Genomic surveillance of malaria parasites in an indigenous community in the Peruvian Amazon

Abstract

Hard-to-reach communities represent Peru's main challenge for malaria elimination, but information about transmission in these areas is scarce. Here, we assessed Plasmodium vivax (Pv) and P. falciparum (Pf) transmission dynamics, resistance markers, and Pf hrp2/3 deletions in Nueva Jerusalén (NJ), a remote, indigenous community in the Peruvian Amazon with high population mobility. We collected samples from November 2019 to May 2020 by active (ACD) and passive case detection (PCD) in NJ. Parasites were identified with microscopy and PCR. Then, we analyzed a representative set of positive-PCR samples (Pv = 68, Pf = 58) using highly-multiplexed deep sequencing assays (AmpliSeq) and compared NJ parasites with ones from other remote Peruvian areas using population genetics indexes. The ACD intervention did not reduce malaria cases in the short term, and persistent malaria transmission was observed (at least one Pv infection was detected in 96% of the study days). In Nueva Jerusalen, the Pv population had modest genetic diversity (He = 0.27). Pf population had lower diversity (He = 0.08) and presented temporal clustering, one of these clusters linked to an outbreak in February 2020. Moreover, Pv and Pf parasites from NJ exhibited variable levels of differentiation (Pv Fst = 0.07-0.52 and Pf Fst = 0.11-0.58) with parasites from other remote areas. No artemisin resistance mutations but chloroquine (57%) and sulfadoxine-pyrimethamine (35-67%) were detected in NJ's Pf parasites. Moreover, pfhrp2/3 gene deletions were common (32-50% of parasites with one or both genes deleted). The persistent Pv transmission and the detection of a Pf outbreak with parasites genetically distinct from the local ones highlight the need for tailored interventions focusing on mobility patterns and imported infections in remote areas to eliminate malaria in the Peruvian Amazon.

Keywords: Drug resistance; Genetic diversity; HRP2; Malaria elimination; Malaria persistence; Population genetics.

Figure 1

Study sites and Sample selection. The map shows the 5 areas where samples were collected. Nueva Jerusalen (NJ, in bold) was the main community in this work. This map was generated in QGIS 3.34.1 (https://www.qgis.org/) by Luis Cabrera-Sosa/Viviana Sánchez-Aizcorbe.

Figure 2

Daily distribution of infections due to P. vivax and P. falciparum during PCD in NJ. The bars represent the number of PCR-positive infections in each day.

Figure 3

Effect of ACD intervention on malaria in NJ. The positive rate in each weekly ACD visit, determined by microscopy or PCR, on malaria infections and by species is shown.

Figure 4

Population structure and parasite connectivity of Pv in NJ. (a) PCA of 68 Pv samples in NJ. (b) Network inferred by IBD between Pv isolates from NJ. Edges connecting parasite pairs indicate that > 45% of their genomes descended from a common ancestor. (c) Neighbor-joining network of Pv samples. All analyses showed the absence of temporal clustering.

Figure 5

Population structure and parasite connectivity of Pf in NJ. (a) PCA of 58 Pf samples in NJ. The shape/color schemes represent to each month. (b) Relative proportion of each cluster in the different months. (c) Network inferred by IBD between Pf isolates from NJ. Edges connecting parasite pairs indicate that > 45% of their genomes descended from a common ancestor. (d) Neighbor-joining network of Pf samples. All analyses showed sub-structuring in 3 clusters (depicted by ellipses), highlighting Cluster 2 with only samples from Feb 2020.

Figure 6

Population genetic analysis and connectivity of Pf samples from NJ (n = 58) and other remotes areas: Mazan (n = 9), Santa Emilia (n = 12), Andoas (n = 4). (a) PCA of Pf samples, showing some clusters with samples from different areas. The shape/color schemes represent to each of area/time of collection. PCA. (b) Expected heterozygosity (He). Each dot represents the mean He of 17/28 non-fixed positions from the SNP barcode for all samples in each group. Low to moderate diversity was noted. (c) Pairwise Fst statistic among the groups. The heatmap color scheme was based on the maximum and minimum of Fst values (numbers at the center of each square). Mazan samples were the most differentiated. (d) Network inferred by IBD between Pf isolates. Edges connecting parasite pairs indicate that > 45% of their genomes descended from a common ancestor. Node colors indicate the 5 groups. Clustering pattern was similar to PCA.

Figure 7

The pfhrp2 and pfhrp3 genotyping. PCR results were used to create the pfhrp2/3 genotypes in all areas (A) or within NJ (B). Double deletion was predominant in Mazan, but both genes were present in the rest of areas. In NJ, pfhrp2+/pfhrp3+ was common in Clusters 1 and 2, and pfhrp2−/pfhrp3+ was predominant in Cluster 3.