Non-coding genome contribution to ALS.

The majority of amyotrophic lateral sclerosis (ALS) is caused by a complex gene-environment interaction. Despite high estimates of heritability, the genetic basis of disease in the majority of ALS patients are unknown. This limits the development of targeted genetic therapies which require an understanding of patient-specific genetic drivers. There is good evidence that the majority of these missing genetic risk factors are likely to be found within the non-coding genome. However, a major challenge in the discovery of non-coding risk variants is determining which variants are functional in which specific CNS cell type. We summarise current discoveries of ALS-associated genetic drivers within the non-coding genome and we make the case that improved cell-specific annotation of genomic function is required to advance this field, particularly via single-cell epigenetic profiling and spatial transcriptomics. We highlight the example of TBK1 where an apparent paradox exists between pathogenic coding variants which cause loss of protein function, and protective non-coding variants which cause reduced gene expression; the paradox is resolved when it is understood that the non-coding variants are acting primarily via change in gene expression within microglia, and the effect of coding variants is most prominent in neurons. We propose that cell-specific functional annotation of ALS-associated genetic variants will accelerate discovery of the genetic architecture underpinning disease in the vast majority of patients.

predicTTE: An accessible and optimal tool for time-to-event prediction in neurological diseases.

Time-to-event prediction is a key task for biological discovery, experimental medicine, and clinical care. This is particularly true for neurological diseases where development of reliable biomarkers is often limited by difficulty visualising and sampling relevant cell and molecular pathobiology. To date, much work has relied on Cox regression because of ease-of-use, despite evidence that this model includes incorrect assumptions. We have implemented a set of deep learning and spline models for time-to-event modelling within a fully customizable 'app' and accompanying online portal, both of which can be used for any time-to-event analysis in any disease by a non-expert user. Our online portal includes capacity for end-users including patients, Neurology clinicians, and researchers, to access and perform predictions using a trained model, and to contribute new data for model improvement, all within a data-secure environment. We demonstrate a pipeline for use of our app with three use-cases including imputation of missing data, hyperparameter tuning, model training and independent validation. We show that predictions are optimal for use in downstream applications such as genetic discovery, biomarker interpretation, and personalised choice of medication. We demonstrate the efficiency of an ensemble configuration, including focused training of a deep learning model. We have optimised a pipeline for imputation of missing data in combination with time-to-event prediction models. Overall, we provide a powerful and accessible tool to develop, access and share time-to-event prediction models; all software and tutorials are available at www.predictte.org.

Deep learning modeling of rare noncoding genetic variants in human motor neurons defines CCDC146 as a therapeutic target for ALS.

Amyotrophic lateral sclerosis (ALS) is a fatal and incurable neurodegenerative disease caused by the selective and progressive death of motor neurons (MNs). Understanding the genetic and molecular factors influencing ALS survival is crucial for disease management and therapeutics. In this study, we introduce a deep learning-powered genetic analysis framework to link rare noncoding genetic variants to ALS survival. Using data from human induced pluripotent stem cell (iPSC)-derived MNs, this method prioritizes functional noncoding variants using deep learning, links cis-regulatory elements (CREs) to target genes using epigenomics data, and integrates these data through gene-level burden tests to identify survival-modifying variants, CREs, and genes. We apply this approach to analyze 6,715 ALS genomes, and pinpoint four novel rare noncoding variants associated with survival, including chr7:76,009,472:C>T linked to CCDC146. CRISPR-Cas9 editing of this variant increases CCDC146 expression in iPSC-derived MNs and exacerbates ALS-specific phenotypes, including TDP-43 mislocalization. Suppressing CCDC146 with an antisense oligonucleotide (ASO), showing no toxicity, completely rescues ALS-associated survival defects in neurons derived from sporadic ALS patients and from carriers of the ALS-associated G4C2-repeat expansion within C9ORF72. ASO targeting of CCDC146 may be a broadly effective therapeutic approach for ALS. Our framework provides a generic and powerful approach for studying noncoding genetics of complex human diseases.