Parkinson’s Disease Gene Biomarkers Screened by the LASSO and SVM Algorithms

Abstract

Parkinson’s disease (PD) is a common progressive neurodegenerative disorder. Various evidence has revealed the possible penetration of peripheral immune cells in the substantia nigra, which may be essential for PD. Our study uses machine learning (ML) to screen for potential PD genetic biomarkers. Gene expression profiles were screened from the Gene Expression Omnibus (GEO). Differential expression genes (DEGs) were selected for the enrichment analysis. A protein–protein interaction (PPI) network was built with the STRING database (Search Tool for the Retrieval of Interacting Genes), and two ML approaches, namely least absolute shrinkage and selection operator (LASSO) and support vector machine recursive feature elimination (SVM-RFE), were employed to identify candidate genes. The external validation dataset further tested the expression degree and diagnostic value of candidate biomarkers. To assess the validity of the diagnosis, we determined the receiver operating characteristic (ROC) curve. A convolution tool was employed to evaluate the composition of immune cells by CIBERSORT, and we performed correlation analyses on the basis of the training dataset. Twenty-seven DEGs were screened in the PD and control samples. Our results from the enrichment analysis showed a close association with inflammatory and immune-associated diseases. Both the LASSO and SVM algorithms screened eight and six characteristic genes. AGTR1, GBE1, TPBG, and HSPA6 are overlapping hub genes strongly related to PD. Our results of the area under the ROC (AUC), including AGTR1 (AUC = 0.933), GBE1 (AUC = 0.967), TPBG (AUC = 0.767), and HSPA6 (AUC = 0.633), suggested that these genes have good diagnostic value, and these genes were significantly associated with the degree of immune cell infiltration. AGTR1, GBE1, TPBG, and HSPA6 were identified as potential biomarkers in the diagnosis of PD and provide a novel viewpoint for further study on PD immune mechanism and therapy.

Diagnostic implications of ubiquitination-related gene signatures in Alzheimer's disease

“…Finally, the results of differential expression analysis were output and visualized via R packages pheatmap and ggplot2. The screening conditions were |log2 (fold change, FC)| > 0.585 and adjusted P-value < 0.05 15 .…”

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

“…In recent years, machine learning algorithms have been increasingly used in the medical field to construct optimal classification models to filter out characterized variables ( 11 ). During our research, two machine algorithms, “least absolute shrinkage and selection operator” (LASSO) and “support vector machine - recursive feature elimination” (SVM-RFE), were utilized for diagnostic gene screening of differential genes ( 12 , 13 ), and at the same time, CIBERSORT, as a widely used machine algorithm for classifying populations of immune cells ( 14 ), was applied to identify three types skin lesion (normal skin, psoriasis non-lesional skin and psoriasis lesional skin) and potential diagnosis genes of PsO associated with immune infiltration, and were verified by real-time quantitative polymerase chain reaction (RT-qPCR) experiments.…”