Discordance between a deep learning model and clinical-grade variant pathogenicity classification in a rare disease cohort.

Genetic testing has become an essential component in the diagnosis and management of a wide range of clinical conditions, from cancer to developmental disorders, especially in rare Mendelian diseases. Efforts to identify rare phenotype-associated variants have predominantly focused on protein-truncating variants, while the interpretation of missense variants presents a considerable challenge. Deep learning algorithms excel in various applications across biomedical tasks 1,2 , yet accurately distinguishing between pathogenic and benign genetic variants remains an elusive goal 3-5 . Specifically, even the most sophisticated models encounter difficulties in accurately assessing the pathogenicity of missense variants of uncertain significance (VUS). Our investigation of AlphaMissense (AM) 5 , the latest iteration of deep learning methods for predicting the potential functional impact of missense variants and assessing gene essentiality, reveals important limitations in its ability to identify pathogenic missense variants within a rare disease cohort. Indeed, AM struggles to accurately assess the pathogenicity of variants in intrinsically disordered regions (IDRs), leading to unreliable gene-level essentiality scores for certain genes containing IDRs. This limitation highlights the challenges in applying AM faces in the context of clinical genetics 6 .