TUGDA: Task uncertainty guided domain adaptation for robust generalization of cancer drug response prediction from in vitro to in vivo settings

Abstract

Over the last decade, large-scale cancer omics studies have highlighted the diversity of patient molecular profiles and the importance of leveraging this information to deliver the right drug to the right patient at the right time. Key challenges in learning predictive models for this include the high-dimensionality of omics data, limitations in the number of data points available, and heterogeneity in biological and clinical factors affecting patient response. The use of multi-task learning (MTL) techniques has been widely explored to address dataset limitations for in vitro drug response models, while domain adaptation (DA) has been employed to extend them to predict in vivo response. In both of these transfer learning settings, noisy data for some tasks (or domains) can substantially reduce the performance for others compared to single-task (domain) learners, i.e. lead to negative transfer (NT). We describe a novel multi-task unsupervised domain adaptation method (TUGDA) that addresses these limitations in a unified framework by quantifying uncertainty in predictors and weighting their influence on shared domain/task feature representations. TUGDAs ability to rely more on predictors with low-uncertainty allowed it to notably reduce cases of negative transfer for in vitro models (63% for drugs with limited data and 94% overall) compared to state-of-the-art methods. For domain adaptation to in vivo settings, TUGDA improved performance for 6 out of 12 drugs in patient-derived xenografts, and 7 out of 22 drugs in TCGA patient datasets, despite being trained in an unsupervised fashion. TUGDAs ability to avoid negative transfer thus provides a key capability as we try to integrate diverse drug-response datasets to build consistent predictive models with in vivo utility. Availabilityhttps://github.com/CSB5/TUGDA