Proteomic Approaches for the Discovery of Biofluid Biomarkers of Neurodegenerative Dementias

Abstract

Neurodegenerative dementias are highly complex disorders driven by vicious cycles of intersecting pathophysiologies. While most can be definitively diagnosed by the presence of disease-specific pathology in the brain at postmortem examination, clinical disease presentations often involve substantially overlapping cognitive, behavioral, and functional impairment profiles that hamper accurate diagnosis of the specific disease. As global demographics shift towards an aging population in developed countries, clinicians need more sensitive and specific diagnostic tools to appropriately diagnose, monitor, and treat neurodegenerative conditions. This review is intended as an overview of how modern proteomic techniques (liquid chromatography mass spectrometry (LC-MS/MS) and advanced capture-based technologies) may contribute to the discovery and establishment of better biofluid biomarkers for neurodegenerative disease, and the limitations of these techniques. The review highlights some of the more interesting technical innovations and common themes in the field but is not intended to be an exhaustive systematic review of studies to date. Finally, we discuss clear reporting principles that should be integrated into all studies going forward to ensure data is presented in sufficient detail to allow meaningful comparisons across studies.

Keywords: Alzheimer’s disease; LC-MS/MS; biomarkers; cerebrospinal fluid; neurodegeneration; plasma; proteomics; serum.

Figure 1

Different proteomic techniques are more suited to different concentration ranges of biofluid analytes. In this plot, cerebrospinal fluid (CSF) proteins are ranked according to their abundance, with the location of specific proteins placed according to their concentrations in enzyme-linked immunoassays (ELISAs), Multiple-Reaction-Monitoring (MRM), and in-house (unpublished) label-free experiments [23,24,25,26]. It is of note that there is a large amount of disagreement between experiments on the exact concentrations of these analytes, and so their place on this plot should be considered illustrative. Of particular note is VGF, an analyte that exists as multiple processed peptides, which is easily detected by single-shot LC-MS/MS but detected in the low pg/mL ranges by ELISA. Single-shot LC-MS/MS will generally quantify 300–500 abundant proteins in CSF (turquoise), and protein identifications can be increased by offline fractionation of samples (orange). While ELISA-based methods measure analytes across the widest concentration range, these techniques require a strong hypothesis for target selection and rely on the availability of an appropriate antibody pair for the analyte. At low analyte concentrations, super depletion can be combined with LC-MS/MS to reveal low-abundance proteins, but there are concerns over nonspecific depletion of some target analytes. Finally, ultrasensitive platforms can be used to measure proteins such as cytokines in CSF, which are present in the low pg/mL to fg/mL range.

Figure 2

String [84] diagram shows functional protein relationships of proteins highlighted as potential CSF biomarkers of Alzheimer’s disease. These proteins currently fall into two main groups: neuropeptides and proteins that interact with amyloid precursor protein (APP, the precursor to beta-amyloid). The type of interaction can be determined from the key in the bottom right. Where peptides from the same protein differ in their significance, the reference is shown in more than one group.