Discovery of biomarkers in the psoriasis through machine learning and dynamic immune infiltration in three types of skin lesions

Abstract

Introduction: Psoriasis is a chronic skin disease characterized by unique scaling plaques. However, during the acute phase, psoriatic lesions exhibit eczematous changes, making them difficult to distinguish from atopic dermatitis, which poses challenges for the selection of biological agents. This study aimed to identify potential diagnostic genes in psoriatic lesions and investigate their clinical significance.

Methods: GSE182740 datasets from the GEO database were analyzed for differential analysis; machine learning algorithms (SVM-RFE and LASSO regression models) are used to screen for diagnostic markers; CIBERSORTx is used to determine the dynamic changes of 22 different immune cell components in normal skin lesions, psoriatic non-lesional skin, and psoriatic lesional skin, as well as the expression of the diagnostic genes in 10 major immune cells, and real-time quantitative polymerase chain reaction (RT-qPCR) and immunohistochemistry are used to validate results.

Results: We obtained 580 differentially expressed genes (DEGs) in the skin lesion and non-lesion of psoriasis patients, 813 DEGs in mixed patients between non-lesions and lesions, and 96 DEGs in the skin lesion and non-lesion of atopic dermatitis, respectively. Then 144 specific DEGs in psoriasis via a Veen diagram were identified. Ultimately, UGGT1, CCNE1, MMP9 and ARHGEF28 are identified for potential diagnostic genes from these 144 specific DEGs. The value of the selected diagnostic genes was verified by receiver operating characteristic (ROC) curves with expanded samples. The the area under the ROC curve (AUC) exceeded 0.7 for the four diagnosis genes. RT-qPCR results showed that compared to normal human epidermis, the expression of UGGT1, CCNE1, and MMP9 was significantly increased in patients with psoriasis, while ARHGEF28 expression was significantly decreased. Notably, the results of CIBERSORTx showed that CCNE1 was highly expressed in CD4+ T cells and neutrophils, ARHGEF28 was also expressed in mast cells. Additionally, CCNE1 was strongly correlated with IL-17/CXCL8/9/10 and CCL20. Immunohistochemical results showed increased nuclear expression of CCNE1 in psoriatic epidermal cells relative to normal.

Conclusion: Based on the performance of the four genes in ROC curves and their expression in immune cells from patients with psoriasis, we suggest that CCNE1 possess higher diagnostic value.

Keywords: atopic dermatitis; diagnosis genes; immune infiltration; machine learning algorithm; psoriasis.

Figure 1

Differential gene expressions (Degs) network of psoriasis (Pso), atopic dermatitis (AD), and their Mixed in a Venn diagram.

Figure 2

Functional enrichment analyses of the unique DEGs between PsO-NL and PsO-LS.

Figure 3

Identification of the gene biomarker for psoriasis diagnosis. (A, B) The LASSO logistic regression technique was utilized, the abscissa indicates the number of modeling genes corresponding to different (λ) values and eights genes with minimum lambda (λ) value were identified with 3-fold cross-validation. (C) A plot of gene biomarker selection by SVM-RFE. The blue dot indicates the best 15 genes. (D) The Venn data of the LASSO and SVM-RFE.

Figure 4

The expression level of UGGT1, MMP9, CCNE1, ARHGEF28 in training (A) and validation (B) cohorts. Ps-NL, psoriasis non-lesion; Ps-LS, psoriasis lesion. *P < 0.05, **P < 0.01, ****P < 0.0001.

Figure 5

(A) Expression of four diagnostic genes in epidermis of PsO and normal human as revealed by RT-qPCR. (B) The determination of its diagnostic effectiveness between normal and psoriatic samples via ROC curves for UGGT1/MMP9/CCNE1/ARHGEF28. ROC, receiver operating characteristic. *P < 0.05, ****P < 0.0001.

Figure 6

(A) A bar plot comparing the percentage of 22 different types of immune cells found infiltrating in three types lesions (B) three types lesions were compared using an histogram plot, which displayed the ratio differentiation of 22 distinct types of immune cells. Ps-NL, psoriasis non-lesion; Ps-LS, psoriasis lesion. * P < 0.05, **P < 0.01, ***P < 0.001.

Figure 7

(A) Validation of CCNE1 in CD4+ T cells from controls and psoriasis patients (B) Correlation between CCNE1 and IL-17A, CXCL8/9/10 and CCL20. * P < 0.05.

Figure 8

Immunohistochemical detection of CCNE1 expression in normal skin lesions (A 20X, C 40X) and psoriatic lesions (B 20X, D 40X).

Figure 9

Multicolor immunofluorescence technology to detect the expression of CCNE1 in the CD4 + cells and neutrophils in normal human skin lesions (A), 10X eyepiece, 10X objective) and PsO lesions (B), 10X ocular lenses, 10X objective). Blue represents DAPI, green represents CCNE1, white represents CD11b positive, and red represents CD4+ positive.