Deep learning drug screens in brain organoid models identify azole compounds for Leigh syndrome

The uploaded lipidomics dataset contains Liquid Chromatography-Tandem Mass Spectrometry (LC-MS/MS) and Shotgun Lipidomics data associated to the publication of Carmen Menacho et al. from the laboratory of Alessandro Prigione. The title of the publication is: Deep learning drug screens in brain organoid models identify azole compounds for Leigh syndrome This article will be published in Nature Communications. Article 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 developed a deep learning algorithm tailored for cell type-specific drug repurposing screening. In parallel, we performed a survival drug screen in a yeast model of Leigh. The two approaches independently converged on azole compounds, two of which - talarozole and sertaconazole - rescued neuronal morphogenesis in Leigh neurons and lowered lactate release and improved growth rate in Leigh midbrain organoids. Mechanistically, the compounds modulated 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 for therapeutic discovery of rare neurodevelopmental diseases.