Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1
Journal of Clinical Investigation · 02.11.2026 · 136 (21)
DOI: 10.1172/jci207160 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Clinical Investigation, online erschienen am 17.09.2026. Verfasst von Jeffrey D Calhoun und 16 weiteren Autor:innen. Beteiligte Einrichtung: Ken and Ruth Davee Department of Neurology, Northwestern Feinberg School of Medicine, Chicago, Illinois, USA. Hauptthemen laut MEDLINE: Munc18 Proteins, Machine Learning, Epilepsy, Mutation, Missense. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NINDS NIH HHS, NINDS.
Abstract (Originalsprache)
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Ken and Ruth Davee Department of Neurology, Northwestern Feinberg School of Medicine, Chicago, Illinois, USA.
- Center for Neurogenetics, Feil Family Brain and Mind Research Institute, Weill Cornell Medicine, New York, New York, USA.
- Northwestern IT Research Computing and Data Services, Evanston, Illinois, USA.
- Departments of Mathematics, Biochemistry & Cell Biology and Biomedical Data Science, Dartmouth College, Hanover, New Hampshire, USA.
- Department of Pediatrics.
- Department of Neurology.
Förderung
- NINDS NIH HHS
- NINDS
Zitieren
APA
Calhoun, J. D., Wang, C., Biar, C. G., Gunti, J. R., Lee, J. S., Geller, A. M., Hong, J. H., Schnell, S., Dang, L. T., Wang, Y., Parent, J. M., Isom, L. L., Uhler, M. D., Mefford, H. C., Ross, M. E., Aguiar-Pulido, V., & Carvill, G. L. (2026). Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1. Journal of Clinical Investigation, 136(21). https://doi.org/10.1172/jci207160
Vancouver
Calhoun JD, Wang C, Biar CG, Gunti JR, Lee JS, Geller AM, et al. Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1. Journal of Clinical Investigation. 2026;136(21). doi:10.1172/jci207160
BibTeX
@article{Calhoun2026,
author = {Calhoun, Jeffrey D and Wang, Chengbing and Biar, Carina G and Gunti, Jonathan R and Lee, John S and Geller, Aaron M and Hong, Jung H and Schnell, Santiago and Dang, Louis T and Wang, Yu and Parent, Jack M and Isom, Lori L and Uhler, Michael D and Mefford, Heather C and Ross, M Elizabeth and Aguiar-Pulido, Vanessa and Carvill, Gemma L},
title = {Gene-specific machine learning model EpiPred identifies likely pathogenic variants in the epilepsy-related gene STXBP1},
journal = {Journal of Clinical Investigation},
year = {2026},
volume = {136},
number = {21},
doi = {10.1172/jci207160}
}
EUVIMED