A predictive framework for stop-loss variants with C-terminal extensions

Abstract Stop codons dictate translation termination, and variants occurring at these sites can result in stop-loss variants, leading to C-terminal extensions with potentially significant functional consequences. Despite their clinical relevance, existing prediction tools—primarily developed for missense variants—lack sufficient accuracy for assessing stop-loss variants, mainly due to their insufficiency in accounting for the sequence features of the extended peptide. To address this gap, we developed TAILVAR (Terminal codon Analysis and Improved prediction of Lengthened VARiants), a machine-learning classifier that integrates multi-omics features spanning transcript- and protein-level properties, along with variant effect annotations. Our analyses showed that transcripts lacking downstream stop codons in the 3’ untranslated region exhibit lower evolutionary constraints. Additionally, we observed that deleterious variants exhibit greater C-terminal hydrophobicity, which is associated with reduced protein stability and increased degradation, as well as a higher aggregation propensity. TAILVAR outperformed existing benchmarks, demonstrating the highest correlation with functional experiments and establishing thresholds to classify variants as benign or pathogenic. This work offers a systematic framework for interpreting stop-loss variants, providing precise predictions of elongated protein effects that may aid genetic diagnosis and facilitate the discovery of novel disease-associated genes. Competing Interest Statement The authors have declared no competing interest.