High performance Legionella pneumophila source attribution using genomics-based machine learning classification

• Published in: Applied and environmental microbiology 2024-01, Vol.90 (3), p.e0129223
• Main Authors: Buultjens, Andrew H, Vandelannoote, Koen, Mercoulia, Karolina, Ballard, Susan, Sloggett, Clare, Howden, Benjamin P, Seemann, Torsten, Stinear, Timothy P
• Format: Article
• Language: English
• Subjects: Classification; Disease control; Disease Outbreaks; Environmental Microbiology; Epidemics; Epidemiology; Gene sequencing; Genomes; Genomics; Genomics - methods; Humans; Learning algorithms; Legionella pneumophila; Legionella pneumophila - genetics; Legionnaire's disease; Legionnaires' disease; Legionnaires' Disease - epidemiology; Legionnaires' disease bacterium; Machine learning; Molecular Epidemiology - methods; Multilocus Sequence Typing - methods; Nucleotide sequence; Outbreaks; Phylogeny; Population structure; Public and Environmental Health Microbiology; Spotlight Selection
• ISSN: 0099-2240; 1098-5336; 1098-5336
• DOI: 10.1128/aem.01292-23

Fundamental to effective Legionnaires' disease outbreak control is the ability to rapidly identify the environmental source(s) of the causative agent, . Genomics has revolutionized pathogen surveillance, but has a complex ecology and population structure that can limit source inference based on standard core genome phylogenetics. Here, we present a powerful machine learning approach that assigns the geographical source of Legionnaires' disease outbreaks more accurately than current core genome comparisons. Models were developed upon 534 . genome sequences, including 149 genomes linked to 20 previously reported Legionnaires' disease outbreaks through detailed case investigations. Our classification models were developed in a cross-validation framework using only environmental genomes. Assignments of clinical isolate geographic origins demonstrated high predictive sensitivity and specificity of the models, with no false positives or false negatives for 13 out of 20 outbreak groups, despite the presence of within-outbreak polyclonal population structure. Analysis of the same 534-genome panel with a conventional phylogenomic tree and a core genome multi-locus sequence type allelic distance-based classification approach revealed that our machine learning method had the highest overall classification performance-agreement with epidemiological information. Our multivariate statistical learning approach maximizes the use of genomic variation data and is thus well-suited for supporting Legionnaires' disease outbreak investigations.IMPORTANCEIdentifying the sources of Legionnaires' disease outbreaks is crucial for effective control. Current genomic methods, while useful, often fall short due to the complex ecology and population structure of , the causative agent. Our study introduces a high-performing machine learning approach for more accurate geographical source attribution of Legionnaires' disease outbreaks. Developed using cross-validation on environmental genomes, our models demonstrate excellent predictive sensitivity and specificity. Importantly, this new approach outperforms traditional methods like phylogenomic trees and core genome multi-locus sequence typing, proving more efficient at leveraging genomic variation data to infer outbreak sources. Our machine learning algorithms, harnessing both core and accessory genomic variation, offer significant promise in public health settings. By enabling rapid and precise source identification in Legionnaires' dise