G4mer: An RNA language model for transcriptome-wide identification of G-quadruplexes and disease variants from population-scale genetic data

RNA G-quadruplexes (rG4s) are key regulatory elements in gene expression, yet theeffects of genetic variants on rG4 formation remain underexplored. Here, we introduceG4mer, an RNA language model that predicts rG4 formation, classifies rG4 subtypes, andevaluates the effects of genetic variants across the transcriptome. G4mer significantly im-proves accuracy over existing methods and uncovers subtype-specific differences in mu-tational sensitivity and evolutionary constraint, highlighting sequence length and flankingmotifs as important rG4 features. Applying G4mer to 5′ untranslated region (UTR) vari-ations, we identify variants in breast cancer-associated genes that alter rG4 formation andvalidate their impact on structure and gene expression. These results demonstrate the poten-tial of integrating computational models with experimental approaches to study rG4 func-tion, especially in diseases where non-coding variants are often overlooked. To supportbroader applications, G4mer is available as both a web tool and a downloadable model.