Genet Med. 2026 May 27:102614. doi: 10.1016/j.gim.2026.102614. Online ahead of print.
ABSTRACT
PURPOSE: Variants in SMARCB1, encoding a core subunit of the BAF chromatin remodeling complex, are associated with intellectual developmental disorders, particularly Coffin-Siris Syndrome (CSS), though the genotype-phenotype spectrum remains incompletely defined. This study aims to assess correlations between SMARCB1 variant location and phenotypic manifestations.
METHODS: We analyzed 31 individuals with pathogenic or likely pathogenic SMARCB1 variants using multimodal approaches, integrating clinical, structural, and machine learning analyses. We predicted variant effects via 3D protein modelling, assessed facial similarity using GestaltMatcher, and conducted phenotype-driven genotype prediction using machine learning classifiers.
RESULTS: Variants clustered within N-terminal (winged-helix/SNF5) and C-terminal (αC-helix) regions. C-terminal CSS variants were associated with more severe speech delay, microcephaly and cleft palate, exhibiting stronger facial gestalt similarity. XGBoost achieved 96.7% accuracy in classifying variant location from phenotype alone. While gestalt is a key feature delineating variants at the αC helix, overall clinical features have greater predictive power for N-terminal variants.
CONCLUSION: Using detailed phenotyping and machine learning algorithms we identify differences between individuals with N-terminus and C-terminus SMARCB1 variants. Our study underscores the importance of multi-modal assessments for genotype-phenotype associations, suggesting integrated modelling can provide insights into SMARCB1 variant effects and biological function, with potential for improvement of diagnostic strategies.
PMID:42206491 | DOI:10.1016/j.gim.2026.102614
