State-of-the-art Bayesian platform for computational oncology

Make better decisions by using disease-specific models

How fast will my patient progress on or off treatment? What is the probability that my new treatment is better than the competitor or standard of care? How predictive is my new biomarker? What attributes differentiate responders from non-responders? These are some of the questions we are working on with leading Pharma and Biotech companies.

Interpretability.png

Interpretability

Our models are generative, transparent, explainable, and testable. In contrast to black box methods, we know what these models are doing.

PredictiveAccuracy.png

Predictive Accuracy

In-sample predictions are easy. Our models make well calibrated predictions out of sample: for a new patient, a new study arm, and even a new trial.

Algorithm (1).png

Algorithms

Recent advances in computational statistics allow us to tackle models previously thought too difficult due to non-linearities and the number of unknowns.

SmallData.png

Clinical Data

Our models work well in the small data regime, such as in platform trials in Oncology and Rare Diseases, where we need to take advantage of information external to the clinical trial.

Generable Website Design2.png

Joint Survival Models

Linking the model for the hazard with     

sub-models for individual biomarkers.   

Joint models for comorbidities.

Generable Website Design.png

Pharmacometric Models

Using Ordinary Differential Equation (ODE) solvers we encode how the drug moves through different parts of the body.

GenomicModelHome.png

Genomic Models

Retain proper uncertainties and produce more accurate predictions than popular tools like Lasso and PCA.

Want to learn more?