MISTIC: A prediction tool to reveal disease-relevant deleterious missense variants.

Kirsley Chennen,Thomas Weber,Xavière Lornage,Olivier Poch,Johann Böhm,Arnaud Kress,Jocelyn Laporte,Julie Thompson,Miguel A Andrade-Navarro

doi:10.1371/journal.pone.0236962

Abstract

The diffusion of next-generation sequencing technologies has revolutionized research and diagnosis in the field of rare Mendelian disorders, notably via whole-exome sequencing (WES). However, one of the main issues hampering achievement of a diagnosis via WES analyses is the extended list of variants of unknown significance (VUS), mostly composed of missense variants. Hence, improved solutions are needed to address the challenges of identifying potentially deleterious variants and ranking them in a prioritized short list. We present MISTIC (MISsense deleTeriousness predICtor), a new prediction tool based on an original combination of two complementary machine learning algorithms using a soft voting system that integrates 113 missense features, ranging from multi-ethnic minor allele frequencies and evolutionary conservation, to physiochemical and biochemical properties of amino acids. Our approach also uses training sets with a wide spectrum of variant profiles, including both high-confidence positive (deleterious) and negative (benign) variants. Compared to recent state-of-the-art prediction tools in various benchmark tests and independent evaluation scenarios, MISTIC exhibits the best and most consistent performance, notably with the highest AUC value (> 0.95). Importantly, MISTIC maintains its high performance in the specific case of discriminating deleterious variants from benign variants that are rare or population-specific. In a clinical context, MISTIC drastically reduces the list of VUS (<30%) and significantly improves the ranking of “causative” deleterious variants. Pre-computed MISTIC scores for all possible human missense variants are available at http://lbgi.fr/mistic.

Highlights

Next-Generation Sequencing technologies, such as Whole Exome Sequencing (WES) involving the targeted sequencing of exonic regions of all known protein-coding genes, have gradually replaced conventional approaches for the study of rare Mendelian disorders since 2010 [1]
The performance of the Logistic Regression models with less than 113 features are lower with a mean AUC value of 0.820, while models with more than 113 features have a stable performance with a mean AUC value of 0.826
Since the global minor allele frequency (MAF) is an important feature in the MISTIC model, MAF values are often missing for deleterious and population-specific benign variants, we evaluated the performance of MISTIC in discriminating deleterious variants from rare benign variants when no MAF data are available

Summary

Introduction

Next-Generation Sequencing technologies, such as Whole Exome Sequencing (WES) involving the targeted sequencing of exonic regions of all known protein-coding genes, have gradually replaced conventional approaches for the study of rare Mendelian disorders since 2010 [1]. Their usage is shifting from research investigations of disease-causing variants to routine clinical exome analysis for diagnosis of Mendelian disorders with known genetic aetiology. MISTIC: A prediction tool to reveal disease-relevant deleterious missense variants “Myocapture” sequencing project, the Fondation pour la Recherche Medicale, and the Association Francaise contre les Myopathies

Methods

Results

Conclusion