The 3D model of the midbrain showed improved growth and lower lactate release with talarozole and sertaconazole.
Image Credit: © HHU / Carmen Menacho
Scientific Frontline: Extended "At a Glance" Summary: AI-Assisted Therapy Discovery for Leigh Syndrome
The Core Concept: Researchers have combined 3D brain organoid models and artificial intelligence to identify potential existing drugs for repurposing to treat Leigh Syndrome, a rare and fatal mitochondrial disease.
Key Distinction/Mechanism: Unlike traditional drug discovery, this approach utilizes lab-grown pluripotent stem cells developed into 3D brain organoids that mimic the genetic variations of the disease, coupled with a deep-learning algorithm to rapidly screen and identify promising existing medications.
Major Frameworks/Components:
- Pluripotent Stem Cells: Patient cells cultivated and differentiated into specialized biological matter.
- 3D Brain Organoids: Laboratory-generated 3D models imitating human brain tissue structure and the specific genetic mutation triggering Leigh Syndrome.
- Deep Learning AI: An algorithm designed to optimize the drug screening process and predict therapeutic candidates.
- Drug Repurposing: Evaluating pre-existing, approved medications (such as talarozole and sertaconazole) for new clinical applications to bypass lengthy initial development phases.
Branch of Science: Molecular Medicine, Systems Biomedicine, Bioinformatics, Artificial Intelligence, and Pediatric Neurology.
Future Application: The identified drugs, talarozole and sertaconazole, will undergo further clinical evaluation for Leigh Syndrome patients, while the underlying AI algorithm can be adapted to discover therapies for other rare diseases.
Why It Matters: Leigh Syndrome currently has no approved therapies, and low patient numbers make traditional clinical trials difficult; this synergistic AI and organoid-driven methodology significantly accelerates the identification of viable treatments for rare, life-limiting diseases.
The need for medical treatments for rare diseases such as Leigh Syndrome is high. However, low patient numbers make research into treatments difficult. Together with a team from the University of Luxembourg, researchers from Heinrich Heine University Düsseldorf (HHU) and University Hospital Düsseldorf (UKD) have succeeded in utilizing artificial intelligence (AI) to establish a model that enables a better understanding of Leigh Syndrome. In the course of this work, they succeeded in identifying new drug candidates for the treatment of the disease.
With one case in 36,000 live births, Leigh Syndrome is classified as a “rare disease”. According to the European definition, a rare disease affects fewer than five in 10,000 people. The progressive brain disease is a so-called mitochondrial disease, i.e. a disease that affects energy metabolism. It usually manifests in childhood and causes brain damage and necrosis, which can lead to severe symptoms such as neurodevelopmental delay, epileptic seizures, muscular weakness, and respiratory failure. Those affected have an extremely limited life expectancy, and most die within a few years of diagnosis. No therapy has yet been approved.
The low number of cases makes research into Leigh Syndrome, and the identification of potential therapy approaches a challenge. The situation is further complicated by the fact that there are very few cellular or animal models, which can faithfully recapitulate the course of the disease in human beings.
Together with Professor Dr Antonio Del Sol (Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, CICbioGUNE Bizkaia, Spain) and his research group, the team headed by Professor Dr Alessandro Prigione (Department of General Pediatrics, Neonatology and Pediatric Cardiology) set out to develop models to advance research into Leigh Syndrome. The researchers in Düsseldorf began by using cells from patients to develop so-called pluripotent stem cells, which have the biological ability to differentiate into all types of cells in the body. The researchers were then able to use these cells to develop brain organoids in the laboratory. These organoids, which can be understood as 3D models of the brain, imitate the structure of and have a similar tissue organization to the human brain. Professor Prigione and his team succeeded in imitating the gene variation, which triggers Leigh Syndrome in the human brain, in the brain organoids, making it possible to map and research Leigh Syndrome and the use of various medications in the laboratory.
Using the brain organoids, the researchers conducted a screening process to identify potential drug candidates for the treatment of Leigh Syndrome. They examined the effect of various existing medications, some of which have been approved for other indications, on the organoids. This approach of expanding the use of existing medications to treat other conditions is referred to as repurposing. The researchers’ aim was to utilize AI to optimize this process and so the Luxembourg team headed by Professor Del Sol developed an algorithm based on deep learning to help identify drug candidates.
Using this algorithm, the researchers together managed to identify two potentially suitable drug candidates for the treatment of Leigh Syndrome – talarozole and sertaconazole. Talarozole was originally developed to treat acne, while sertaconazole is already approved for the topical treatment of fungal skin infections such as athlete’s foot. The research group of Professor Prigione was able to demonstrate in brain organoids that treatment with both drugs sustained brain cell development, improved growth and reduced lactate release. These results suggest that the drugs could also have a positive effect on disease progression in patients and their ongoing development.
“The development of the brain organoids represents a great success for research into rare diseases,” says Professor Prigione. “The fact that we were able to identify two potential drug candidates using the organoids is highly promising. Further studies are now needed to establish exactly how effective talarozole and sertaconazole are in patients, but we are optimistic.” Professor Del Sol adds: “Screening existing drugs for repurposing is an important approach in the search for therapeutic strategies for rare diseases. We have demonstrated that the use of AI can optimize this process. In the future, we will be able to use the algorithm we have developed not only for Leigh syndrome but also for other diseases.”
Additional information: In addition to HHU, the UKD and the University of Luxembourg, other organizations involved in the research included the University of Pittsburgh, the Fraunhofer Institute for Translational Medicine and Pharmacology ITMP in Hamburg, the Biogipuzkoa Health Institute San Sebastian, the Max Delbrück Center for Molecular Medicine in Berlin, the Charité hospital Berlin, the Polish Academy of Sciences in Warsaw and the Universidad Autònoma de Barcelona.
Published in journal: Nature Communications
Title: Accelerating Leigh syndrome drug discovery through deep learning screening in brain organoids
Authors: Carmen Menacho, Satoshi Okawa, Iris Álvarez-Merz, Annika Wittich, Mikel Muñoz-Oreja, Pawel Lisowski, Mario López Martín, Tancredi Massimo Pentimalli, Shiri Zakin, Mathuravani Thevandavakkam, Caleb Jerred, Selene Lickfett, Laura Petersilie, Agnieszka Rybak-Wolf, Annette Seibt, Diran Herebian, Gizem Inak, Susanne Brodesser, Andrea Zaliani, Barbara Mlody, Justin Donnelly, Kasey Woleben, Francesc Xavier Soriano, Jose C. Fernandez-Checa, Natascia Ventura, Sidney Cambridge, Ertan Mayatepek, Antonella Spinazzola, Markus Schuelke, Nikolaus Rajewsky, Andrea Rossi, Alex Peralvarez-Marin, Felix Distelmaier, Ethan Perlstein, Ian J. Holt, Emma Puighermanal, Ole Pless, Christine R. Rose, Antonio Del Sol, and Alessandro Prigione
Source/Credit: Heinrich Heine University Düsseldorf | Anne Wansing
Reference Number: med042026_01
.jpg)