Cystinosis is a rare genetic disease, that causes cysteine to accumulate in cells, leading to severe damage to organs such as the kidneys, eyes, and more. It affects 1 in 100,000-200,000 births, posing lifelong risks.
Cystinosis currently lacks a cure, and there is an urgent need for better interventions to improve the quality of life and long-term outcomes for patients.
Recent advances in preclinical model systems and disease-specific screening technologies have the potential to unveil pathophysiological mechanisms and evaluate therapeutic hypotheses.
The Mechanisms of Inherited Kidney Disorders (MIKADO) group at the University of Zurich (UZH) and DeepLife are collaborating to create digital twins of cystinosis-affected cells.
The MIKADO group, a translational team of the Institute of Physiology of the UZH focused on generating evidence-driven insights to understand and potentially reverse rare inherited diseases, and DeepLife, an innovative startup using state-of-the-art AI technology to develop digital twins of cells, today announced a research collaboration designed to accelerate the identification of biological pathways with the potential to be therapeutically targeted.
The MIKADO group will use its multi-omics databank from preclinical models and cystinosis patient cells alongside DeepLife's AI tools to create digital twins of diseased cells. The digital models will pinpoint the fundamental biological processes involved in cystinosis, including those with demonstrable relevance to evolutionary conservation. Subsequently the MIKADO group at UZH will enhance drug discovery using digital twins of cells for in silico screening and target identification.
“I am thrilled by the collaboration between MIKADO, ITINERARE and DeepLife. With the power of AI-driven digital twins and digital technologies, we intend to accelerate therapeutic discoveries and to bring innovative and more effective medicines to cystinosis patients while decreasing costs and increasing probabilities of success” said Olivier Devuyst, MD, Ph.D., head of MIKADO group at the UZH.
“Combining excellence in data with state-of-the-art generative AI approaches to understand the disease at a cellular level is one of the most promising and fastest opportunities for patients to access reliable treatment” said Jonathan Baptista, CEO of DeepLife.
“Employing virtual “replicas” of cystinosis-affected cells, tissues, and organs that incorporate detailed mechanistic data, disease manifestations, electronic health records, and lifestyle traits could help uncover disease signatures that predict drug efficacy and elucidate drug mode of action to improve clinical outcomes” said Alessandro Luciani, Ph.D., team lead at MIKADO.
Cystinosis is one of a family of approximately 70 rare inborn diseases of the metabolism, known as lysosomal storage diseases, which collectively affect 1 in 5,000 live births. Cystinosis is caused by inactivating mutations in the CTNS gene encoding the proton−driven transporter cystinosin, which exports cystine from the lysosome. Its functional loss leads cystine to accumulate within the lysosomes of tissues across the body, culminating in severe multiorgan dysfunctions that affect primarily the brain, eyes, liver, muscles, pancreas, and kidneys. The first manifestation of cystinosis, usually within the first months of life, reflects the dysfunction of the kidney proximal tubule, causing loss of vital solutes most often complicated by chronic kidney disease and life−threatening complications. Later, patients with cystinosis can also develop hypothyroidism, hypogonadism, diabetes, myopathy, deterioration of the vision, and decline of the central nervous system. Beyond supportive care, the only available FDA-approved strategy to counteract cystine storage is the oral administration of cysteamine, which allows cystine to exit from the lysosomes. However, cysteamine treatment is hampered by side effects and poor tolerance, and it does not prevent nor treat the dysfunction of the proximal tubule and kidney disease. Therefore, there is an urgent need to develop novel therapeutics for this devastating disease.
Employing algorithms to mirror complex biological processes, DeepLife's Digital Twin of Cells functions as a numerical representation of cells, able to mimic intricate cellular events that guide scientific decision-making. Built on DeepLife's OMICS Catalog and atlases, which provide an extensive repository of single-cell RNA sequencing data covering a plethora of cell types and tissues, this Digital Twin utilizes state-of-the-art large language models (LLM) for processing and interpreting vast biological datasets. DeepLife’s Digital Twin technology serves as a foundation model, which can simulate the biological behavior of real-world cells under varying conditions or disease states.
DeepLife is a digital biotech company based in Paris that develops novel biomedical data analysis approaches based on state-of-the-art multi-omics data, machine learning, and systems engineering to accelerate drug discovery. DeepLife has recently developed AI-Based technology to build digital twins of human cells, enabling scientists to rapidly evaluate how unhealthy cells respond to drug candidates in silico, decipher therapeutic mechanisms of action, and identify new targets and biomarkers.
The group “Mechanisms of Inherited Kidney Disorders” (MIKADO) led by Prof. Dr. med. Olivier Devuyst and Dr. Alessandro Luciani is investigating the fundamental mechanisms of disorders affecting the epithelial cells lining the kidney tubule, leading to chronic kidney disease (CKD) ⎯ one of the fastest growing disease worldwide and a major public health burden. Combining human genetic studies with deep phenotyping on innovative model organisms and physiologically relevant cellular systems, and integrating them with OMICs technologies and cutting-edge screening assays, we are applying the knowledge gained from epithelial cell biology to develop disease biomarkers and novel therapeutics that might improve the care of patients with genetic disorders affecting the kidney and other organs. The MIKADO group belongs to the Innovative Therapies in Rare Diseases (ITINERARE) University Research Priority Program of the UZH.