Integrative analysis associates monocytes with insufficient erythropoiesis during acute Plasmodium cynomolgi malaria in rhesus macaques

Abstract

Background: Mild to severe anaemia is a common complication of malaria that is caused in part by insufficient erythropoiesis in the bone marrow. This study used systems biology to evaluate the transcriptional and alterations in cell populations in the bone marrow during Plasmodium cynomolgi infection of rhesus macaques (a model of Plasmodium vivax malaria) that may affect erythropoiesis.

Results: An appropriate erythropoietic response did not occur to compensate for anaemia during acute cynomolgi malaria despite an increase in erythropoietin levels. During this period, there were significant perturbations in the bone marrow transcriptome. In contrast, relapses did not induce anaemia and minimal changes in the bone marrow transcriptome were detected. The differentially expressed genes during acute infection were primarily related to ongoing inflammatory responses with significant contributions from Type I and Type II Interferon transcriptional signatures. These were associated with increased frequency of intermediate and non-classical monocytes. Recruitment and/or expansion of these populations was correlated with a decrease in the erythroid progenitor population during acute infection, suggesting that monocyte-associated inflammation may have contributed to anaemia. The decrease in erythroid progenitors was associated with downregulation of genes regulated by GATA1 and GATA2, two master regulators of erythropoiesis, providing a potential molecular basis for these findings.

Conclusions: These data suggest the possibility that malarial anaemia may be driven by monocyte-associated disruption of GATA1/GATA2 function in erythroid progenitors resulting in insufficient erythropoiesis during acute infection.

Keywords: Bone marrow; Erythropoiesis; GATA1; Immune response; Nonhuman primates; Plasmodium cynomolgi; Plasmodium vivax; Relapse; Systems biology; Transcriptomics.

Fig. 1

The bone marrow does not compensate for anemia during acute cynomolgi malaria despite increased EPO levels. a Parasitaemia kinetics for the four animals are shown. Bone marrow sample collection times in relation to parasite kinetics are indicated by a vertical bar; the colour of the bar indicates the infection point classification of the sample. b Hemoglobin levels, peripheral reticulocyte numbers, and the reticulocyte production index for each infection stage are shown. Statistical significance relative to pre-infection was assessed where relevant using a linear mixed-model with Tukey–Kramer post hoc analysis. c Mean erythropoietin levels during each infection stage are indicated. Dashed line indicates the limit of detection of the assay. Statistical significance was assessed using a paired t test relative to pre-infection levels. Error bars indicate standard error for b and c. Asterisk indicates p < 0.05

Fig. 2

Acute malaria but not malaria relapse causes substantial changes in the bone marrow transcriptome. a Clustered heatmap of the BM transcriptome, with infection points of samples indicated. Four samples from acute primary infection form a cluster separated from other infection points. Another cluster captures more mild infection responses, including four out of six relapse time points. Colours indicate z-score normalized expression values. b Volcano plots of differentially expressed host genes in the BM at acute primary infection, post-peak, and relapse compared to pre-infection. The y axis is the negative logarithm base 10 of the p value. The x axis is the log2 difference in expression values between pre-infection and the infection point of a given plot. The red dotted horizontal line represents FDR = 0.05. Thus, the right arm of dots above the threshold line corresponds to genes significantly upregulated compared to pre-infection; the left arm of dots above the threshold line corresponds to downregulated genes. Red and blue dots for all three plots represent genes upregulated or downregulated (respectively) at acute primary infection, visualizing the fact that few genes differentially expressed at primary infection are differentially expressed during post-peak and relapse, with many genes not even trending in the same direction between the two infection points. c Venn diagram showing the overlap of differentially expressed genes at acute primary infection, post-peak and relapses

Fig. 3

Type I and Type II interferon transcriptional signatures are enriched in the bone marrow during acute malaria. a Pathways enriched with upregulated genes using GSEA. Pathways associated with interferons are highlighted in red. Bars indicate the negative logarithm base 10 of the p value of the enrichment for a given gene set. b Pathways enriched with upregulated genes using MetaCore. Pathways associated with interferons are highlighted in red. c Pathways enriched with downregulated genes using GSEA. d Pathways enriched with downregulated genes using MetaCore. e Clustered heatmap of transcriptional profiles of Type I IFN signature genes. Colours indicate z-score normalized expression values. f Clustered heatmap of transcriptional profiles of Type II IFN signature genes. g ifnγ BM expression levels. h IFNα serum concentrations. i IFNγ serum concentrations

Fig. 4

Intermediate and non-classical monocytes in the bone marrow are correlated with gene modules that may negatively impact the erythroid lineage. a Correlation of gene modules with cell population measurements and clinical traits based on WGNCA analysis of the BM transcriptome. Rows contain different transcriptional modules identified by WGCNA, with the colour in a given column indicating the degree of correlation of that module with cell population or clinical trait measurements. The top number in each entry is the Spearman correlation coefficient for any correlation with p < 0.05, and the bottom number is the p value significance of the correlation coefficient. The last column indicates the number of genes in each module. b–e Significantly enriched pathways in the turquoise, blue, brown, and yellow modules based on analysis using MSigDB. Bars indicate the negative logarithm base 10 of the p value of the enrichment for a given gene set

Fig. 5

Systemic cytokines are positively associated with transcriptional modules that are negatively associated with erythroid progenitors but positively correlated with intermediate and non-classical monocytes. The correlation of gene modules with cell population measurements and cytokine concentrations based on WGNCA analysis of the BM transcriptome is shown. Cytokine measurements were performed using a multiplex assay with plasma collected after isolation of bone marrow mononuclear cells collected for RNA-Seq analysis. Rows contain different transcriptional modules identified by WGCNA, with the colour in a given column indicating the degree of correlation of that module with cell population or cytokine measurements. The top number in each entry is the Spearman correlation coefficient for any correlation with p < 0.05, and the bottom number is the p value significance of the correlation coefficient. The last column indicates the number of genes in each module

Fig. 6

Disruption of GATA1 and GATA2 in erythroid progenitor cells may contribute to the decrease in erythroid progenitors and insufficient erythropoietic output during acute malaria. a Transcription factor analysis identified eight transcription factors (NES > 3) associated with the cluster of genes positively correlated with reticulocyte levels. The line plot indicates the NES score, while the bar plot indicates the number of genes in the set containing a binding site for each transcription factor. b Frequency of erythroid progenitors in the bone marrow during different infection periods as determined by flow cytometry. There is a small but statistically significant decrease at acute primary infection. c, d Transcriptional expression levels of GATA1 and GATA2 in BM. Expression of GATA1 was upregulated at post-peak, but not at acute primary infection, while GATA2 levels were not significantly changed. e Heatmap of gene expression levels of the GATA1 and GATA2 transcriptional regulatory network; samples are in chronological order, while genes are hierarchically clustered. Most pathway members were downregulated at acute primary infection and upregulated at the post-peak infection point. f Gene expression of GATA1/2 targets was downregulated at acute primary and upregulated at post-peak compared to pre-infection. Gene measurements were averaged across animals for each infection point, and paired t tests were used to assess statistical significance (Asterisk: significant at p < 0.01)