Covariate-aware genomic prediction of blood metabolite profiles using multi-task neural networks
Guler, M. N.; Alver, M.; Haller, T.; Jay, F.; Pagani, L.; Milani, L.; Yelmen, B.
Show abstract
Circulating metabolites capture clinically relevant physiological variation and contribute to disease aetiology yet are mostly studied as biomarkers rather than prediction targets. Although genome-wide association studies have identified genetic determinants of metabolites, marginal associations do not show how accurately the metabolome can be predicted or whether deep learning approaches can improve prediction by exploiting nonlinearities and dependencies. Here, we developed a multi-task neural network (NN) for predicting metabolomic profiles with a three-stage architecture separating covariate, genotype and joint covariate-genotype contributions. In comparative analyses, the multi-task NN demonstrated the strongest mean performance across metabolites (R2=0.219), followed by the single-task NN (R2=0.211), elastic net (R2=0.207), and an activation-free multi-task model (R2=0.191). Decomposition analyses indicated that gains were driven by nonlinear covariate modelling, with limited and heterogeneous genetic and joint covariate-genotype contributions. With further validation, multi-task NNs could serve as compact, efficient models for predicting metabolite profiles in research and clinical settings.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Genome-wide association study of 1,391 plasma metabolites in 6,136 Finnish men identifies 303 novel signals and provides biological insights into human diseases 96%
- Genetic analysis of blood molecular phenotypes reveals regulatory networks affecting complex traits: a DIRECT study 96%
- Metabolome-wide Mendelian randomization characterizes heterogeneous and shared causal effects of metabolites on human health 95%
Similar papers in this journal
- Integrative analysis of metabolite GWAS illuminates the molecular basis of pleiotropy and genetic correlation 95%
- Exploiting the mediating role of the metabolome to unravel transcript-to-phenotype associations 93%
- Serum proteomic profiling of physical activity reveals CD300LG as a novel exerkine with a potential causal link to glucose homeostasis 92%
Similar papers in this journal
- Polygenic scores capture genetic modification of the adiposity-cardiometabolic risk factor relationship 96%
- Multiset correlation and factor analysis enables exploration of multi-omic data 94%
- Proteome-wide Mendelian randomization in global biobank meta-analysis reveals multi-ancestry drug targets for common diseases 94%
Similar papers in this journal
- Revealing grand-paternal programming of lipid metabolism using a novel computational tool 95%
- Composite trait Mendelian Randomization reveals distinct metabolic and lifestyle consequences of differences in body shape 94%
- AutoFocus: A hierarchical framework to explore multi-omic disease associations spanning multiple scales of biomolecular interaction 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.