Interpretable Deep Learning Methods for Multiview Learning

TL;DR

iDeepViewLearn is an interpretable deep learning method designed for multiview data, effectively performing feature selection and classification, especially useful for small-sample biomedical datasets.

Contribution

The paper introduces iDeepViewLearn, a novel deep learning approach that combines interpretability, feature selection, and multiview data integration for biomedical applications.

Findings

Competitive classification accuracy on real and simulated data

Identified biologically relevant genes and CpG sites

Effective for small-sample-size multiview learning problems

Abstract

Technological advances have enabled the generation of unique and complementary types of data or views (e.g. genomics, proteomics, metabolomics) and opened up a new era in multiview learning research with the potential to lead to new biomedical discoveries. We propose iDeepViewLearn (Interpretable Deep Learning Method for Multiview Learning) for learning nonlinear relationships in data from multiple views while achieving feature selection. iDeepViewLearn combines deep learning flexibility with the statistical benefits of data and knowledge-driven feature selection, giving interpretable results. Deep neural networks are used to learn view-independent low-dimensional embedding through an optimization problem that minimizes the difference between observed and reconstructed data, while imposing a regularization penalty on the reconstructed data. The normalized Laplacian of a graph is used to model bilateral relationships between variables in each view, therefore, encouraging selection of related variables. iDeepViewLearn is tested on simulated and two real-world data, including breast cancer-related gene expression and methylation data. iDeepViewLearn had competitive classification results and identified genes and CpG sites that differentiated between individuals who died from breast cancer and those who did not. The results of our real data application and simulations with small to moderate sample sizes suggest that iDeepViewLearn may be a useful method for small-sample-size problems compared to other deep learning methods for multiview learning.