Gene-specific pathogenicity predictor for chromatin remodeling BAF complex-associated neurodevelopmental disorders

Clinical Snapshot

Key Findings

• P Value: Not reported

• Effect Size: Accuracy 0.93 for SMARCA2/4, 0.91 for all BAF genes

• Primary Outcome: Prediction accuracy for pathogenic variants in BAF complex genes

• Nnt Or Sensitivity: Superior area under precision-recall curve compared to existing predictors

• Confidence Interval: Not reported

Clinical Application

Computationally inexpensive tool suitable for integration into clinical genetic testing workflows Relevant to Australian genetic counselling services and could support PBS-funded genetic testing interpretation for neurodevelopmental disorders Patients with suspected BAF complex-associated neurodevelopmental disorders undergoing genetic testing

Abstract

Advancements in whole-genome sequencing have increased the number of variants of uncertain significance (VUS) identified in human genomes. This has created a diagnostic bottleneck for genetic counselors tasked with sifting through these variants and determining those most likely to be causative for a patient's clinical presentation. Machine learning (ML) tools can aid in identifying pathogenic variants from VUS, but there is a need for gene-specific algorithms that predict pathogenic variants with high accuracy. To address this need, we present a workflow for developing gene-specific, ensemble-learning ML tools, that leverage outputs from other algorithms, locations of variants within the gene, and evolutionary conservation data to make a prediction of pathogenicity. Variants in SMARCA2 and SMARCA4 that are associated with rare neurodevelopmental diseases were used to screen 15 ML algorithms. A random forest learner was tuned to yield a final accuracy of 0.93 on holdout data. Generalizing this predictor to other BRG1/BRM-associated factor (BAF) complex proteins resulted in a sharp decline in performance. We trained a final predictor for all genes in the study to create a predictor that identifies pathogenic variants in these BAF subunits with an accuracy of 0.91 on holdout data. This predictor specific to BAF complex proteins performs with higher accuracy and area under the precision-recall curve than any other predictor. The decline in performance when generalized to other proteins emphasizes the need for the gene-specific calibration of predictors. Our workflow for the development of such models provides a quick, computationally inexpensive route for improving the ML tools available to genetic counselors.

References

1. 1.Hack, J., & Nazim, M. (2026). Gene-specific pathogenicity predictor for chromatin remodeling BAF complex-associated neurodevelopmental disorders. HGG Advances. https://doi.org/10.1371/journal.pone.0210475