Exploring the Future of Glaucoma Treatment: AI-Driven Drug Discovery
Glaucoma, a progressive eye disorder characterized by fluid buildup and subsequent increased intraocular pressure, affects nearly 112 million people worldwide by 2024. Without proper treatment, it can lead to blindness. While treatments exist to manage eye hypertension and slow down the progression, a cure for glaucoma remains elusive.
However, a team of researchers from various facilities and medical centers in China is working together to change that. They are employing an AI-directed drug screening technique in their quest for glaucoma medication by trying to identify potential RIPK3 inhibitors.
Understanding Glaucoma
Retinal ganglion cells (RGCs) play a crucial role in transmitting visual signals from the eyes to the brain. Their degeneration is a key marker of glaucoma, leading to optic nerve damage. In recent years, scientists have focused on developing neuroprotective drugs that could save RGCs and restore optic nerve paths.
Necroptosis, a cell death process that combines aspects of both apoptosis and necrosis, plays a significant role in RGC loss. Receptor-interacting protein kinase 3 (RIPK3), a key signal molecule, is known to play a critical role in necroptosis, making it a promising target for therapeutic intervention.
AI-Driven Drug Discovery
The research team, led by Dr. Yuanxu Gao from Macau University of Science and Technology and Professor Zhang Kang from Guangzhou National Laboratory, used advanced AI models, including language models (LLMs) and neural network models, to identify RIPK3-targeted molecules. They generated a random AI-generated list and employed other AI models like DynamicBind to predict drug affinity and interaction patterns.
Through this AI-driven approach, the team identified HG9-91-01, dabrafenib, AZD5423, GSK840, and HS-1371 as the most potent small-molecule connections that could effectively target RIPK3. AI predictive models suggested HG9-91-01 as the most promising candidate, with molecular simulations confirming its stability in complexing with RIPK3. The compound also showed good results in safety and drug-related tests based on ADMET predictions.
Lab Validation
The effectiveness of the compound was validated through laboratory experiments. In an in vitro model mimicking optic nerve damage, RGCs exposed to oxygen-glucose deprivation (OGD) showed higher survival rates when treated with HG9-91-01 compared to other candidates. The compound also reduced the presence of gasdermin D (GSDMD)-positive cells, a marker of pyroptosis, a type of inflammatory cell death.
“The study investigates potential drug treatments targeting RIPK3 to prevent RGC death and examines their role in inhibiting PANoptosis, including cell-cell communication and cell death cascades,” said the researchers.
AI in Drug Development
The findings of this study offer intriguing insights into the potential of combining AI algorithms and traditional screening methods for drug development, which could lead to a logical and data-driven drug development model. Biologically investigating drug-target interactions is time- and resource-intensive, making AI-based predictive models a valuable tool for simplifying and expediting this process.
To confirm that HG9-91-01 can protect the retina in AOH patients, the team plans to conduct further retinal studies.
In 2022, Dutch researchers developed an AI algorithm that significantly improved glaucoma diagnosis, enabling non-specialist eye doctors to diagnose glaucoma as accurately as glaucoma specialists. This advancement, initiated by Het Oogziekenhuis Rotterdam, has the potential to enhance glaucoma care and management worldwide.
