Forecasting autism gene discovery with machine learning and genome-scale data
AbstractBackgroundGenes are one of the most powerful windows into the biology of autism, and it has been estimated that perhaps a thousand or more genes may confer risk. However, less than 100 genes are currently viewed as having robust enough evidence to be considered true "autism genes". Massive genetic studies are underway to produce data to implicate additional genes, but this approach, although necessary, is costly and slow-moving.MethodsWe approach autism gene discovery as a machine learning problem, rather than a genetic association problem, and use genome-scale data as predictors for identifying further genes that have similar properties in the feature space compared to established autism risk genes. This approach, which we call forecASD, integrates spatiotemporal gene expression, heterogeneous network data, and previous gene-level predictors of autism association into an ensemble classifier that yields a single score that indexes each gene’s evidence for being involved in the etiology of autism.ResultsWe demonstrate that forecASD has substantially increased sensitivity and specificity compared to previous gene-level predictors of autism association, including genetic measures such as TADA. On an independent test set, consisting of newly-released pilot data from the SPARK Genomics Consortium, we show that forecASD best predicts which genes will have an excess of likely gene disrupting (LGD) de novo mutations. We further use independent data from a recent post mortem study of case/control gene expression to show that forecASD is also a significant predictor of genes implicated in ASD through differential expression. Using forecASD results, we show which molecular pathways are currently under-represented in the autism literature and likely represent under-appreciated biological mechanisms of autism. Finally, forecASD correctly predicted 12 of 16 genes implicated at FDR=0.2 by the latest ASD gene discovery study, while also identifying the most likely false positives among the candidate genes.ConclusionsThese results demonstrate that forecASD bridges the gap between genetic- and expression-based ASD gene discovery, and provides a data-driven replacement to much of the manual filtering and curation that is a critical step in ensuring the robustness of gene discovery studies.