Composite local low-rank structure in learning drug sensitivity

TL;DR

This paper introduces a composite local low-rank modeling approach for integrating multi-omics data to improve drug sensitivity prediction in cancer, accounting for modality-specific structures.

Contribution

It proposes a novel composite local nuclear norm penalization method that captures modality-specific low-rank structures for better predictive accuracy.

Findings

Improved prediction performance over global low-rank methods

Effective integration of multi-omics data modalities

Enhanced identification of relevant features for drug sensitivity

Abstract

The molecular characterization of tumor samples by multiple omics data sets of different types or modalities (e.g. gene expression, mutation, CpG methylation) has become an invaluable source of information for assessing the expected performance of individual drugs and their combinations. Merging the relevant information from the omics data modalities provides the statistical basis for determining suitable therapies for specific cancer patients. Different data modalities may each have their specific structures that need to be taken into account during inference. In this paper, we assume that each omics data modality has a low-rank structure with only few relevant features that affect the prediction and we propose to use a composite local nuclear norm penalization for learning drug sensitivity. Numerical results show that the composite low-rank structure can improve the prediction performance compared to using a global low-rank approach or elastic net regression.