Completion of the DrugMatrix Toxicogenomics Database using 3-Dimensional Tensors

TL;DR

This paper presents a tensor completion method that preserves the 3D structure of toxicogenomics data, improving accuracy over previous methods and revealing tissue relationships, with implications for cross-species drug studies.

Contribution

The paper introduces a novel tensor-based completion approach that outperforms traditional matrix methods in toxicogenomics data imputation and analysis.

Findings

Lower mean squared errors and mean absolute errors compared to prior methods

Effectively captures organ-specific variability in the data

Reveals relationships among tissues through non-negative tensor completion

Abstract

We explore applying a tensor completion approach to complete the DrugMatrix toxicogenomics dataset. Our hypothesis is that by preserving the 3-dimensional structure of the data, which comprises tissue, treatment, and transcriptomic measurements, and by leveraging a machine learning formulation, our approach will improve upon prior state-of-the-art results. Our results demonstrate that the new tensor-based method more accurately reflects the original data distribution and effectively captures organ-specific variability. The proposed tensor-based methodology achieved lower mean squared errors and mean absolute errors compared to both conventional Canonical Polyadic decomposition and 2-dimensional matrix factorization methods. In addition, our non-negative tensor completion implementation reveals relationships among tissues. Our findings not only complete the world's largest in-vivo toxicogenomics database with improved accuracy but also offer a promising methodology for future studies of drugs that may cross species barriers, for example, from rats to humans.