BACKGROUND: Retinal ganglion cell (RGC) death caused by acute ocular hypertension is an important characteristic of acute glaucoma. Receptor-interacting protein kinase 3 (RIPK3) that mediates necroptosis is a potential therapeutic target for RGC death. However, the current understanding of the targeting agents and mechanisms of RIPK3 in the treatment of glaucoma remains limited. Notably, artificial intelligence (AI) technologies have significantly advanced drug discovery. This study aimed to discover RIPK3 inhibitor with AI assistance. METHODS: An acute ocular hypertension model was used to simulate pathological ocular hypertension in vivo . We employed a series of AI methods, including large language and graph neural network models, to identify the target compounds of RIPK3. Subsequently, these target candidates were validated using molecular simulations (molecular docking, absorption, distribution, metabolism, excretion, and toxicity [ADMET] prediction, and molecular dynamics simulations) and biological experiments (Western blotting and fluorescence staining) in vitro and in vivo . RESULTS: AI-driven drug screening techniques have the potential to greatly accelerate drug development. A compound called HG9-91-01, identified using AI methods, exerted neuroprotective effects in acute glaucoma. Our research indicates that all five candidates recommended by AI were able to protect the morphological integrity of RGC cells when exposed to hypoxia and glucose deficiency, and HG9-91-01 showed a higher cell survival rate compared to the other candidates. Furthermore, HG9-91-01 was found to protect the retinal structure and reduce the loss of retinal layers in an acute glaucoma model. It was also observed that the neuroprotective effects of HG9-91-01 were highly correlated with the inhibition of PANoptosis (apoptosis, pyroptosis, and necroptosis). Finally, we found that HG9-91-01 can regulate key proteins related to PANoptosis, indicating that this compound exerts neuroprotective effects in the retina by inhibiting the expression of proteins related to apoptosis, pyroptosis, and necroptosis. CONCLUSION AI-enabled drug discovery revealed that HG9-91-01 could serve as a potential treatment for acute glaucoma.
Animals ; Glaucoma/metabolism* ; Neuroprotective Agents/pharmacology* ; Mice ; Receptor-Interacting Protein Serine-Threonine Kinases/metabolism* ; Artificial Intelligence ; Retinal Ganglion Cells/metabolism* ; Disease Models, Animal ; Molecular Docking Simulation ; Mice, Inbred C57BL ; Male

Objective:To explore the clinical value of peripheral remnant lipoproteins (RLP), low density lipoprotein cholesterol particle (LDL-P) and sdLDL particle (sdLDL-P) measurement in the diagnosis of carotid plaque, so as to provide practical basis for the accurate diagnosis of carotid plaque and the control of carotid plaque related cardiovascular and cerebrovascular diseases.Methods:People who underwent carotid plaque ultrasound examination in Xingtai Third Hospital , from January 2020 to June 2021 were selected as the research object. According to the ultrasound results, they were divided into carotid plaque group ( n=146) and control group without carotid plaque ( n=149). The fasting RLP, LDL-P and sdLDL-P of the two groups were measured by vertical auto profile (VAP) centrifugal separation phase, and the fasting TG and LDL-C were detected by routine mixed phase method. The indexes were compared between the two groups and the true positive rate, true negative rate, false positive rate and false negative rate of the diagnosis of carotid plaque were analyzed. The receiver operating characteristic curve of each test index was drawn, and AUC was used to evaluate the clinical diagnostic value of each test index for carotid plaque. Results:The levels of RLP, LDL-P and sdLDL-P in carotid plaque group were significantly higher than those in non-carotid plaque group ([1.07±0.36] mmol/L vs [0.59±0.17] mmol/L,[1 300±370] nmol/L vs [781±215] nmol/L,[435±139] nmol/L vs [156±59] nmol/L, all P<0.01). The true positive rate (78.08% [114/146],81.51% [119/146]) and true negative rate (84.56% [126/149], 86.58%[129/149]) of serum RLP and LDL-P for the diagnosis of carotid plaque were significantly higher than TG (58.90%[86/146], 43.62%[65/149]) and LDL-C (59.59% [87/146], 46.98% [70/149]), and the false positive rate (15.44% [23/149], 13.42% [20/149]) and false negative rate (21.92% [32/146], 18.49% [27/146]) were significantly lower than TG (56.38% [84/149], 41.10% [60/146]) and LDL-C (53.02% [79/149], 40.41% [59/146], all P<0.01). The AUC of the ROC curve of RLP (0.890), LDL-P (0.902) and sdLDL-P (0.973) for the diagnosis of carotid plaque was higher than TG (0.682) and LDL-C (0.712). The AUC of ROC curve of the RLP combined with sdLDL-P (0.977) for the diagnosis of carotid plaque was higher than the RLP and sdLDL-P (all P<0.01). Conclusion:The serum RLP, LDL-P and sdLDL-P can be used as indicators of carotid plaque, and their clinical diagnostic value are superior to TG and LDL-C; the combined diagnostic effect of lipoprotein subclass is better than that of single index alone.