Accelerating Leigh syndrome drug discovery through deep learning screening in brain organoids
Clinical Snapshot
PICO Framework
| P — Population | Leigh syndrome models (SURF1 variant cerebral organoids, yeast models, and human neurons) |
| I — Intervention | Deep learning-guided drug repurposing screen and survival drug screen identifying azole compounds (talarozole and sertaconazole) |
| C — Comparator | Control organoids and untreated models |
| O — Outcomes | Neuronal morphogenesis rescue, lactate release reduction, growth rate improvement, and mechanistic pathway modulation |
Bottom Line
This innovative preclinical study identifies azole antifungal compounds as potential therapeutics for Leigh syndrome through sophisticated screening combining deep learning and human brain organoids. The convergent results from computational and experimental approaches strengthen the findings, while mechanistic insights into retinoic acid and lipid metabolism pathways provide biological plausibility. However, the study represents early-stage drug discovery requiring extensive clinical validation. The identified compounds (talarozole and sertaconazole) have established safety profiles from other indications, potentially facilitating clinical translation. For Australian clinicians managing Leigh syndrome patients, these findings offer hope for future therapeutic options but require cautious interpretation pending human studies. The methodology demonstrates promising new approaches for rare disease drug discovery that could benefit other mitochondrial disorders.
Key Findings
P Value: Not reported
Effect Size: Not specified in abstract
Primary Outcome: Rescue of neuronal morphogenesis defects in Leigh syndrome organoids
Nnt Or Sensitivity: Two azole compounds (talarozole and sertaconazole) showed therapeutic activity across multiple endpoints
Confidence Interval: Not reported
Clinical Application
Moderate - requires clinical trials to establish safety and efficacy in humans Relevant to Australian rare disease programs; would require TGA approval for clinical trials and eventual PBS consideration for orphan drug status Patients with Leigh syndrome, particularly those with SURF1 variants
Abstract
Leigh syndrome (Leigh) is an untreatable mitochondrial disorder characterized by lactic acidosis and basal ganglia and midbrain pathology, leading to psychomotor regression and early death. We previously uncovered impaired neuronal morphogenesis in Leigh cerebral organoids carrying SURF1 gene variants. Leveraging this phenotype, we here develop a deep learning algorithm tailored for cell type-specific drug repurposing screening. In parallel, we perform a survival drug screen in a yeast model of Leigh. The two approaches independently converge on azole compounds, two of which - talarozole and sertaconazole - rescue neuronal morphogenesis in Leigh neurons and lower lactate release and improve growth rate in Leigh midbrain organoids. Mechanistically, these compounds modulate the retinoic acid pathway and membrane-associate lipid metabolism. The findings highlight azoles as promising candidates for Leigh and demonstrate the potential of combining in silico screens with human brain organoids as new approach methodologies (NAMs) to advance the discovery of therapeutics addressing rare neurodevelopmental disorders.
References
- 1.Menacho, C., Okawa, S., Álvarez-Merz, I., Wittich, A., Muñoz-Oreja, M., Lisowski, P., Martín, M. L., Pentimalli, T. M., Zakin, S., Thevandavakkam, M., Jerred, C., Lickfett, S., Petersilie, L., Rybak-Wolf, A., Seibt, A., Herebian, D., Inak, G., Brodesser, S., Zaliani, A., Mlody, B., Donnelly, J., Woleben, K., Soriano, F. X., Fernandez-Checa, J. C., Ventura, N., Cambridge, S., Mayatepek, E., Spinazzola, A., Schuelke, M., Rajewsky, N., Rossi, A., Peralvarez-Marin, A., Distelmaier, F., Perlstein, E., Holt, I. J., Puighermanal, E., Pless, O., Rose, C. R., Del Sol, A., & Prigione, A. (2026). Accelerating Leigh syndrome drug discovery through deep learning screening in brain organoids. Nature Communications. https://doi.org/10.1093/nar/gkv1042
Related Research
European radiology
Deep learning improves image quality in motion-robust and sedation-free pediatric brain MRI
2 Aug 2026
Seminars in fetal & neonatal medicine
Intraventricular hemorrhage in preterm infants: A systematic review of risk- and outcome-prediction models
2 Aug 2026
Indian journal of pediatrics
Emerging Applications of Artificial Intelligence in Pediatric Care
2 Aug 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service