Integration of bulk/scRNA-seq and multiple machine learning algorithms identifies PIM1 as a biomarker associated with cuproptosis and ferroptosis in abdominal aortic aneurysm

Abstract

Background: Abdominal aortic aneurysm (AAA) is a serious life-threatening vascular disease, and its ferroptosis/cuproptosis markers have not yet been characterized. This study was aiming to identify markers associated with ferroptosis/cuproptosis in AAA by bioinformatics analysis combined with machine learning models and to perform experimental validation.

Methods: This study used three scRNA-seq datasets from different mouse models and a human PBMC bulk RNA-seq dataset. Candidate genes were identified by integrated analysis of scRNA-seq, cell communication analysis, monocle pseudo-time analysis, and hdWGCNA analysis. Four machine learning algorithms, LASSO, REF, RF and SVM, were used to construct a prediction model for the PBMC dataset, the above results were comprehensively analyzed, and the targets were confirmed by RT-qPCR.

Results: scRNA-seq analysis showed Mo/MF as the most sensitive cell type to AAA, and 34 cuproptosis associated ferroptosis genes were obtained. Pseudo-time series analysis, hdWGCNA and machine learning prediction model construction were performed on these genes. Subsequent comparison of the above results showed that only PIM1 appeared in all algorithms. RT-qPCR and western blot results were consistent with sequencing results, showing that PIM1 was significantly upregulated in AAA.

Conclusion: In a conclusion, PIM1 as a novel biomarker associated with cuproptosis/ferroptosis in AAA was highlighted.

Keywords: PIM1; WGCNA; abdominal aortic aneurysm; cuproptosis; ferroptosis.

Figure 1

The landscape of AAA in a single-cell resolution. (A) UMAP plots show the cell distribution and number of different cell types included in the analysis under the three AAA models. (B) Violin plots show the expression characteristics of marker genes in different cell types (C) Heatmap showing the top 5 genes in different cell types. (D) UMAP plots show the distribution of cell types in different samples. (E) The distribution ratio of different cell types in each sample. (F) The bar graphs show the distribution statistics of different cell types under AAA and Con. Statistics were performed using Student’s T test, ** represents p < 0.01. (G) The circular histogram shows the sensitivity of different cell types to AAA, calculated by Augur. AAA1 means CaCl₂-induced model, AAA2 means elastase-induced model and AAA3 means Ang II-induced model.

Figure 2

The cellular communication between SMC and Mo/MF is altered in AAA. (A) The bar graph shows the communication frequency (left) and strength (right) of all cell types in different groups. (B) The network diagram shows the frequency of cell communication for each cell type in different groups. (C) The stacked bar chart shows the differences in each signaling pathway under different groups. (D) The bubble chart shows the differential communication signals between Mo/MF and SMC in different groups. The left side shows the up-regulated signals in AAA, and the right side shows the down-regulated signals. e and f, Network diagram showing the differences in TNF-α (E) and TGF-β (F) signaling in different groups.

Figure 3

The transcriptional dynamics of Mo/MF were altered under different models. (A) The volcano plot shows the DEGs of Mo/MF under CaCl2-induced model, the DEGs screening threshold was |log2FC| > 0.25 and p < 0.05. (B) The GO enrichment analysis results of DEGs, p < 0.05 was considered significantly enriched. (C) The KEGG enrichment analysis results of DEGs, p < 0.05 was considered significantly enriched. D-F, DEGs (D) and related GO (E) and KEGG (F) enrichment analysis results under the elastase-induced model. (G–I), DEGs (G) and related GO (H) and KEGG (I) enrichment analysis results under the Ang II-induced model.

Figure 4

Comparative analysis of Mo/MF differences under different models. (A) The Venn diagram showing the comparative analysis of differentially expressed genes in Mo/MF under different models. (B, C) The GO (B) and KEGG (C) enrichment results of common DEGs in different models, p < 0.05 was considered significantly enriched. (D) The Venn diagram shows the comparative analysis of KEGG pathways in different models. (E) GSEA results showed the status of the Apoptosis signaling pathway under different models. (F) The Venn diagram shows the comparative analysis of GO terms in different models. (G) GSEA results showed the status of the cell death, cell killing and cell population proliferation signaling pathway under different models. AAA1 means CaCl₂-induced model, AAA2 means elastase-induced model and AAA3 means Ang II-induced model.

Figure 5

Identification of cuproptosis-associated ferroptosis genes in AAA. (A) The PPI network shows the interactions among cuprotosis genes. (B) The bar graph shows the Reactome Pathway of cuproptosis genes. (C) The volcano plot shows the correlation between candidate ferroptosis genes and cuproptosis genes. (D) The Venn diagram showing the relationship between candidate ferroptosis genes and DEGs. AAA1 means CaCl₂-induced model, AAA2 means elastase-induced model and AAA3 means Ang II-induced model.

Figure 6

Construction of pseudo-development trajectories of Mo/MF cells. (A, B) The pseudo-time trajectories of Mo/MF show different fate trajectories (A) and different cell states (B). (C) Distribution of different groups under pseudo-time trajectory. (D) The stacked bar graphs show the distribution patterns of different groups in different cell states. (E) Expression trends of candidate cuproptosis-associated ferroptosis genes under pseudo-temporal trajectories. (F) The heat map shows the gene expression trends before and after cell fate 2. (G) The KEGG enrichment analysis of gene sets with different patterns in the heatmap.

Figure 7

Construction of WGCNA in Mo/MF at the single-cell level. (A) Free-scale network topology analysis for different soft threshold powers. The black circle shows the optimal threshold chosen. (B) Hierarchical clustering numbers show the modules to which genes belong. (C) The genes in each module ranked by kME that iseigengene-based connectivity. (D) The heat map shows the expression characteristics of hub genes in different cell types. (E) Correlation analysis between different modules. (F) The dot plot shows the expression patterns of different modules under different groups. (G) Co-expression network of the top 25 genes in the yellow module. (H) Co-expression network of cuproptosis-associated ferroptosis genes in Mo/MF.

Figure 8

Analysis of transcriptional differences in PBMCs in AAA. (A) PCA analysis shows the top2 PCs under different groups. (B) The volcano plot shows the distribution of DEGs, and the DEGs screening threshold was |log2FC| > 0.5 and p < 0.05.  (C) The heat map showing the expression characteristics of DEGs. (D) KEGG enrichment results of DEGs. (E) The Venn diagram showing the comparative analysis of DEGs and cuproptosis-associated ferroptosis genes. AAA1-6 means different sample.

Figure 9

Analysis of transcriptional differences in PBMCs in AAA. (A) and (B) LASSO regression analysis was performed in PBMC data using candidate cuproptosis-associated ferroptosis genes. The minimum value was defined based on 10-fold cross validation, where the best λ yielded 4 cuproptosis-associated ferroptosis genes (A). Coefficient curves were plotted according to (log λ) sequence and lambda value (B). (C) The REF model generated five candidate cuproptosis-associated ferroptosis genes. (D) The top 10 cuproptosis-associated ferroptosis genes generated by RF model evaluation. (E, F) Under the SVM model, the line graph shows the accuracy (E) and error of different genes (F). (G) The Venn diagram shows the comparative analysis of candidate cuproptosis-associated ferroptosis genes obtained by screening with different bioinformatics algorithms and machine models. (H–J) The expression characteristics of PIM1 were examined by sequencing (H), RT-qPCR (I) and western blot (J). AAA1 means CaCl₂-induced model, AAA2 means elastase-induced model and AAA3 means Ang II-induced model.