Evidence for additive and interaction effects of host genotype and infection in malaria

Abstract

The host mechanisms responsible for protection against malaria remain poorly understood, with only a few protective genetic effects mapped in humans. Here, we characterize a host-specific genome-wide signature in whole-blood transcriptomes of Plasmodium falciparum-infected West African children and report a demonstration of genotype-by-infection interactions in vivo. Several associations involve transcripts sensitive to infection and implicate complement system, antigen processing and presentation, and T-cell activation (i.e., SLC39A8, C3AR1, FCGR3B, RAD21, RETN, LRRC25, SLC3A2, and TAPBP), including one association that validated a genome-wide association candidate gene (SCO1), implicating binding variation within a noncoding regulatory element. Gene expression profiles in mice infected with Plasmodium chabaudi revealed and validated similar responses and highlighted specific pathways and genes that are likely important responders in both hosts. These results suggest that host variation and its interplay with infection affect children's ability to cope with infection and suggest a polygenic model mounted at the transcriptional level for susceptibility.

Fig. 1.

Malaria infection impacts gene expression genome-wide. Correlation structure in whole-transcriptome data for the combined dataset of 155 cases and controls (A and B) and for the 94 cases alone (C and D). (A and C) Hierarchical clustering of whole-genome gene expression correlation matrix. The colored bars from left to right indicate the following phenotypes in the proportions displayed in the pie charts: hemoglobin genotype (AA, AC, or AS), location (Cotonou and Zinvié), and malaria infections status (control and high and low parasitemia groups). Parasite load or log2 parasitemia (low to high) is shown only in C. (B and D) PC analysis of the correlation matrix. The two major expression PCs (ePC1 and ePC2) are shown and individuals are labeled to indicate their infection status (controls, blue; high parasitemia, red; low parasitemia, orange).

Fig. 2.

Differential expression in whole-blood transcriptome. (A) Volcano plots of statistical significance vs. magnitude of differential expression for the two-way contrasts between the controls (marked as “C”) and high parasitemia (HP) and low parasitemia (LP) groups. For each transcript, significance is shown as the –log10 P value on the y axis, and the log2 of magnitude of mean expression difference is on the x-axis. The red horizontal line indicates the 1% FDR threshold. (B) Venn diagram shows numbers of differentially expressed transcripts for each comparison and the overlaps between them. For each contrast, GSEA was performed for KEGG pathways (C) and the C2, C3, and C5 collections of the Molecular Signatures Database (D) as previously described (9, 16). Only pathways and modules significantly enriched (Bonferroni-adjusted P < 0.05) from at least one contrast are shown. Colors in the heat map indicate the enrichment score from the GSEA analysis.

Fig. 3.

Genome-wide eSNP map in malaria-infected children. Circos plot displaying all genome-wide significant associations detected in the combined dataset of cases and controls and in the cases alone. Each chromosome is shown in a different color. Distal associations are displayed in the center of the plot, with the links indicating target transcripts. Circularized Manhattan plot displays local associations and their respective significance (−log10 P value). Associations significant for the genotype-by-infection effect are shown in red, and those implicating genes differentially expressed at 1% FDR in at least one of the two-way contrasts among control and high and low parasitemia groups (Table 1) are shown in green.

Fig. 4.

Transcriptional additive and multiplicative effects in malaria. Examples of transcriptional interaction effects implicating the genes SLC39A8, C3AR1, and PADI3. The case of GSTO1 illustrates the scenario of an interaction effect for a disease phenotype in the absence of a transcriptional interaction. This example illustrates how the effect of the gene is conditional on genotype with only the minor allele homozygote individuals shifting to the resistance zone (transcript abundance >12.0 indicated by horizontal line) when infected, giving rise to an interaction effect for the disease phenotype. Genotypes on the x-axis are labeled to indicate the number of minor alleles and individuals are labeled to indicate their infection status (controls, blue; high parasitemia, red; low parasitemia, orange). The y axis shows normalized expression values.