Identification of host-microbe interaction factors in the genomes of soft rot-associated pathogens Dickeya dadantii 3937 and Pectobacterium carotovorum WPP14 with supervised machine learning

Abstract

BackgroundA wealth of genome sequences has provided thousands of genes of unknown function, but identification of functions for the large numbers of hypothetical genes in phytopathogens remains a challenge that impacts all research on plant-microbe interactions. Decades of research on the molecular basis of pathogenesis focused on a limited number of factors associated with long-known host-microbe interaction systems, providing limited direction into this challenge. Computational approaches to identify virulence genes often rely on two strategies: searching for sequence similarity to known host-microbe interaction factors from other organisms, and identifying islands of genes that discriminate between pathogens of one type and closely related non-pathogens or pathogens of a different type. The former is limited to known genes, excluding vast collections of genes of unknown function found in every genome. The latter lacks specificity, since many genes in genomic islands have little to do with host-interaction.ResultIn this study, we developed a supervised machine learning approach that was designed to recognize patterns from large and disparate data types, in order to identify candidate host-microbe interaction factors. The soft rot Enterobacteriaceae strains Dickeya dadantii 3937 and Pectobacterium carotovorum WPP14 were used for development of this tool, because these pathogens are important on multiple high value crops in agriculture worldwide and more genomic and functional data is available for the Enterobacteriaceae than any other microbial family. Our approach achieved greater than 90% precision and a recall rate over 80% in 10-fold cross validation tests.ConclusionApplication of the learning scheme to the complete genome of these two organisms generated a list of roughly 200 candidates, many of which were previously not implicated in plant-microbe interaction and many of which are of completely unknown function. These lists provide new targets for experimental validation and further characterization, and our approach presents a promising pattern-learning scheme that can be generalized to create a resource to study host-microbe interactions in other bacterial phytopathogens.Electronic supplementary materialThe online version of this article (doi:10.1186/1471-2164-15-508) contains supplementary material, which is available to authorized users.

Prevalence and Specificity of Chemoreceptor Profiles in Plant-Associated Bacteria

“…To further validate our findings, we cross-linked our predictions with experimental data from previous studies ( 39 – 43 ). In particular, we found that CRs with increased expression in planta , and particularly those required for full bacterial virulence, belonged to high-DPS clusters ( Table 2 ).…”

“…In particular, we found that CRs with increased expression in planta , and particularly those required for full bacterial virulence, belonged to high-DPS clusters ( Table 2 ). This list includes CRs that are upregulated in Dickeya dadantii 3937 and Pectobacterium carotovorum WPP14, two soft-rot bacterial strains ( 39 ); Dickeya dianthicola RNS04.9, which grows on macerated potato tubers ( 40 ); and Xanthomonas fragariae , which grows on strawberry leaves ( 41 ). Similarly, we found several CRs with very high DPS values (80%) that were shown to be relevant in Xanthomonas citri virulence ( 42 ) or required for fitness of Pseudomonas savastanoi pv.…”

Role of Dickeya dadantii 3937 chemoreceptors in the entry to Arabidopsis leaves through wounds

“…The large number of putative chemoreceptors involved in this process demonstrates the relevance of the perception of plant compounds during the interaction. Indeed, the identification of host–microbe interaction factors in the genome of Dd 3937 with supervised machine learning shows that methyl‐accepting chemotaxis genes are highly enriched among the predicted host–microbe interaction factors in this bacterium (Ma et al ., ).…”

Prediction of bacterial associations with plants using a supervised machine‐learning approach

“…The capacity of a bacterium to develop an interaction with a host is influenced by many elements that intervene to varying degrees, including the environment, bacterial gene components and regulatory networks, or the host itself. The vast amount of data that is currently available as a result of numerous sequencing projects has motivated researchers to explore whether bacteria-host associations can be identified based on genomic information (Ma et al, 2014). Previous studies have been based on sequence similarity to classify bacterial pathogenicity, typically by using pre-established virulence-related genes (Iraola et al, 2012) or genes that are distinctive of a collection of genomes (Andreatta et al, 2010;Barbosa et al, 2014).…”