Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1
11 affiliations
- 1Ken and Ruth Davee Department of Neurology, Northwestern Feinberg School of Medicine, Chicago, Illinois, USA.
- 2Center for Neurogenetics, Feil Family Brain and Mind Research Institute, Weill Cornell Medicine, New York, New York, USA.
- 3Northwestern IT Research Computing and Data Services, Evanston, Illinois, USA.
- 4Departments of Mathematics, Biochemistry & Cell Biology and Biomedical Data Science, Dartmouth College, Hanover, New Hampshire, USA.
- 5Department of Pediatrics
- 6Department of Neurology
- 7Department of Pharmacology, and
- 8Department of Biological Chemistry and Molecular Neuroscience Institute, University of Michigan, Ann Arbor, Michigan, USA.
- 9Center for Pediatric Neurological Disease Research, St. Jude Children’s Research Hospital, Memphis, Tennessee, USA.
- 10Department of Computer Science, University of Miami, Miami, Florida, USA.
- 11Department of Pharmacology, Northwestern Feinberg School of Medicine, Chicago, Illinois, USA.
Abstract
STXBP1 variants are a frequent cause of early onset developmental and epileptic encephalopathies and related neurodevelopmental disorders, but the clinical interpretation of these variants remains a major challenge. Most reported STXBP1 missense variants are classified as variants of uncertain significance (VUS), complicating diagnosis, counseling, and patient eligibility for precision therapies. Here, we developed EpiPred, a gene-specific machine learning classifier that predicts the pathogenicity of STXBP1 missense variants and tests these predictions using empirical evidence from well-established cellular assays. Trained on a curated set of pathogenic and benign variants, EpiPred outperformed global prediction tools in accuracy, sensitivity, and specificity. We validated the model’s predictions using variant effect assays that measure protein abundance, solubility, stability, and interaction with the SNARE complex partner syntaxin 1. These biochemical readouts aligned closely with model outputs and enabled reclassification of several possibly misdiagnosed variants, which warrant further validation and clinical reevaluation. We deployed EpiPred in an interactive web application that allows clinicians, researchers, and patients to explore predictions for all possible STXBP1 missense variants. By identifying likely pathogenic STXBP1 variants, including those that may respond to emerging therapies, such as protein stabilizers. By coupling gene-calibrated machine learning with orthogonal variant-effect assays and public deployment, EpiPred provides a transferable framework for VUS resolution, trial enrichment, and precision diagnosis across clinically actionable Mendelian disease genes.
Related
- Population-specific differences in ClinVar pathogenic and likely pathogenic variants of epilepsy-associated genes between East Asian and non-finnish European populations: a nucleotide-resolved gnomAD v4.1.1 analysis
- Integrative Bioinformatics Analysis Incorporating Artificial Intelligence and Machine Learning Identifies Putative Pathogenic HNF1B Missense Variants Associated with HNF1B-MODY
- Altered astrocyte morphology in pathogenic HEPACAM variants: a multipoint analysis and new machine learning framework for 3D Sholl analysis
- Cis-Attenuation of Pathogenic Scn8a Variant Causing Childhood Epilepsy Reveals Opposing Transcriptional Programs Driving NaV1.6 Gain and Loss of Function Phenotypes
- Base Editing as a Therapeutic Strategy for Autosomal Dominant Tubulointerstitial Kidney Disease caused by Pathogenic UMOD Variants
BibTeX
@article{calhoun2026genespecific,
title = {{Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1}},
author = {Jeffrey D. Calhoun and Chengbing Wang and Carina G. Biar and Jonathan R. Gunti and John S. Lee and Aaron M. Geller and Jung H. Hong and Santiago Schnell and Louis T. Dang and Yu Wang and Jack M. Parent and Lori L. Isom and Michael D. Uhler and Heather C. Mefford and M. Elizabeth Ross and Vanessa Aguiar-Pulido and Gemma L. Carvill},
journal = {The Journal of Clinical Investigation},
year = {2026},
month = sep,
doi = {10.1172/jci207160},
url = {https://doi.org/10.1172/jci207160},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1
AU - Jeffrey D. Calhoun
AU - Chengbing Wang
AU - Carina G. Biar
AU - Jonathan R. Gunti
AU - John S. Lee
AU - Aaron M. Geller
AU - Jung H. Hong
AU - Santiago Schnell
AU - Louis T. Dang
AU - Yu Wang
AU - Jack M. Parent
AU - Lori L. Isom
AU - Michael D. Uhler
AU - Heather C. Mefford
AU - M. Elizabeth Ross
AU - Vanessa Aguiar-Pulido
AU - Gemma L. Carvill
PY - 2026
DA - 2026/09/17
JO - The Journal of Clinical Investigation
DO - 10.1172/jci207160
UR - https://doi.org/10.1172/jci207160
AB - STXBP1 variants are a frequent cause of early onset developmental and epileptic encephalopathies and related neurodevelopmental disorders, but the clinical interpretation of these variants remains a major challenge. Most reported STXBP1 missense variants are classified as variants of uncertain significance (VUS), complicating diagnosis, counseling, and patient eligibility for precision therapies. Here, we developed EpiPred, a gene-specific machine learning classifier that predicts the pathogenicity of STXBP1 missense variants and tests these predictions using empirical evidence from well-established cellular assays. Trained on a curated set of pathogenic and benign variants, EpiPred outperformed global prediction tools in accuracy, sensitivity, and specificity. We validated the model’s predictions using variant effect assays that measure protein abundance, solubility, stability, and interaction with the SNARE complex partner syntaxin 1. These biochemical readouts aligned closely with model outputs and enabled reclassification of several possibly misdiagnosed variants, which warrant further validation and clinical reevaluation. We deployed EpiPred in an interactive web application that allows clinicians, researchers, and patients to explore predictions for all possible STXBP1 missense variants. By identifying likely pathogenic STXBP1 variants, including those that may respond to emerging therapies, such as protein stabilizers. By coupling gene-calibrated machine learning with orthogonal variant-effect assays and public deployment, EpiPred provides a transferable framework for VUS resolution, trial enrichment, and precision diagnosis across clinically actionable Mendelian disease genes.
SN - 0021-9738
SN - 1558-8238
ER -