Permutation invariant multi-output Gaussian Processes for drug combination prediction in cancer
This work addresses the problem of predicting drug combination effects in cancer, which is incremental as it builds on prior methods to improve scalability and applicability.
The authors tackled dose-response prediction for cancer drug combinations by developing a variational approximation to permutation invariant multi-output Gaussian Processes, enabling scalability, uncertainty quantification, and handling of missing data, and demonstrated its performance on a high-throughput dataset with efficient information sharing across outputs.
Dose-response prediction in cancer is an active application field in machine learning. Using large libraries of \textit{in-vitro} drug sensitivity screens, the goal is to develop accurate predictive models that can be used to guide experimental design or inform treatment decisions. Building on previous work that makes use of permutation invariant multi-output Gaussian Processes in the context of dose-response prediction for drug combinations, we develop a variational approximation to these models. The variational approximation enables a more scalable model that provides uncertainty quantification and naturally handles missing data. Furthermore, we propose using a deep generative model to encode the chemical space in a continuous manner, enabling prediction for new drugs and new combinations. We demonstrate the performance of our model in a simple setting using a high-throughput dataset and show that the model is able to efficiently borrow information across outputs.