Machine learning algorithms integrate bulk and single-cell RNA data to reveal the crosstalk and heterogeneity of Glycolysis and Lactylation activity following Pulmonary Arterial Hypertension

Background: Glycolysis and lactylation activity significantly impact the pathogenesis of Pulmonary Arterial Hypertension (PAH); however, studies exploring their heterogeneity and potential correlation at the single-cell level are still lacking. Identifying the feature genes that are commonly regulated by both glycolysis and lactylation could significantly enhance our understanding of PAH. Methods: We employed single-cell RNA sequencing (scRNA-seq) to investigate the heterogeneity of glycolysis and lactylation activity across various cellular tiers following PAH, aiming to acquire comprehensive biological insights into PAH. We Utilized AUCell, Ucell, singscore, ssGSEA, and AddModuleScore algorithms to identify common positive and negative regulated glycolysis and lactylation activity in PAH cellular level. Furthermore, we employed three machine learning algorithms, Boruta, Random Forest, and SVM-RFE to identify the optimal feature genes related to PAH in BulkRNA-seq level. We further leveraged CellChat and pseudotime analysis to delve into the potential biological regulatory mechanisms of the characteristic genes. We used qPCR to detect the expression of ACTR2, CCDC88A, and MRC1 in the rat model of pulmonary hypertension. Results: For the first time at the cellular level, we discovered that glycolysis and lactylation activities exhibit heterogeneity across different cell layers following PAH. However, their activities show remarkable consistency, being highly active in macrophages, fibroblasts, monocytes, and epithelial cells, while displaying lower activity in lymphatic endothelial cells. This indicates a correlation between these two pathways in PAH. Consequently, we defined a set of genes that co-regulate both pathways at the PAH level. Using various machine learning algorithms, we further identified key predictive genes for PAH, namely ACTR2, CCDC88A, and MRC1. We used qPCR to verify the excessive expression of ACTR2, CCDC88A, and MRC1 in the rat model of pulmonary hypertension. Conclusions: Following PAH, ACTR2, CCDC88A, and MRC1 might simultaneously upregulating glycolysis and lactylation activities in macrophages and monocytes and further contribute PAH progression. Clinical trial Not applicable.