biostudies-literatureYang SGuizhou Provincial People's Hospital National Science FoundationGuizhou Provincial People's Hospital Doctor FoundationGuizhou Provincial Science and Technology ProjectsNational Natural Science Foundation of ChinaGeneral Project of Chongqing Natural Science FoundationGuizhou Provincial People's Hospital Youth Funde18296https://www.ebi.ac.uk/biostudies/studies/S-EPMC11069052biostudies-literatureUnknown28(9)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 diagnJournal of cellular and molecular medicineMachine learning and deep learning to identifying subarachnoid haemorrhage macrophage-associated biomarkers by bulk and single-cell sequencing.PMC11069052GPPH-NSFC-2019-0982260533[2018]03CSTB2023NSCQ-MSX0749[2018]0682360482[2020]1Z066GPPH-NSFC-2019-18GPPH-NSFC-D-2019-17GZSYQN20220282360376Liu JHu YRan ZDeng MHao YTan YHan GMa JXiang XWang XYang SShi HLuo TfalseMachine 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 diagn2024-01-01T00:00:00Z2024 May2026-07-14T18:58:47.895Z2026-06-22T03:13:04.671ZS-EPMC110690523870295410.1111/jcmm.18296