Hundreds of cardiac MRI traits derived using 3D diffusion autoencoders share a common genetic architecture
Authors:
- Sara OmettoSOSara Ometto
- Soumick ChatterjeeSoumick Chatterjee
- Andrea Mario VerganiAVAndrea Mario Vergani
- Arianna LandiniALArianna Landini
- Sodbo SharapovSSSodbo Sharapov
- Edoardo GiacopuzziEGEdoardo Giacopuzzi
- Alessia ViscontiAVAlessia Visconti
- Emanuele BianchiEBEmanuele Bianchi
- Federica SantonastasoFSFederica Santonastaso
- Emanuel M. SodaESEmanuel M. Soda
- Francesco CisterninoFCFrancesco Cisternino
- Carlo Andrea PivatoCPCarlo Andrea Pivato
Preprint
Abstract
Biobank-scale imaging provides an unprecedented opportunity to characterise thousands of organ phenotypes, how they vary in populations and how they relate to disease outcomes. However, deriving specific phenotypes from imaging data, such as Magnetic Resonance Imaging (MRI), requires time-consuming expert annotation, limiting scalability, and does not exploit how information-dense such image acquisitions are. In this study, we developed a 3D diffusion autoencoder to derive latent phenotypes from temporally resolved cardiac MRI data of 71,021 UK Biobank participants. These phenotypes were reproducible, heritable ( h 2 = [4 - 18%]), and significantly associated with cardiometabolic traits and outcomes, including atrial fibrillation ( P = 8.5 × 10 −29 ) and myocardial infarction ( P = 3.7 × 10 −12 ). By using latent space manipulation techniques, we were able to learn, directly interpret and visualise what specific latent phenotypes are capturing in a given MRI. To establish the genetic basis of such traits, we performed a genome-wide association study, identifying 89 significant common variants ( P < 2.3 × 10 −9 ) across 42 loci, including seven novel loci. Extensive multi-trait colocalisation analyses (PP.H 4 > 0.8) linked variants across phenotypic scales, from intermediate cardiac traits to cardiac disease endpoints. For example, rs142556838 that falls in CCDC141 colocalises with a latent imaging phenotype and a diastolic blood pressure locus. Using single-cell RNA-sequencing data we map CCDC141 expression specifically to a population of ventricular cardiomyocytes. Finally, Polygenic Risk Scores (PRS) derived from latent phenotypes demonstrated predictive power for a range of cardiometabolic diseases and enabled us to successfully stratify the individuals into different risk groups. In conclusion, this study showcases the use of diffusion autoencoding methods as powerful tools for unsupervised phenotyping, genetic discovery and disease risk prediction using cardiac MRI data.Keywords
This publication has 71 references indexed in Scilit:
- Cell-autonomous effect of cardiomyocyte branched-chain amino acid catabolism in heart failure in miceActa Pharmacologica Sinica, 2023
- Systematic single-variant and gene-based association testing of thousands of phenotypes in 394,841 UK Biobank exomesCell Genomics, 2022
- Machine learning optimized polygenic scores for blood cell traits identify sex-specific trajectories and genetic correlations with diseaseCell Genomics, 2022
- Large-scale machine-learning-based phenotyping significantly improves genomic discovery for optic nerve head morphologyThe American Journal of Human Genetics, 2021
- Integrative approaches for large-scale transcriptome-wide association studiesNature Genetics, 2016
- LD Score regression distinguishes confounding from polygenicity in genome-wide association studiesNature Genetics, 2015
- The Genotype-Tissue Expression (GTEx) projectNature Genetics, 2013
- Conditional and joint multiple-SNP analysis of GWAS summary statistics identifies additional variants influencing complex traitsNature Genetics, 2012
- SCN5A channelopathies – An update on mutations and mechanismsProgress in Biophysics and Molecular Biology, 2008
- Identifiability of Model ParameterIFAC Proceedings Volumes, 1985