Non-linear interactions among single nucleotide polymorphisms (SNPs), genes, and pathways play an important role in human diseases, but identifying these interactions is a challenging task. Neural networks are state-of-the-art predictors in many domains due to their ability to analyze big data and model complex patterns, including non-linear interactions. In genetics, visible neural networks are popular as they provide insight into the most important SNPs, genes, and pathways for prediction. Visible neural networks use prior knowledge (e.g., gene and pathway annotations) to define node connections in the network, making them sparse and interpretable. Currently, most of these networks provide measures for the importance of SNPs, genes, and pathways but do not provide information about interactions. In this paper, we explore different methods to detect non-linear interactions with visible neural networks. We adapt and speed up existing methods, create a comprehensive benchmark with simulated data from GAMETES and EpiGEN, and demonstrate that these methods can extract multiple types of interactions from trained neural networks. Finally, we apply these methods to a genome-wide case-control study of inflammatory bowel disease and find high consistency of the epistasis pairs candidates between interpretation methods. The follow-up association test on these candidates identifies seven significant epistasis pairs.

Integrating multi-omics data into predictive models has the potential to enhance accuracy, which is essential for precision medicine. In this study, we developed interpretable predictive models for multi-omics data by employing neural networks informed by prior biological knowledge, referred to as visible networks. These neural networks offer insights into the decision-making process and can unveil novel perspectives on the underlying biological mechanisms associated with traits and complex diseases. We tested the performance, interpretability and generalizability for inferring smoking status, subject age and LDL levels using genome-wide RNA expression and CpG methylation data from the blood of the BIOS consortium (four population cohorts, Ntotal = 2940). In a cohort-wise cross-validation setting, the consistency of the diagnostic performance and interpretation was assessed. Performance was consistently high for predicting smoking status with an overall mean AUC of 0.95 (95% CI: 0.90-1.00) and interpretation revealed the involvement of well-replicated genes such as AHRR, GPR15 and LRRN3. LDL-level predictions were only generalized in a single cohort with an R2 of 0.07 (95% CI: 0.05-0.08). Age was inferred with a mean error of 5.16 (95% CI: 3.97-6.35) years with the genes COL11A2, AFAP1, OTUD7A, PTPRN2, ADARB2 and CD34 consistently predictive. For both regression tasks, we found that using multi-omics networks improved performance, stability and generalizability compared to interpretable single omic networks. We believe that visible neural networks have great potential for multi-omics analysis; they combine multi-omic data elegantly, are interpretable, and generalize well to data from different cohorts.

Applying deep learning in population genomics is challenging because of computational issues and lack of interpretable models. Here, we propose GenNet, a novel open-source deep learning framework for predicting phenotypes from genetic variants. In this framework, interpretable and memory-efficient neural network architectures are constructed by embedding biologically knowledge from public databases, resulting in neural networks that contain only biologically plausible connections. We applied the framework to seventeen phenotypes and found well-replicated genes such as HERC2 and OCA2 for hair and eye color, and novel genes such as ZNF773 and PCNT for schizophrenia. Additionally, the framework identified ubiquitin mediated proteolysis, endocrine system and viral infectious diseases as most predictive biological pathways for schizophrenia. GenNet is a freely available, end-to-end deep learning framework that allows researchers to develop and use interpretable neural networks to obtain novel insights into the genetic architecture of complex traits and diseases.