TBX5-encoded T-box transcription factor 5 variant T223M is associated with long QT syndrome and pediatric sudden cardiac death.

Long QT syndrome (LQTS) is a genetic disease resulting in a prolonged QT interval on a resting electrocardiogram, predisposing affected individuals to polymorphic ventricular tachycardia and sudden death. Although a number of genes have been implicated in this disease, nearly one in four individuals exhibiting the LQTS phenotype are genotype-negative. Whole-exome sequencing identified a missense T223M variant in TBX5 that cosegregates with prolonged QT interval in a family with otherwise genotype-negative LQTS and sudden death. The TBX5-T223M variant was absent among large ostensibly healthy populations (gnomAD) and predicted to be pathogenic by in silico modeling based on Panther, PolyPhen-2, Provean, SIFT, SNAP2, and PredictSNP prediction tools. The variant was located in a highly conserved region of TBX5 predicted to be part of the DNA-binding interface. A luciferase assay identified a 57.5% reduction in the ability of TBX5-T223M to drive expression at the atrial natriuretic factor promotor compared to wildtype TBX5 in vitro. We conclude that the variant is pathogenic in this family, and we put TBX5 forward as a disease susceptibility allele for genotype-negative LQTS. The identification of this familial variant may serve as a basis for the identification of previously unknown mechanisms of LQTS with broader implications for cardiac electrophysiology.

GENESIS: Gene-Specific Machine Learning Models for Variants of Uncertain Significance Found in Catecholaminergic Polymorphic Ventricular Tachycardia and Long QT Syndrome-Associated Genes.

BACKGROUND: Cardiac channelopathies such as catecholaminergic polymorphic tachycardia and long QT syndrome predispose patients to fatal arrhythmias and sudden cardiac death. As genetic testing has become common in clinical practice, variants of uncertain significance (VUS) in genes associated with catecholaminergic polymorphic ventricular tachycardia and long QT syndrome are frequently found. The objective of this study was to predict pathogenicity of catecholaminergic polymorphic ventricular tachycardia-associated RYR2 VUS and long QT syndrome-associated VUS in KCNQ1, KCNH2, and SCN5A by developing gene-specific machine learning models and assessing them using cross-validation, cellular electrophysiological data, and clinical correlation. METHODS: The GENe-specific EnSemble grId Search framework was developed to identify high-performing machine learning models for RYR2, KCNQ1, KCNH2, and SCN5A using variant- and protein-specific inputs. Final models were applied to datasets of VUS identified from ClinVar and exome sequencing. Whole cell patch clamp and clinical correlation of selected VUS was performed. RESULTS: The GENe-specific EnSemble grId Search models outperformed alternative methods, with area under the receiver operating characteristics up to 0.87, average precisions up to 0.83, and calibration slopes as close to 1.0 (perfect) as 1.04. Blinded voltage-clamp analysis of HEK293T cells expressing 2 predicted pathogenic variants in KCNQ1 each revealed an ≈80% reduction of peak Kv7.1 current compared with WT. Normal Kv7.1 function was observed in KCNQ1-V241I HEK cells as predicted. Though predicted benign, loss of Kv7.1 function was observed for KCNQ1-V106D HEK cells. Clinical correlation of 9/10 variants supported model predictions. CONCLUSIONS: Gene-specific machine learning models may have a role in post-genetic testing diagnostic analyses by providing high performance prediction of variant pathogenicity.