Unsupervised ensemble-based phenotyping helps enhance the discoverability of genes related to heart morphology

TL;DR

This paper introduces Unsupervised Phenotype Ensembles (UPE), a deep learning framework that enhances gene discovery related to heart shape by pooling multiple unsupervised learned phenotypes, leading to improved detection of genetic loci.

Contribution

The paper presents a novel unsupervised ensemble approach for phenotyping that improves gene discovery from cardiac MRI data, outperforming traditional methods.

Findings

Identified 11 significant genetic loci influencing heart shape.

Demonstrated improved gene discovery using ensemble phenotypes.

Applicable to other organs and imaging modalities.

Abstract

Recent genome-wide association studies (GWAS) have been successful in identifying associations between genetic variants and simple cardiac parameters derived from cardiac magnetic resonance (CMR) images. However, the emergence of big databases including genetic data linked to CMR, facilitates investigation of more nuanced patterns of shape variability. Here, we propose a new framework for gene discovery entitled Unsupervised Phenotype Ensembles (UPE). UPE builds a redundant yet highly expressive representation by pooling a set of phenotypes learned in an unsupervised manner, using deep learning models trained with different hyperparameters. These phenotypes are then analyzed via (GWAS), retaining only highly confident and stable associations across the ensemble. We apply our approach to the UK Biobank database to extract left-ventricular (LV) geometric features from image-derived three-dimensional meshes. We demonstrate that our approach greatly improves the discoverability of genes influencing LV shape, identifying 11 loci with study-wide significance and 8 with suggestive significance. We argue that our approach would enable more extensive discovery of gene associations with image-derived phenotypes for other organs or image modalities.