Scalable Randomized Kernel Methods for Multiview Data Integration and Prediction

TL;DR

This paper introduces scalable randomized kernel methods for integrating multiview data and predicting outcomes, effectively capturing nonlinear relationships and identifying key variables, with applications to COVID-19 molecular data.

Contribution

The paper presents a novel scalable approach using randomized Fourier bases for nonlinear multiview data integration and outcome prediction, suitable for small sample sizes.

Findings

Outperforms existing linear and nonlinear methods in simulations

Identifies molecular signatures associated with COVID-19 severity

Effective for small sample size problems

Abstract

We develop scalable randomized kernel methods for jointly associating data from multiple sources and simultaneously predicting an outcome or classifying a unit into one of two or more classes. The proposed methods model nonlinear relationships in multiview data together with predicting a clinical outcome and are capable of identifying variables or groups of variables that best contribute to the relationships among the views. We use the idea that random Fourier bases can approximate shift-invariant kernel functions to construct nonlinear mappings of each view and we use these mappings and the outcome variable to learn view-independent low-dimensional representations. Through simulation studies, we show that the proposed methods outperform several other linear and nonlinear methods for multiview data integration. When the proposed methods were applied to gene expression, metabolomics, proteomics, and lipidomics data pertaining to COVID-19, we identified several molecular signatures forCOVID-19 status and severity. Results from our real data application and simulations with small sample sizes suggest that the proposed methods may be useful for small sample size problems. Availability: Our algorithms are implemented in Pytorch and interfaced in R and would be made available at: https://github.com/lasandrall/RandMVLearn.