Machine Learning-Based Identification of Mating Type and Metalaxyl Response in Phytophthora infestans Using SSR Markers.

Phytophthora infestans is the causal agent of late blight in potato. The occurrence of P. infestans with both A1 and A2 mating types in the field may result in sexual reproduction and the generation of recombinant strains. Such strains with new combinations of traits can be highly aggressive, resistant to fungicides, and can make the disease difficult to control in the field. Metalaxyl-resistant isolates are now more prevalent in potato fields. Understanding the genetic structure and rapid identification of mating types and metalaxyl response of P. infestans in the field is a prerequisite for effective late blight disease monitoring and management. Molecular and phenotypic assays involving molecular and phenotypic markers such as mating types and metalaxyl response are typically conducted separately in the studies of the genotypic and phenotypic diversity of P. infestans. As a result, there is a pressing need to reduce the experimental workload and more efficiently assess the aggressiveness of different strains. We think that employing genetic markers to not only estimate genotypic diversity but also to identify the mating type and fungicide response using machine learning techniques can guide and speed up the decision-making process in late blight disease management, especially when the mating type and metalaxyl resistance data are not available. This technique can also be applied to determine these phenotypic traits for dead isolates. In this study, over 600 P. infestans isolates from different populations-Estonia, Pskov region, and Poland-were classified for mating types and metalaxyl response using machine learning techniques based on simple sequence repeat (SSR) markers. For both traits, random forest and the support vector machine demonstrated good accuracy of over 70%, compared to the decision tree and artificial neural network models whose accuracy was lower. There were also associations (p < 0.05) between the traits and some of the alleles detected, but machine learning prediction techniques based on multilocus SSR genotypes offered better prediction accuracy.

The Variability of Phytophthora infestans Isolates Collected from Estonian Islands in the Baltic Sea.

Knowledge of a pathogen's genetic variability and population structure is of great importance to effective disease management. In this study, 193 isolates of Phytophthora infestans collected from three Estonian islands were characterized over 3 years using simple sequence repeat (SSR) marker data complemented by information on their mating type and resistance to metalaxyl. In combination with SSR marker data from samples in the neighboring Pskov region of Northwest Russia, the impact of regional and landscape structure on the level of genetic exchange was also examined. Among the 111 P. infestans isolates from Estonian islands, 49 alleles were detected among 12 SSR loci, and 59 SSR multilocus genotypes were found, of which 64% were unique. The genetic variation was higher among years than that among islands, as revealed by the analysis of molecular variance. The frequency of metalaxyl-resistant isolates increased from 9% in 2012 to 30% in 2014, and metalaxyl resistance was most frequent among A1 isolates. The test for isolation by distance among the studied regions was not significant, and coupled with the absence of genetic differentiation, the result revealed gene flow and the absence of local adaptation. The data are consistent with a sexual population in which diversity is driven by an annual germination of soilborne oospores. The absence of shared genotypes over the years has important implications when it comes to the management of diseases. Such population diversity can make it difficult to predict the nature of the outbreak in the coming year as the genetic makeup is different for each year.

High Temporal Variability in Late Blight Pathogen Diversity, Virulence, and Fungicide Resistance in Potato Breeding Fields: Results from a Long-Term Monitoring Study.

Long-term site-specific studies describing changes in the phenotypic variability of Phytophthora infestans populations allow quantitative predictions of pathogen spread and possible outbreaks of epidemics, and provide key input for regional resistance breeding programs. Late blight samples were collected from potato (Solanum tuberosum) breeding fields in Estonia during a twelve-year study period between 2001 and 2014. In total, 207 isolates were assessed for mating type and 235 isolates for metalaxyl resistance and 251 isolates for virulence factors. The frequency of mating types strongly fluctuated across the years, whereas the later period of 2010-2014 was dominated by the A2 mating. Despite fluctuations, both mating types were recorded in the same fields in most years, indicating sustained sexual reproduction of P. infestans with oospore production. Metalaxyl-resistant and intermediately resistant strains dominated in the first years of study, but with the progression of the study, metalaxyl-sensitive isolates became dominant, reaching up to 88%. Racial diversity, characterized by normalized Shannon diversity index decreased in time, varying from 1.00 in 2003 to 0.43 in 2013. The frequency of several virulence factors changed in a time-dependent manner, with R2 increasing and R6, R8, and R9 decreasing in time. Potato cultivar resistance background did not influence the frequency of P. infestans mating type, response to metalaxyl, and racial diversity. However, the diversity index decreased in time among isolates collected from resistant and susceptible cultivars, and remained at a high level in moderately resistant cultivars. These data demonstrate major time-dependent changes in racial diversity, fungicide resistance, and virulence factors in P. infestans, consistent with alterations in the control strategies and popularity of potato cultivars with different resistance.

Highly Diverse Phytophthora infestans Populations Infecting Potato Crops in Pskov Region, North-West Russia.

There is limited understanding of the genetic variability in Phytophthora infestans in the major potato cultivation region of north-western Russia, where potato is grown primarily by small households with limited chemical treatment of late blight. In this study, the mating type, sensitivity to metalaxyl, and genotype and population genetic diversity (based on 12 simple sequence repeat (SSR) markers) of 238 isolates of P. infestans from the Pskov region during the years 2010-2013 were characterized. The aim was to examine the population structure, phenotypic and genotypic diversity, and the prevalent reproductive mode of P. infestans, as well as the influence of the location, time, and agricultural management practices on the pathogen population. The frequency of the A2 mating was stable over the four seasons and ranged from 33 to 48% of the sampled population. Both mating types occurred simultaneously in 90% of studied fields, suggesting the presence of sexual reproduction and oospore production in P. infestans in the Pskov region. Metalaxyl-sensitive isolates prevailed in all four years (72%), however, significantly fewer sensitive isolates were found in samples from large-scale conventional fields. A total of 50 alleles were detected in the 141 P. infestans isolates analyzed for genetic diversity. Amongst the 83 SSR multilocus genotypes (MLGs) detected, 65% were unique and the number of MLGs varied between locations from 3 to 20. These results, together with the high genotypic diversity observed in all the locations and the lack of significance of linkage disequilibrium, suggest that sexual recombination is likely responsible for the unique MLGs and the high genetic diversity found in the Pskov region population, resembling those of north-eastern European populations.