Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra

TL;DR

This paper introduces DeepWAS, a novel method leveraging accelerated linear algebra to train large neural network models for genetic variant effect prediction, overcoming previous computational limitations and improving disease prediction accuracy.

Contribution

The paper presents a new approach using modern linear algebra techniques to enable training of large, flexible neural networks for genetic variant effect modeling, surpassing prior small-model limitations.

Findings

Larger models trained with full likelihood outperform small models.

Full likelihood training enables effective use of larger neural networks.

Models trained with traditional summary statistics do not benefit from increased size.

Abstract

To understand how genetic variants in human genomes manifest in phenotypes -- traits like height or diseases like asthma -- geneticists have sequenced and measured hundreds of thousands of individuals. Geneticists use this data to build models that predict how a genetic variant impacts phenotype given genomic features of the variant, like DNA accessibility or the presence of nearby DNA-bound proteins. As more data and features become available, one might expect predictive models to improve. Unfortunately, training these models is bottlenecked by the need to solve expensive linear algebra problems because variants in the genome are correlated with nearby variants, requiring inversion of large matrices. Previous methods have therefore been restricted to fitting small models, and fitting simplified summary statistics, rather than the full likelihood of the statistical model. In this paper, we leverage modern fast linear algebra techniques to develop DeepWAS (Deep genome Wide Association Studies), a method to train large and flexible neural network predictive models to optimize likelihood. Notably, we find that larger models only improve performance when using our full likelihood approach; when trained by fitting traditional summary statistics, larger models perform no better than small ones. We find larger models trained on more features make better predictions, potentially improving disease predictions and therapeutic target identification.