Towards a deep-learning genomic tool for risk stratification and diagnostic support in sporadic ALS

Abstract

Abstract Background A variety of common and rare genetic factors have been implicated in the development of amyotrophic lateral sclerosis (ALS), and the evidence is that a genetic component is present in most affected individuals. However, our current understanding of ALS genetics causally explains only a small proportion of sporadic ALS, which accounts for over 90% of all people with ALS. This limits the utility of genetic testing in screening, diagnosis and management to the 15–20% of people with ALS who carry a known pathogenic variant. Capsule Networks (CapsNets) constitute a deep learning method that has demonstrated strong performance in using genotyping data to predict individuals at risk for ALS. However, their use is constrained by a lack of generalised, flexible, and externally validated implementations across comprehensive datasets that account for the technical, biological, and clinical heterogeneity found in real-world disease scenarios. Methods In this study, we build upon this method to address existing limitations using large-scale datasets from over 47,000 individuals from 13 countries, genotyped with nine different genotyping platforms. We developed a new model that is validated across diverse ALS populations, can handle discrepancies between genotyping technologies, and is applicable to individual external samples. Results Our model achieved high precision and sensitivity in distinguishing between individuals with ALS and non-affected controls. Moreover, in simulations of population screening for ALS, its predictive performance under a simulated population screening scenario was comparable to published estimates for screening based on major ALS-causing mutations, such as FUS and C9orf72 . Conclusions Our results demonstrate that this flexible and externally validated method could support genetic risk stratification and, following further prospective clinical validation, future diagnostic support in sporadic ALS. Complementing current genetic testing approaches based on known ALS mutations, it has the potential to extend genetic risk assessment to all individuals, regardless of their family history or the presence of known ALS mutations.