Abstract: The applicability of multivariate approaches for joint genomic-phenomic data analysis is currently limited by the lack of scalability, and interpretability to relate findings from a biological perspective. To tackle these limitations, we present Bayesian Genome-to-Phenome Sparse Regression (G2PSR), a novel multivariate regression method based on sparse SNP-gene constraints.
The statistical framework of G2PSR is based on a Bayesian neural network, were constraints on SNPs are integrated by incorporating a priori knowledge linking variants to their respective genes, to then reconstruct the phenotypic data in the output layer. Interpretability is promoted by inducing sparsity on the genes through variational dropout, allowing to estimate the uncertainty associated with each gene
in the reconstruction task. Ultimately, G2PSR prevents multiple testing correction and assesses the combined effect of SNPs, thus increasing the statistical power in detecting genome-to-phenome associations. G2PSR effectiveness was demonstrated on synthetic and real data, with respect to state-of-the-art methods. The real data application used the Alzheimer’s Disease Neuroimaging Initiative data, relating SNPs from more than 3,500 genes to clinical and multi-variate brain volumetric information. The experimental results show that our method provides accurate selection of relevant genes in dataset with large SNPs-to-samples ratio, thus overcoming limitations of current genome-tophenome association methods.

Keywords: Bayesian, Genome, Phenome, Sparse Regression.

Blei, D. M., Kucukelbir, A., and McAuliffe, J. D. (2017). Variational Inference: A Review for Statisticians. J. Am. Stat. Assoc. 112, 859–877. doi:10.1080/01621459.2017.1285773
Deprez M, Moreira J, Sermesant M and Lorenzi M (2022). Decoding Genetic Markers of Multiple Phenotypic Layers Through Biologically Constrained Genome-To-Phenome Bayesian Sparse Regression. Front. Mol. Med, doi: 10.3389/fmmed.2022.830956
Molchanov, D., Ashukha, A., and Vetrov, D. (2017). “Variational Dropout Sparsifies Deep Neural Networks,” in Proceedings of the 34th International Conference on Machine Learning - Volume 70(JMLR.org), ICML’17, 2498–2507.
Shen, L., and Thompson, P. M. (2020). Brain Imaging Genomics: Integrated Analysis and Machine
Learning. Proc. IEEE 108, 125–162. doi:10.1109/JPROC.2019.2947272