The MSH2 c.2034T>A (p.Tyr678Ter; p.Y678*) variant has been reported in ClinVar as pathogenic by 2 clinical laboratories.¹ This variant is absent from gnomAD v2.1 and gnomAD v4.1, which is below the MSH2 VCEP PM2 threshold of less than 0.00002 in gnomAD v4.² This nonsense variant introduces a premature stop codon at Tyr678; under the MSH2 VCEP specification, nonsense variants at or before codon 891 meet PVS1, and p.(Tyr678Ter) falls within that range.³ SpliceAI predicts no significant splice impact for this variant (max delta score 0.01), which is consistent with premature protein truncation rather than a predicted splice defect.⁴