Classification of the plant-associated lifestyle of Pseudomonas strains using genome properties and machine learning

• Published in: Scientific reports Vol. 12; no. 1; p. 10857
• Main Authors: Poncheewin, Wasin, van Diepeningen, Anne D., van der Lee, Theo A. J., Suarez-Diez, Maria, Schaap, Peter J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 27.06.2022; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 631/114/1314; 631/114/1386; 631/114/2164; 631/114/2404; 631/114/2785; 631/326/41/2530; 631/326/41/2531; 631/326/421; Classification; Computer applications; Genomes; Humanities and Social Sciences; Learning algorithms; Lifestyles; Machine learning; multidisciplinary; Phenotypes; Phyllosphere; Plant bacterial diseases; Plant growth; Pseudomonas; Rhizosphere; Science; Science (multidisciplinary)
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-022-14913-4

The rhizosphere, the region of soil surrounding roots of plants, is colonized by a unique population of Plant Growth Promoting Rhizobacteria (PGPR). Many important PGPR as well as plant pathogens belong to the genus Pseudomonas . There is, however, uncertainty on the divide between beneficial and pathogenic strains as previously thought to be signifying genomic features have limited power to separate these strains. Here we used the Genome properties (GP) common biological pathways annotation system and Machine Learning (ML) to establish the relationship between the genome wide GP composition and the plant-associated lifestyle of 91 Pseudomonas strains isolated from the rhizosphere and the phyllosphere representing both plant-associated phenotypes. GP enrichment analysis, Random Forest model fitting and feature selection revealed 28 discriminating features. A test set of 75 new strains confirmed the importance of the selected features for classification. The results suggest that GP annotations provide a promising computational tool to better classify the plant-associated lifestyle.