Using the structure of genome data in the design of deep neural networks for predicting amyotrophic lateral sclerosis from genotype
Amyotrophic lateral sclerosis (ALS) is a neurodegenerative disease caused by aberrations in the genome. While several disease-causing variants have been identified, a major part of heritability remains unexplained. ALS is believed to have a complex genetic basis where nonadditive combinations of variants constitute disease, which cannot be picked up using the linear models employed in classical genotype-phenotype association studies. Deep learning on the other hand is highly promising for identifying such complex relations. We therefore developed a deep-learning based approach for the classification of ALS patients versus healthy individuals from the Dutch cohort of the ProjectMinE dataset. Based on recent insight that regulatory regions on the genome play a major role in ALS, we employ a two-step approach: first promoter regions that are likely associated to ALS are identified, and second individuals are classified based on their genotype in the selected genomic regions. Both steps employ a deep convolutional neural network. The network architecture accounts for the structure of genome data by applying convolution only to parts of the data where this makes sense from a genomics perspective. Our approach identifies potential ALS-associated genetic variants, and generally outperforms other classification methods. Test results support the hypothesis that ALS is caused by non-additive combinations of variants. Our method can be applied to large-scale whole genome data. We consider this a first step towards genotype-phenotype association with deep learning that is tailored to genomics and can deal with genome-sized data.