Increasing trustworthiness of machine learning-based drug sensitivity prediction with a multivariate random forest approach

Ensuring the trustworthiness of machine learning (ML) models in high-stake applications is crucial. One such application is predicting anti-cancer drug sensitivity, where ML models are built with the final goal of integrating them into treatment recommendation systems for personalized medicine. Here, we propose a trustworthy multivariate random forest method, called MORGOTH. Besides standard regression and classification functions, MORGOTH allows for the simultaneous optimization of regression and classification tasks via a joint splitting criterion. Additionally, it provides a graph representation of the random forest to address model interpretability, and a cluster analysis of the leaves to measure the dissimilarity of new inputs from the training data to account for its reliability. While our approach is broadly applicable, we demonstrate its capabilities for anti-cancer drug sensitivity prediction by a comprehensive large-scale study on the Genomics of Drug Sensitivity in Cancer (GDSC) database. We trained single-drug as well as multi-drug models. In either case, MORGOTH clearly outperforms state-of-the-art neural network approaches. Moreover, we highlight an evaluation issue for multi-drug models and demonstrate that single-drug models consistently outperform them when evaluated fairly.