Reference-Free Plant Disease Detection Using Machine Learning and Long-Read Metagenomic Sequencing

Regional diversity and leaf microbiome interactions of the fungal maize pathogen Exserohilum turcicum in Switzerland: A metagenomic analysis

The spread and adaptation of fungal plant pathogens in agroecosystems are facilitated by environmental homogeneity. Metagenomic sequencing of infected tissues allowed us to monitor eco-evolutionary dynamics and interactions between host, pathogen and plant microbiome. Exserohilum turcicum, the causal agent of northern corn leaf blight (NCLB) in maize, is distributed in multiple clonal lineages throughout Europe. To characterize regional pathogen diversity, we conducted metagenomic DNA sequencing on 241 infected leaf samples from the highly susceptible Swiss maize landrace Rheintaler Ribelmais, collected over 3 years (2016-2018) from an average of 14 agricultural farms within the Swiss Rhine Valley. All major European clonal lineages of E. turcicum were identified. Lineages differ by their mating types which indicates potential for sexual recombination and rapid evolution of new pathogen strains, although we found no evidence of recent recombination. The associated eukaryotic and prokaryotic leaf microbiome exhibited variation in taxonomic diversity between years and locations and is likely influenced by local weather conditions. A network analysis revealed distinct clusters of eukaryotic and prokaryotic taxa that correlates with the frequency of E. turcicum sequencing reads, suggesting causal interactions. Notably, the yeast genus Metschnikowia exhibited a strongly negative association with E. turcicum, supporting its known potential as biological control agent against fungal pathogens. Our findings show that metagenomic sequencing is a useful tool for analysing the role of environmental factors and potential pathogen-microbiome interactions in shaping pathogen dynamics and evolution, suggesting their potential for effective pathogen management strategies.

Microbiome-based classification models for fresh produce safety and quality evaluation

Small sample sizes and loss of sequencing reads during the microbiome data preprocessing can limit the statistical power of differentiating fresh produce phenotypes and prevent the detection of important bacterial species associated with produce contamination or quality reduction. Here, we explored a machine learning-based k-mer hash analysis strategy to identify DNA signatures predictive of produce safety (PS) and produce quality (PQ) and compared it against the amplicon sequence variant (ASV) strategy that uses a typical denoising step and ASV-based taxonomy strategy. Random forest-based classifiers for PS and PQ using 7-mer hash data sets had significantly higher classification accuracy than those using the ASV data sets. We also demonstrated that the proposed combination of integrating multiple data sets and leveraging a 7-mer hash strategy leads to better classification performance for PS and PQ compared to the ASV method but presents lower PS classification accuracy compared to the feature-selected ASV-based taxonomy strategy. Due to the current limitation of generating taxonomy using the 7-mer hash strategy, the ASV-based taxonomy strategy with remarkably less computing time and memory usage is more efficient for PS and PQ classification and applicable for important taxa identification. Results generated from this study lay the foundation for future studies that wish and need to incorporate and/or compare different microbiome sequencing data sets for the application of machine learning in the area of microbial safety and quality of food.

IMPORTANCE

Identification of generalizable indicators for produce safety (PS) and produce quality (PQ) improves the detection of produce contamination and quality decline. However, effective sequencing read loss during microbiome data preprocessing and the limited sample size of individual studies restrain statistical power to identify important features contributing to differentiating PS and PQ phenotypes. We applied machine learning-based models using individual and integrated k-mer hash and amplicon sequence variant (ASV) data sets for PS and PQ classification and evaluated their classification performance and found that random forest (RF)-based models using integrated 7-mer hash data sets achieved significantly higher PS and PQ classification accuracy. Due to the limitation of taxonomic analysis for the 7-mer hash, we also developed RF-based models using feature-selected ASV-based taxonomic data sets, which performed better PS classification than those using the integrated 7-mer hash data set. The RF feature selection method identified 480 PS indicators and 263 PQ indicators with a positive contribution to the PS and PQ classification.