DeepCOMBI: Explainable artificial intelligence for the analysis and discovery in genome-wide association studies

Deep learning algorithms have revolutionized data science in many fields by greatly improving prediction performances in comparison to conventional approaches. Recently, explainable artificial intelligence (XAI) has emerged as a novel area of research that goes beyond pure prediction improvement. Knowledge embodied in deep learning methodologies is extracted by interpreting their results. We investigate such explanations to explore the genetic architectures of phenotypes in genome-wide association studies. Instead of testing each position in the genome individually, the novel three-step algorithm, called DeepCOMBI, first trains a neural network for the classification of subjects into their respective phenotypes. Second, it explains the classifiers decisions by applying layerwise relevance propagation as one example from the pool of XAI techniques. The resulting importance scores are eventually used to determine a subset of most relevant locations for multiple hypothesis testing in the third step. The performance of DeepCOMBI in terms of power and precision is investigated on generated datasets and a 2007 WTCCC study. Verification of the latter is achieved by validating all findings with independent studies published up until 2020. DeepCOMBI is shown to outperform ordinary raw p-value thresholding as well as other baseline methods. Moreover, two novel disease associations (rs10889923 for hypertension and rs4769283 for type 1 diabetes) were identified.