Identification of ADAM23 as a Potential Signature for Psoriasis Using Integrative Machine-Learning and Experimental Verification

Abstract

Pingping Yao,1 Yuying Jia,1 Xuewei Kan,1 Jiaqi Chen,1 Jinliang Xu,1 Huichao Xu,1 Shuyang Shao,1 Bing Ni,2 Jun Tang1 1Department of Dermatology, the First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230000, People’s Republic of China; 2Department of Pathophysiology, Third Military Medical University, Chongqing, 400038, People’s Republic of ChinaCorrespondence: Bing Ni; Jun Tang, Email [email protected]; [email protected]: Psoriasis is a common chronic, recurrent, and inflammatory skin disease. Identifying novel and potential biomarkers is valuable in the treatment and diagnosis of psoriasis. The goal of this study was to identify novel key biomarkers of psoriasis and analyze the potential underlying mechanisms.Methods: Psoriasis-related datasets were downloaded from the Gene Expression Omnibus database to screen differential genes in the datasets. Functional and pathway enrichment analyses were performed on the differentially expressed genes (DEGs). Candidate biomarkers for psoriasis were identified from the GSE30999 and GSE6710 datasets using four machine learning algorithms, namely, random forest (RF), least absolute shrinkage and selection operator (LASSO) logistic regression, weighted gene co-expression network analysis (WGCNA), and support vector machine recursive feature elimination (SVM-RFE), and were validated using the GSE41662 dataset. Next, we used CIBERSORT and single-cell RNA analysis to explore the relationship between ADAM23 and immune cells. Finally, we validated the expression of the identified biomarkers expressions in human and mouse experiments.Results: A total of 709 overlapping DEGs were identified, including 426 upregulated and 283 downregulated genes. Enhanced by enrichment analysis, the differentially expressed genes (DEGs) were spatially arranged in relation to immune cell involvement, immune-activating processes, and inflammatory signals. Based on the enrichment analysis, the DEGs were mapped to immune cell involvement, immune-activating processes, and inflammatory signals. Four machine learning strategies and single-cell RNA sequencing analysis showed that ADAM23, a disintegrin and metalloprotease, may be a unique, critical biomarker with high diagnostic accuracy for psoriasis. Based on CIBERSORT analysis, ADAM23 was found to be associated with a variety of immune cells, such as macrophages and mast cells, and it was upregulated in the macrophages of psoriatic lesions in patients and mice.Conclusion: ADAM23 may be a potential biomarker in the diagnosis of psoriasis and may contribute to the pathogenesis by regulating immunological activity in psoriatic lesions.Keywords: psoriasis, machine learning, differential gene analysis, CIBERSORT, ADAM23

Keywords

• psoriasis
• machine learning
• differential gene analysis
• cibersort
• adam23