Using computational approaches to enhance the interpretation of missense variants in thePAX6gene

Abstract

ABSTRACTPurposeThePAX6gene encodes a highly-conserved transcription factor involved in eye development. Heterozygous loss-of-function variants inPAX6can cause a range of ophthalmic disorders including aniridia. A key molecular diagnostic challenge is that manyPAX6missense changes are presently classified as variants of uncertain significance. While computational tools can be used to assess the effect of genetic alterations, the accuracy of their predictions varies. Here, we evaluated and optimised the performance of computational prediction tools in relation toPAX6missense variants.MethodsThrough inspection of publicly available resources (including HGMD, ClinVar, LOVD and gnomAD), we identified 241PAX6missense variants that were used for model training and evaluation. The performance of ten commonly-used computational tools was assessed and a threshold optimization approach was utilized to determine optimal cut-off values. Validation studies were subsequently undertaken usingPAX6variants from a local database.ResultsAlphaMissense, SIFT4G and REVEL emerged as the best-performing predictors; the optimized thresholds of these tools were 0.967, 0.025, and 0.772, respectively. Combining the prediction from these top-three tools resulted in lower performance compared to using AlphaMissense alone.ConclusionTailoring the use of computational tools by employing optimized thresholds specific toPAX6can enhance algorithmic performance. Our findings have implications forPAX6variant interpretation in clinical settings.