Differential proteomic profiles between cognitive frail and robust older adults from the MELoR cohort

Abstract

The present study explored for the first time the blood-based proteomic signature that could potentially distinguish older adults with and without cognitive frailty (CF). The participants were recruited under the Malaysian Elders Longitudinal Research (MELoR) study. Cognition and physical frailty were determined using the Montreal Cognitive Assessment (MoCA) and Fried's criteria, respectively. The differential protein expression in the blood samples (38 CF vs 40 robust) were then determined using the Sequential Window Acquisition of All Theoretical Mass Spectra (SWATH) analysis. A total of 294 proteins were found to be differentially expressed in the CF group as opposed to the robust group. Considering proteins with fold change (FC) ≥ ± 2 and p-values < 0.05, 13 proteins were significantly upregulated and nine proteins significantly downregulated in the CF group when compared to the robust group. Subsequent correlation analysis identified nine dysregulated proteins, namely APOA1, APOA2, APOA4, APOC1, APOE, GPX3, RBP4, SERPINC1 and TTR, to exhibit significantly and moderately strong correlations with parameters of cognitive and/or frailty assessments. These proteins could potentially serve as useful proteomic signature of CF given their sensitivity > 78%, specificity > 75%, accuracy > 80% and area under the curve (AUC) > 0.8. The major biological pathways that could be potentially dysregulated by the nine proteins were associated with lipid metabolism and the retinoid system. The present findings warrant further validation in future studies that involve a larger cohort.

Keywords: Blood; Cognitive frailty; Lipid metabolism; Proteomic signature; Retinoid system.

Fig. 1

Flowchart of participant selection for the present study

Fig. 2

Volcano plot of the differentially expressed proteins in the CF group as opposed to the robust group. Proteins were deemed differentially expressed between the CF and robust groups when FC ≥  ± 2 and p < 0.05

Fig. 3

Correlations between differentially expressed proteins (FC ≥  ± 2, p < 0.05) and parameters of cognitive and frailty assessments (significantly different, p < 0.05). A Heatmap of correlation analysis. B List of proteins that exhibited moderately strong correlation (correlation coefficient ≥ 0.60, p < 0.05) with parameters of cognitive and/or frailty assessments. *The coefficient value ≥ 0.60. Abbreviations: PCV, packed cell volume; MoCA, Montreal Cognitive Assessment; TUG, timed-up and go

Fig. 4

Separation between the CF and robust participants based on the nine dysregulated proteins that exhibited moderately strong correlation with parameters of cognitive and/ or frailty assessments. A PCA plot of the participants. B Hierarchical clustering heatmap that depict the expression trend of the nine dysregulated proteins in each participant. See Fig. S1 for the expression trend of the nine dysregulated proteins in each participant based on diabetes and hypertension incidences.

Fig. 5

STRING network of protein–protein interactions (PPI) and potential biological pathways significantly regulated of the identified nine proteins. A PPI of upregulated proteins. B Downregulated proteins. C Combined upregulated and downregulated proteins. Remarks: The proteins highlighted in the coloured box are the nine dysregulated proteins that exhibited moderately strong correlation with frailty (boxes with blue outlines) or both cognition and frailty parameters (boxes with yellow outlines). D Significant pathways involving upregulated proteins. E Significant pathways involving downregulated proteins

Fig. 5

STRING network of protein–protein interactions (PPI) and potential biological pathways significantly regulated of the identified nine proteins. A PPI of upregulated proteins. B Downregulated proteins. C Combined upregulated and downregulated proteins. Remarks: The proteins highlighted in the coloured box are the nine dysregulated proteins that exhibited moderately strong correlation with frailty (boxes with blue outlines) or both cognition and frailty parameters (boxes with yellow outlines). D Significant pathways involving upregulated proteins. E Significant pathways involving downregulated proteins

Fig. 6

Proposed pathways that may involve the potential crosstalk between the nine dysregulated proteins during the pathogenesis of CF via the brain-skeletal muscle axis. Remark: Part of this image was created using BioRender (BioRender.com)