strategies in laboratory models corresponding to those patient profiles.
RASTRUM creates 3D pancreatic cancer models in which tumour and stromal components can be controlled and altered independently.
Genialis will characterise the models through Supermodel, its molecular model trained on a harmonised and curated transcriptomics dataset, and compare them with molecular states seen in clinical settings.
The work also uses data generated through Genialis’ existing collaboration with PanCAN.
Inventia Life Science CEO and co-founder Cameron Ferris said: “This collaboration closes an important gap in drug discovery by connecting what we learn from patients with what we can test in the lab.
“Genialis can identify clinically meaningful biological states in real tumours, while RASTRUM allows us to model and perturb those states at scale.
“Together, that creates a powerful way to generate and test therapeutic hypotheses that are grounded in the biology of the patients we ultimately want to treat.”
The collaboration follows interest in targeted treatments for pancreatic cancer and the challenge of determining which patient groups may benefit from particular approaches.
The companies said their process links patient-derived hypotheses with experimental testing in human-relevant systems before relating findings to clinical populations.