# Clustering individuals using INMTD: a novel versatile multi-view embedding framework integrating omics and imaging data

## TL;DR

This paper introduces INMTD, a new method that combines omics and 3D imaging data to create meaningful and unconfounded clusters of individuals.

## Contribution

The novel INMTD framework integrates NMTF and NTD for multi-view clustering, effectively handling confounders in omics and imaging data.

## Key findings

- INMTD outperformed other methods on synthetic data using the adjusted Rand index.
- INMTD produced biologically relevant embeddings in real facial-genomic data.
- Unconfounded clustering improved internal and external quality with distinct subgroup characteristics.

## Abstract

Combining omics and images can lead to a more comprehensive clustering of individuals than classic single-view approaches. Among the various approaches for multi-view clustering, nonnegative matrix tri-factorization (NMTF) and nonnegative Tucker decomposition (NTD) are advantageous in learning low-rank embeddings with promising interpretability. Besides, there is a need to handle unwanted drivers of clusterings (i.e. confounders).

In this work, we introduce a novel multi-view clustering method based on NMTF and NTD, named INMTD, which integrates omics and 3D imaging data to derive unconfounded subgroups of individuals. According to the adjusted Rand index, INMTD outperformed other clustering methods on a synthetic dataset with known clusters. In the application to real-life facial-genomic data, INMTD generated biologically relevant embeddings for individuals, genetics, and facial morphology. By removing confounded embedding vectors, we derived an unconfounded clustering with better internal and external quality; the genetic and facial annotations of each derived subgroup highlighted distinctive characteristics. In conclusion, INMTD can effectively integrate omics data and 3D images for unconfounded clustering with biologically meaningful interpretation.

INMTD is freely available at https://github.com/ZuqiLi/INMTD.