ComboPath: An ML system for predicting drug combination effects with superior model specification

Abstract

Drug combinations have been shown to be an effective strategy for cancer therapy, but identifying beneficial combinations through experiments is labor-intensive and expensive [Mokhtari et al., 2017]. Machine learning (ML) systems that can propose novel and effective drug combinations have the potential to dramatically improve the efficiency of combinatoric drug design. However, the biophysical parameters of drug combinations are degenerate, making it difficult to identify the ground truth of drug interactions even given experimental data of the highest quality available. Existing ML models are highly underspecified to meet this challenge, leaving them vulnerable to producing parameters that are not biophysically realistic and harming generalization. We have developed a new ML model, "ComboPath", aimed at a novel ML task: to predict interpretable cellular dose response surface of a two-drug combination based on each drugs interactions with their known protein targets. ComboPath incorporates a biophysically-motivated intermediate parameterization with prior information used to improve model specification. This is the first ML model to nominate beneficial drug combinations while simultaneously reconstructing the dose response surface, providing insight on both the potential of a drug combination and its optimal dosing for therapeutic development. We show that our models were able to accurately reconstruct 2D dose response surfaces across held out combination samples from the largest available combinatoric screening dataset while substantially improving model specification for key biophysical parameters.