Standardized Whole Blood Assay and Bead-Based Cytokine Profiling Reveal Commonalities and Diversity of the Response to Bacteria and TLR Ligands in Cattle

Abstract

Recent developments in multiplex technologies enable the determination of a large nu\mber of soluble proteins such as cytokines in various biological samples. More than a one-by-one determination of the concentration of immune mediators, they permit the establishment of secretion profiles for a more accurate description of conditions related to infectious diseases or vaccination. Cytokine profiling has recently been made available for bovine species with the development of a Luminex^® technology-based 15-plex assay. Independently from the manufacturer, we evaluated the bovine cytokine/chemokine multiplex assay for limits of detection, recovery rate, and reproducibility. Furthermore, we assessed cytokine secretion in blood samples from 107 cows upon stimulation with heat-killed bacteria and TLR2/4 ligands compared to a null condition. Secretion patterns were analyzed either using the absolute concentration of cytokines or using their relative concentration with respect to the overall secretion level induced by each stimulus. Using Partial Least Square-Discriminant Analysis, we show that the 15-cytokine profile is different under Escherichia coli, Staphylococcus aureus, and Streptococcus uberis conditions, and that IFN-γ, IL-1β, and TNF-α contribute the most to differentiate these conditions. LPS and E. coli induced largely overlapping biological responses, but S. aureus and S. uberis were associated with distinct cytokine profiles than their respective TLR ligands. Finally, results based on adjusted or absolute cytokine levels yielded similar discriminative power, but led to different stimuli-related signatures.

Keywords: MAMPs; bacteria; bead-based assay; cattle; cytokine; inflammation; whole blood stimulation.

Figure 1

Average dose–response curves for each cytokine (red curves). The x and y-axis represent analyte concentration and the Log10 MFI value, respectively. Each dot corresponds to the average response of a given standard, and the error bars show the variances calculated on values from 6 plates for each cytokine.

Figure 2

Recovery rates for each cytokine. The x and y-axis represent the analytes and the recovery rate, respectively. Each dot represents the recovery rate of a given plate. The solid red line indicates a 100% recovery rate. A recovery rate is considered correct when the value is between 75 and 125% (dashed red lines). For display purposes, all the samples having a recovery rate of less than 50% were set to 50%. Each color corresponds to one of the six plates containing control samples.

Figure 3

Coefficient of variation of MFI estimates as a function of cytokine concentrations. The x and y-axis represent analyte concentrations in Log10 and the coefficient of variation in percentage, respectively. The values of 6 separate plates are represented in different colors: horizontal black dashed lines indicate the 25% threshold that was used to define the reliable lower and upper quantification limits represented by the vertical blue dashed lines.

Figure 4

Radarplots of cytokine concentration values obtained for each stimulus. (A) represents the log10-transformed fold-changes induced by a stimulus over the null condition. (B) represents the adjusted concentration values. CTL, FSL-1, GDQ, HKEC, HKSA, HKSU, and LPS stand for control, fibroblast-stimulating lipopeptide 1, gardiquimod, heat-killed Escherichia coli, heat-killed Staphylococcus aureus, heat-killed Streptococcus uberis, and lipopolysaccharide stimuli, respectively.

Figure 5

Multilevel PLS-DA on bacterial stimuli adjusted MFI values reveals specific expression patterns depending on the bacteria species. On the plot of the individuals (A), each dot represents an individual cow, and the corresponding stimulus is defined by its color. The x and y-axis correspond to the first and second PLS-DA components, respectively. The proportion of variance explained by each principal component is written in brackets. The contribution of the cytokines to the first (B) and second (C) principal components is represented by a horizontal barplot. The two first principal components are sufficient to achieve an almost perfect misclassification rate (D).

Figure 6

Multilevel PLS-DA on TLR ligands adjusted MFI values identifies commonalities between TLR2/6 and TLR4 engagements. On the plots of the individuals (A, B), each dot represents an individual cow and the corresponding stimulus is defined by the different colors and shapes. The x and y-axis correspond to the PLS-DA components. The proportion of variance explained by each principal component is written in brackets. The contribution of the cytokines to the first (D), second (E) and third (F) principal components are represented by a horizontal barplot. The three first principal components are sufficient to reach a misclassification rate below 10% (C).

Figure 7

Multilevel PLS-DA on all bacteria and TLR ligands except GDQ. (A–C) output of the same PLS-DA but displaying only one bacterial stimulus and the TLR ligands known to activate the same TLR. The x and y-axes correspond to the first and second PLS-DA components, respectively. The proportion of variance explained by each principal component is given in brackets. (D, E) the variable contributions to the first and second components, respectively.