Genialis™ Supermodel
A foundation model of cancer biology
Trained on hundreds of thousands of RNA sequencing samples, this large molecular model (LMM) defines a comprehensive landscape of cancer biology, learned from preclinical, single-cell, and globally diverse patient records. The LMM maps each new patient sample into this high-dimensional space, revealing its underlying biological states and processes.
The Genialis Supermodel enables rapid configuration of biomarkers across the entire landscape of cancer drug targets.
It yields predictive biomarkers that:
From the transcriptome to therapeutically relevant biology
The Genialis Supermodel is a cornerstone of every biomarker program we undertake. It performs two critical functions:
Accurate, informative, and scalable
We stratify patients by combining biological signatures into therapeutically relevant phenotypes. This approach accurately predicts response to specific therapies, and aids in clinical decision-making by identifying alternative strategies for non-responders.
The Genialis approach is unique in its explainability. Classifiers are explainable by design, model outputs reveal mechanisms of response and resistance, and nominate potential combination therapy approaches.
Genialis biomarkers not only outperform standard-of-care and on-market solutions, they are applicable from cell lines to clinical trials to Cdx devices, guiding drug development across all stages.
