Development of a single nucleotide polymorphism barcode to genotype Plasmodium vivax infections

Abstract

Plasmodium vivax, one of the five species of Plasmodium parasites that cause human malaria, is responsible for 25-40% of malaria cases worldwide. Malaria global elimination efforts will benefit from accurate and effective genotyping tools that will provide insight into the population genetics and diversity of this parasite. The recent sequencing of P. vivax isolates from South America, Africa, and Asia presents a new opportunity by uncovering thousands of novel single nucleotide polymorphisms (SNPs). Genotyping a selection of these SNPs provides a robust, low-cost method of identifying parasite infections through their unique genetic signature or barcode. Based on our experience in generating a SNP barcode for P. falciparum using High Resolution Melting (HRM), we have developed a similar tool for P. vivax. We selected globally polymorphic SNPs from available P. vivax genome sequence data that were located in putatively selectively neutral sites (i.e., intergenic, intronic, or 4-fold degenerate coding). From these candidate SNPs we defined a barcode consisting of 42 SNPs. We analyzed the performance of the 42-SNP barcode on 87 P. vivax clinical samples from parasite populations in South America (Brazil, French Guiana), Africa (Ethiopia) and Asia (Sri Lanka). We found that the P. vivax barcode is robust, as it requires only a small quantity of DNA (limit of detection 0.3 ng/μl) to yield reproducible genotype calls, and detects polymorphic genotypes with high sensitivity. The markers are informative across all clinical samples evaluated (average minor allele frequency > 0.1). Population genetic and statistical analyses show the barcode captures high degrees of population diversity and differentiates geographically distinct populations. Our 42-SNP barcode provides a robust, informative, and standardized genetic marker set that accurately identifies a genomic signature for P. vivax infections.

Fig 1. qPCR-HRM assays quantify alleles within DNA mixtures.

The derivative melt graphs show the T_m profiles of a representative assay (12) tested with mixtures of clinical samples known to contain only one allele at this assay position. The ratios of genomic DNA from samples containing reference (C) allele to alternate (T) allele in the mixtures were: (A) 1:10, 1:4, 1:2, 1:1 and (B) 10:1, 4:1, 2:1 1:1. The other 41 assays not shown were tested similarly and all performed comparably to detect mixed allelic samples.

Fig 2. WGA does not affect results in HRM analysis.

The derivative melt graphs show the comparison of T_m profiles of a representative assay (14) tested with mixtures of monogenomic clinical samples processed with and without WGA prior to PCR. The ratios of reference (T) allele to alternate (C) allele in the mixtures were: (A) 1:2 and 1:4 and (B) 4:1 and 2:1.

Fig 3. The 42-SNP barcode is distributed across the genome.

The location of the 42 SNPs is illustrated on the 14 chromosomes of the P. vivax genome. SNPs are colored by their average minor allele frequency (AMAF) among the populations tested; 17 SNPs had AMAF ≥ 0.3, 18 SNPs had 0.3 > AMAF ≥ 0.2, and 7 SNPs had 0.2 > AMAF > 0.1 (S7 Table). Putative centromere locations are indicated by the pinched location on the perimeter of each chromosome [16].

Fig 4. Barcodes with a reduced number of SNPs lose the ability to classify samples by geographic origin.

PCA analysis of the global sample set, with samples colored by collection site. (A) The 42-SNP barcode shows separation by continent in PCA, and the three continental clusters are circled. Samples from South America appear to show substructure, with Brazil samples dividing into two distinct clusters, one of which overlaps the single cluster of samples from French Guiana. (B) A 28-SNP and (C) a 14-SNP barcode selected for maximal population diversity were unable to distinguish populations.

Fig 5. The 42-SNP barcode detects population divergence.

(A) 95% confidence intervals for F_ST values. All F_ST values reflect statistically significant population divergence (p < 10^-5). (B) Population pairs separate in PCA with the first two principal components.