Genetic analysis reveals long-standing population differentiation and high diversity in the rust pathogen Melampsora lini

Abstract

A priority for research on infectious disease is to understand how epidemiological and evolutionary processes interact to influence pathogen population dynamics and disease outcomes. However, little is understood about how population adaptation changes across time, how sexual vs. asexual reproduction contribute to the spread of pathogens in wild populations and how diversity measured with neutral and selectively important markers correlates across years. Here, we report results from a long-term study of epidemiological and genetic dynamics within several natural populations of the Linum marginale-Melampsora lini plant-pathogen interaction. Using pathogen isolates collected from three populations of wild flax (L. marginale) spanning 16 annual epidemics, we probe links between pathogen population dynamics, phenotypic variation for infectivity and genomic polymorphism. Pathogen genotyping was performed using 1567 genome-wide SNP loci and sequence data from two infectivity loci (AvrP123, AvrP4). Pathogen isolates were phenotyped for infectivity using a differential set. Patterns of epidemic development were assessed by conducting surveys of infection prevalence in one population (Kiandra) annually. Bayesian clustering analyses revealed host population and ecotype as key predictors of pathogen genetic structure. Despite strong fluctuations in pathogen population size and severe annual bottlenecks, analysis of molecular variance revealed that pathogen population differentiation was relatively stable over time. Annually, varying levels of clonal spread (0-44.8%) contributed to epidemics. However, within populations, temporal genetic composition was dynamic with rapid turnover of pathogen genotypes, despite the dominance of only four infectivity phenotypes across the entire study period. Furthermore, in the presence of strong fluctuations in population size and migration, spatial selection may maintain pathogen populations that, despite being phenotypically stable, are genetically highly dynamic.

Fig 1. Melampsora lini populations and genetic clusters differ in their Avr genotype and pathotype compositions.

The distribution of Melampsora lini isolates by study site: (A) pathotypes; (B) Avr genotypes; and by genetic clusters (C) pathotypes; (D) Avr genotypes.

Fig 2. Melampsora lini population differentiation and temporal change revealed by genetic clusters, Avr genotypes and pathotypes.

(A) Annual infection prevalence of Melampsora lini on Linum marginale in Kiandra over years 1987–2008. The distribution of (B) pathotypes, (C) genetic clusters, and (D) Avr genotypes of Melampsora lini populations Kiandra, P1 and P2 over years 1987–2010.

Fig 3. Principal component analysis on SNP genotyping of Melampsora lini shows population differentiation.

Distribution of the genetic variation of Melampsora lini isolates collected from populations Kiandra (blue), P1 (yellow) and P2 (red) based on principal component analysis.

Fig 4. DAPC clustering of Melampsora lini isolates reveals six clusters with low levels of hybridization between clusters.

(A) Genetic clusters of Melampsora lini obtained by DAPC. (B) Distribution of the clusters in the populations and their assignment probability, each bar represents percentage probability to genetic group(s).

Fig 5. Linking Melampsora lini pathotype infectivity and share of the population.

(A) Correlation between Melampsora lini pathotypes share of the population in three populations, Kiandra, P1 and P2, and infectivity over the Linum marginale differential host set. (B) Correlation between the pathotype’s mean share of the population and years of prevalence in the population. (C) Correlation between the differential set measured pathogen infectivity and infectivity measured using sympatric hosts (grey circles, dashed line) and allopatric hosts (black circles, solid line).