Neuroinflammation and Alzheimer’s Disease: A Machine Learning Approach to CSF Proteomics

Abstract

In Alzheimer’s disease (AD), the contribution of pathophysiological mechanisms other than amyloidosis and tauopathy is now widely recognized, although not clearly quantifiable by means of fluid biomarkers. We aimed to identify quantifiable protein biomarkers reflecting neuroinflammation in AD using multiplex proximity extension assay (PEA) testing. Cerebrospinal fluid (CSF) samples from patients with mild cognitive impairment due to AD (AD-MCI) and from controls, i.e., patients with other neurological diseases (OND), were analyzed with the Olink Inflammation PEA biomarker panel. A machine-learning approach was then used to identify biomarkers discriminating AD-MCI (n: 34) from OND (n: 25). On univariate analysis, SIRT2, HGF, MMP-10, and CXCL5 showed high discriminatory performance (AUC 0.809, p = 5.2 × 10−4, AUC 0.802, p = 6.4 × 10−4, AUC 0.793, p = 3.2 × 10−3, AUC 0.761, p = 2.3 × 10−3, respectively), with higher CSF levels in AD-MCI patients as compared to controls. These same proteins were the best contributors to the penalized logistic regression model discriminating AD-MCI from controls (AUC of the model 0.906, p = 2.97 × 10−7). The biological processes regulated by these proteins include astrocyte and microglia activation, amyloid, and tau misfolding modulation, and blood-brain barrier dysfunction. Using a high-throughput multiplex CSF analysis coupled with a machine-learning statistical approach, we identified novel biomarkers reflecting neuroinflammation in AD. Studies confirming these results by means of different assays are needed to validate PEA as a multiplex technique for CSF analysis and biomarker discovery in the field of neurological diseases.

Association of the inflammation-related proteome with dementia development at older age: results from a large, prospective, population-based cohort study

“…Six of the identified 33 proteins for Alzheimer's disease in plasma samples corresponded with our findings in serum samples and can now be considered replicated by our study (Casp-8, CXCL5, CXCL6, ST1A1, TRAIL, uPA). Gaetani and colleagues measured biomarker levels of the Olink inflammation panel in CSF samples of 34 AD-MCI cases and 25 controls having other neurological diseases (OND) [33]. In univariate analyses, 11 of 46 analysed biomarkers were found to have the highest discriminatory ability between AD-MCI and OND.…”

SIRT2 inhibition rescues neurodegenerative pathology but increases systemic inflammation in a transgenic mouse model of Alzheimer’s disease

“…In our hands and in agreement with Silva et al, (2017) we observed increased expression of SIRT2 in brain cortex samples of AD patients. Interestingly, con rming these results, a recent study, with a machine-learning approach, has identi ed in the CSF quanti able protein biomarkers discriminating AD from other neurological diseases and demonstrated that SIRT2 shows a very high discriminatory performance with higher CSF levels in AD patients as compared to controls (Gaetani et al, 2021). These studies support the association of SIRT2 expression in the CNS with AD pathophysiology and the interest in continuing studying the therapeutic potential of its inhibition.…”

Bisdemethoxycurcumin (BDC)-Loaded H-Ferritin-Nanocages Mediate the Regulation of Inflammation in Alzheimer’s Disease Patients

“…The most deregulated coding genes were CDCA2, SLC1A2, and CXCL5 (downregulated) and UCHL1 and MARCO (upregulated). Interesting, CXCL5 and MARCO are both related to inflammation [ 44 , 45 ], while UCHL1 is a gene specific for Parkinson’s disease but also described in AD [ 46 ].…”