Utilizing Machine Learning to Identify Biomarkers of Endoplasmic Reticulum Stress and Analyze Immune Cell Infiltration in Parkinson's Disease.

The neurodegenerative disorder known as Parkinson's disease (PD) affects many people. The objective of this investigation was to examine the relationship between immune system infiltration, ATP-binding cassette transporter subfamily A member 7 (ABCA7) and TBL2 as well as potential therapeutic targets for the identification of PD associated to endoplasmic reticulum (ER) stress. First, we obtained PD data through GEO and divided it into two sets: a training set (GSE8397) plus a set for validation (GSE7621). Functional enrichment analysis was performed on a set of DEGs that overlapped with genes involved in endoplasmic reticulum stress. To identify genes of PD linked with endoplasmic reticulum stress, we employed random forest (RF) along with the least absolute shrinkage and selection operator (LASSO) logistic regression. Spearman's rank correlation analysis was then used to find associations among diagnostic markers with immune cell penetration. A grand total of 2 stress-related endoplasmic reticulum signature transcripts were identified. ABCA7 and TBL2 were shown to have diagnostic potential for PD and immune infiltrating cells have a role in the etiology of the disease. Additionally, resting CD4 memory, plasma cells, and NK cells overall exhibited positive associations with ABCA7, whereas triggered macrophages, T cells with active CD4 memory, activating NK cells, T cells with activated CD4 naive, engaged NK cells, and neutrophils all had adverse interactions with ABCA7. Overall, ABCA7 together with TBL2 have diagnostic utility for PD, and several types of immune cells, especially macrophages, may be involved in the development and progression of the disease.