AbstractWith the emergence of large-scale genomic datasets, there is a unique opportunity to integrate machine learning approaches as standard tools within genome-wide association (GWA) studies. Unfortunately, while machine learning methods have been shown to account for nonlinear data structures and exhibit greater predictive power over classic linear models, these same algorithms have also become criticized as “black box” techniques. Here, we present biologically annotated neural networks (BANNs), a novel probabilistic framework that makes machine learning fully amenable for GWA applications. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. Part of our key innovation is to treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects are manifested at different genomic scales. The BANN software uses scalable variational inference to provide fully interpretable posterior summaries which allow researchers to simultaneously perform (i) fine-mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations and real GWA data applications, we show that our method improves upon state-of-the-art approaches in both settings across a wide range of genetic architectures.

Histopathological images are used to characterize complex phenotypes such as tumor stage. Our goal is to associate features of stained tissue images with high-dimensional genomic markers. We use convolutional autoencoders and sparse canonical correlation analysis (CCA) on paired histological images and bulk gene expression to identify subsets of genes whose expression levels in a tissue sample correlate with subsets of morphological features from the corresponding sample image. We apply our approach, ImageCCA, to two TCGA data sets, and find gene sets associated with the structure of the extracellular matrix and cell wall infrastructure, implicating uncharacterized genes in extracellular processes. We find sets of genes associated with specific cell types, including neuronal cells and cells of the immune system. We apply ImageCCA to the GTEx v6 data, and find image features that capture population variation in thyroid and in colon tissues associated with genetic variants (image morphology QTLs, or imQTLs), suggesting that genetic variation regulates population variation in tissue morphological traits.

Summary: Recent technological developments in measuring genetic variation have ushered in an era of genome-wide association studies which have discovered many genes involved in human disease. Current methods to perform association studies collect genetic information and compare the frequency of variants in individuals with and without the disease. Standard approaches do not take into account any information on whether or not a given variant is likely to have an effect on the disease. We propose a novel method for computing an association statistic which takes into account prior information. Our method improves both power and resolution by 8% and 27%, respectively, over traditional methods for performing association studies when applied to simulations using the HapMap data. Advantages of our method are that it is as simple to apply to association studies as standard methods, the results of the method are interpretable as the method reports p-values, and the method is optimal in its use of prior information in regards to statistical power.Availability: The method presented herein is available at http://masa.cs.ucla.eduContact: eeskin@cs.ucla.edu