Multimodal Data Visualization and Denoising with Integrated Diffusion

TL;DR

This paper introduces integrated diffusion, a novel method for combining multimodal datasets to improve data visualization, denoising, and clustering, demonstrated on multi-omic blood cell data.

Contribution

The paper presents a new integrated diffusion technique that effectively combines multimodal data, enhancing analysis and visualization over existing methods.

Findings

Better visualization of joint data geometry

Improved capture of cross-modality associations

Accurate identification of cellular populations

Abstract

We propose a method called integrated diffusion for combining multimodal datasets, or data gathered via several different measurements on the same system, to create a joint data diffusion operator. As real world data suffers from both local and global noise, we introduce mechanisms to optimally calculate a diffusion operator that reflects the combined information from both modalities. We show the utility of this joint operator in data denoising, visualization and clustering, performing better than other methods to integrate and analyze multimodal data. We apply our method to multi-omic data generated from blood cells, measuring both gene expression and chromatin accessibility. Our approach better visualizes the geometry of the joint data, captures known cross-modality associations and identifies known cellular populations. More generally, integrated diffusion is broadly applicable to multimodal datasets generated in many medical and biological systems.