Transcriptomic evidence for modulation of host inflammatory responses during febrile Plasmodium falciparum malaria

Abstract

Identifying molecular predictors and mechanisms of malaria disease is important for understanding how Plasmodium falciparum malaria is controlled. Transcriptomic studies in humans have so far been limited to retrospective analysis of blood samples from clinical cases. In this prospective, proof-of-principle study, we compared whole-blood RNA-seq profiles at pre-and post-infection time points from Malian adults who were either asymptomatic (n = 5) or febrile (n = 3) during their first seasonal PCR-positive P. falciparum infection with those from malaria-naïve Dutch adults after a single controlled human malaria infection (n = 5). Our data show a graded activation of pathways downstream of pro-inflammatory cytokines, with the highest activation in malaria-naïve Dutch individuals and significantly reduced activation in malaria-experienced Malians. Newly febrile and asymptomatic infections in Malians were statistically indistinguishable except for genes activated by pro-inflammatory cytokines. The combined data provide a molecular basis for the development of a pyrogenic threshold as individuals acquire immunity to clinical malaria.

Figure 1. Study design and classes.

RNA-seq was performed on whole blood collected prior to infection and at the first PCR-detectable P. falciparum (Pf) blood-stage infection in a natural malaria infection study of malaria-experienced individuals or during a controlled human malaria infection study of naïve individuals as described in the Methods.

Figure 2. Whole-blood transcriptomic analysis of paired uninfected and infected samples demonstrates greater gene expression changes in NF than EF individuals during febrile malaria.

Clinical classes were defined as in Fig. 1, and characteristics of subjects used in this analysis are in Table 1. (a) Principal component analysis of the paired RNA-seq samples (infected – uninfected baseline samples for each subject) using the top 50% most variably expressed genes across all paired samples after normalization of raw data (n = 13 subjects). (b) An unsupervised clustering heat map (Spearman correlation with Ward’s linkage) of the top 50% most variably expressed genes (8208 genes). Red intensity indicates increased expression with infection, and blue intensity indicates decreased expression with infection. Clinical classes are denoted as blue (NF), red (EF), and gray (EA). Female gender is denoted as black. Grayscale intensities represent relative rankings for age, temperature, and parasite density. Differential gene expression analysis for paired infection vs. uninfected baseline comparisons within each clinical class (c) and between each class (d) using contrasts described in the Methods. Venn diagrams show the number of differentially expressed genes (DEGs) using an absolute log₂ fold-change (logFC) of >0.585 (1.5-fold in linear space) and a false discovery rate (FDR) <0.05. For the smear density plots, the average expression in log counts per million (x axis) is plotted against logFC (y axis), DEGs with FDR <0.05 are visualized as red points, and the fold-change cut-off is represented as blue lines.

Figure 3. Molecular signatures of febrile malaria in naïve and malaria-experienced individuals differ in intensity and quality by pathways analysis.

Canonical pathways analysis using DEGs with FDR <0.05 (no fold-change cut-off) for the ΔNF (a) and ΔEF (b) classes.

Figure 4. Upstream regulator analysis reveals graded activation of interferon-mediated inflammation.

Upstream regulator analysis using the DEGs with FDR <0.05 (no fold-change cut-off) for the ΔNF (a) and ΔEF (b) classes. A positive z-score predicts activation of the indicated gene based on the expression patterns of downstream genes, whereas a negative z-score predicts inhibition. (c) Z-score data from (a,b) in heatmap format is shown with the addition of z-scores from the between group (ΔNF-ΔEF) analysis. Rows are sorted by descending Z-scores in the third column. (d) Z–scores in heatmap format for between-class comparisons of ΔNF and ΔEF with ΔEA using DEGS with FDR < 0.10 (no fold-change cut-off). Rows are sorted by descending Z-scores in the second column. Only the top 40 predicted regulators with an absolute z-score >2 and P value <0.01 are shown.

Figure 5. Modular transcriptional repertoire analysis shows differential induction of functional and cell subset modules in naïve and malaria-experienced individuals during febrile malaria.

Modular transcriptional repertoire analyses using DEGs with FDR <0.05 (no fold-change cut-off) for within class (a) and with FDR <0.10 (no fold-change cut-off) for between class (b) comparisons. Only modules with differences in at least one comparison are shown. Rows are clustered by Euclidean distance with Ward’s linkage.