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.
Read the full preprint for free at ChemRxiv!
Lisa-Marie Rolli is a PhD student working on the RADAR project, this work describes the background she will use to develop a computational model for the prediction of toxicity of chemicals and if necessary redesign of these chemicals.
MORGOTH: A Trustworthy AI Tool for Cancer Drug Prediction
MORGOTH is a new machine learning method designed to reliably predict how cancer drugs will work for different patients. It combines multiple types of predictions and offers clear explanations of its results, helping build trust in high-stakes medical decisions. Tested on a large cancer drug database, MORGOTH outperformed leading AI models and showed that focusing on individual drugs gives more accurate results than combining many at once.
Link to the RADAR project:
Lisa-Marie Rolli is a PhD student working on the RADAR project, this work describes the background she will use to develop a computational model for the prediction of toxicity of chemicals and if necessary redesign of these chemicals.
