Machine learning-based screening for biomarkers of psoriasis and immune cell infiltration.

BACKGROUND: Psoriasis is a chronic immune-mediated skin disease. However, the pathogenesis is not yet well established. OBJECTIVES: This study aimed to screen psoriasis biomarker genes and analyse their significance in immune cell infiltration. MATERIALS & METHODS: GSE13355 and GSE14905 datasets were downloaded from Gene Expression Omnibus (GEO) as training groups to establish the model. GSE30999 obtained from GEO was used to validate the model. Differential expression and multiple enrichment analyses were performed on 91 psoriasis samples and 171 control samples from the training group. The "LASSO" regression model and support vector machine model were used to screen and verify genes implicated in psoriasis. Genes with an area under the ROC curve >0.9 were selected as candidate biomarkers and verified in the validation group. Differential analysis of immune cell infiltration was performed on psoriasis and control samples using the "CIBERSORT" algorithm. Correlation analyses between the screened psoriasis biomarkers and 22 types of immune cell infiltration were performed. RESULTS: In total, 101 differentially expressed genes were identified, which were mainly shown to be involved in regulating cell proliferation and immune functions. Three psoriasis biomarkers, BTC, IGFL1, and SERPINB3, were identified using two machine learning algorithms. These genes showed high diagnostic value in training and validation groups. The proportion of immune cells during immune infiltration differed between psoriasis and control samples, which was associated with the three biomarkers. CONCLUSION: BTC, IGFL1, and SERPINB3 are associated with the infiltration of multiple immune cells, and may therefore be used as biomarkers for psoriasis.

Bioinformatic Analysis of the Potential Common Pathogenic Mechanisms for Psoriasis and Metabolic Syndrome.

The pathogeneses of psoriasis and metabolic syndrome are closely related; however, the underlying biological mechanisms are yet to be clarified. A psoriasis training set was downloaded from the Gene Expression Omnibus database and analyzed to identify the differentially expressed genes (|logFC|> 1 and adjust P < 0.05). Differentially expressed genes for metabolic syndrome were obtained from the GeneCards, Online Mendelian Inheritance in Man, and DisGeNET databases, and crosstalk genes were obtained for multiple enrichment analysis after identifying the disease intersection. Characteristic crosstalk genes were screened using the least absolute shrinkage and selection operator regression model and random forest tree model, and the genes with area under the receiver operating characteristic curve > 0.7 were selected for validation by the two validation sets. Differential analyses of immune cell infiltration were performed on psoriasis lesion and control samples using the CIBERSORT and ImmuCellAI methods, and correlation analyses were performed between the screened signature crosstalk genes and immune cell infiltration. Significant crosstalk genes were analyzed based on the psoriasis area and severity index and on the responses to biological agents. We found five signature genes (NLRX1, KYNU, ABCC1, BTC, and SERPINB4) were screened based on two machine learning algorithms, and NLRX1 was validated. The infiltration of multiple immune cells in psoriatic lesions and non-lesions was associated with NLRX1 expression. NLRX1 was found to be associated with psoriasis severity and response rate after the use of biologics. NLRX1 could be a significant crosstalk gene for psoriasis and metabolic syndrome.