Machine learning and deep learning to identifying subarachnoid haemorrhage macrophage-associated biomarkers by bulk and single-cell sequencing.

We investigated subarachnoid haemorrhage (SAH) macrophage subpopulations and identified relevant key genes for improving diagnostic and therapeutic strategies. SAH rat models were established, and brain tissue samples underwent single-cell transcriptome sequencing and bulk RNA-seq. Using single-cell data, distinct macrophage subpopulations, including a unique SAH subset, were identified. The hdWGCNA method revealed 160 key macrophage-related genes. Univariate analysis and lasso regression selected 10 genes for constructing a diagnostic model. Machine learning algorithms facilitated model development. Cellular infiltration was assessed using the MCPcounter algorithm, and a heatmap integrated cell abundance and gene expression. A 3 × 3 convolutional neural network created an additional diagnostic model, while molecular docking identified potential drugs. The diagnostic model based on the 10 selected genes achieved excellent performance, with an AUC of 1 in both training and validation datasets. The heatmap, combining cell abundance and gene expression, provided insights into SAH cellular composition. The convolutional neural network model exhibited a sensitivity and specificity of 1 in both datasets. Additionally, CD14, GPNMB, SPP1 and PRDX5 were specifically expressed in SAH-associated macrophages, highlighting its potential as a therapeutic target. Network pharmacology analysis identified some targeting drugs for SAH treatment. Our study characterised SAH macrophage subpopulations and identified key associated genes. We developed a robust diagnostic model and recognised CD14, GPNMB, SPP1 and PRDX5 as potential therapeutic targets. Further experiments and clinical investigations are needed to validate these findings and explore the clinical implications of targets in SAH treatment.

Knockdown of BCL-3 Attenuates Inflammatory Response in Intracerebral Hemorrhage Through an rBMECs/MGs Microenvironment.

Intracerebral hemorrhage (ICH) is a severe disease with high mortality. Recently, the role of BCL-3 in ICH has started to gain attention, but its mechanism remains unclear. A collagenase injection method was used to establish an ICH model in rats, and the expression of BCL-3 were detected. Rat brain microvascular endothelial cells (rBMECs) were isolated and induced with Hemin to establish an in vitro ICH model. The expression of BCL-3 was assessed, followed by detection of cell apoptosis. In the cell model, the recruitment, polarization, and pro-inflammatory features of the microglia (MGs) were assessed after co-cultured with rBMECs. Finally, in the ICH animal model, after knockdown of BCL-3, comprehensive evaluations of inflammatory responses in brain tissue, polarization and recruitment of microglia, and apoptosis were conducted. Results revealed an upregulated expression of BCL-3 in brain tissue of the ICH animal model. In Hemin-treated rBMECs, an upward trend in BCL-3 expression was observed, accompanied by an increase of cell apoptosis. After co-culturing with the in vitro model, microglia exhibited enhanced M1 polarization and intensified inflammatory responses. However, when BCL-3 expression was inhibited in the in vitro model, a reversal occurred in the polarization tendency and inflammatory responses of microglia. Additionally, after knockdown of BCL-3 in the animal model, notable improvements occurred in M1 polarization, infiltration of macrophages, and inflammatory reactions in the brain tissue. Therefore, BCL-3 modulates the inflammatory response after ICH occurrence through the BMECs/MGs microenvironment. Additionally, BCL-3 might be a potential therapeutic target for ICH management.

BCL-3 Promotes Intracerebral Hemorrhage Progression by Increasing Blood-Brain Barrier Permeability, Inflammation, and Cell Apoptosis via Endoplasmic Reticulum Stress.

Background: Intracerebral hemorrhage (ICH) is among the common types of stroke with high mortality and morbidity. Molecular biomarker selection is crucial for ICH diagnosis and treatment. However, the identification of ICH-related biomarkers remains inadequate. Materials and Methods: In vivo and in vitro ICH models were generated and transfected with silenced B-cell lymphoma-3 (BCL-3 and siRNA BCL-3), overexpressed BCL-3, and endoplasmic reticulum stress (ERS) agonist (2-CLHA). Hematoxylin-eosin staining and transmission electron microscopy were used to observe the transfected cells. RNA sequencing was performed in vivo on the sham and ICH groups. The blood-brain barrier (BBB) permeability was evaluated by determining Evans blue dye extravasation, transendothelial electrical resistance, and paracellular permeability. Moreover, tight junction-, cell apoptosis-, and endoplasmic reticulum stress- (ERS-) related proteins were evaluated through real-time quantitative PCR, western blotting, immunohistochemistry, and TUNEL staining. The levels of inflammatory cytokines were measured through the enzyme-linked immunosorbent assay. Results: RNA-seq revealed that BCL-3 acts as a key player. BCL-3 promotes ICH progression by increasing BBB permeability, ERS, inflammation, and cell apoptosis. Silencing of BCL-3 slows ICH progression by reducing BBB permeability and inflammation and terminating cell apoptosis and ERS in vitro and in vivo. Conclusion: Our study identified ICH biomarkers and elucidated the role of BCL-3 in ICH for the first time.