SPREAD: Spatiotemporal Pathogen Relationships and Epidemiological Analysis Dashboard.

In the scope of public health, the rapid identification and control of infectious disease outbreaks are a paramount concern. Traditional surveillance methods often face challenges in effectively combining genetic, geographical, and temporal data, which is crucial for a comprehensive understanding of disease transmission dynamics. Addressing this critical need, the Spatiotemporal Phylogenomic Research and Epidemiological Analysis Dashboard (SPREAD) emerges as an innovative standalone web-based application. SPREAD integrates several modules for detailed genomic relationships, pinpointing genetically close pathogens, and spatial mapping, providing in-depth views of how diseases spread across populations and territories, with significant advantage to manage both bacteria and viruses based on allele and variant calling, respectively. Designed for broad accessibility, SPREAD operates seamlessly within web browsers, eliminating the need for sophisticated IT infrastructure and facilitating its use across various public health contexts. Its intuitive interface ensures that users can effortlessly navigate complex datasets, facilitating widespread access to advanced surveillance capabilities. Through its initial deployments, SPREAD has proven instrumental in quickly identifying transmission clusters, significantly aiding in the formulation of prompt and targeted public health responses. Through the integration of state-of-the-art technology with a focus on user-centered design, SPREAD offers a promising solution that highlights the potential of digital health innovations.

Spatial and temporal dynamics of West Nile virus between Africa and Europe.

It is unclear whether West Nile virus (WNV) circulates between Africa and Europe, despite numerous studies supporting an African origin and high transmission in Europe. We integrated genomic data with geographic observations and phylogenetic and phylogeographic inferences to uncover the spatial and temporal viral dynamics of WNV between these two continents. We focused our analysis towards WNV lineages 1 (L1) and 2 (L2), the most spatially widespread and pathogenic WNV lineages. Our study shows a Northern-Western African origin of L1, with back-and-forth exchanges between West Africa and Southern-Western Europe; and a Southern African origin of L2, with one main introduction from South Africa to Europe, and no back introductions observed. We also noticed a potential overlap between L1 and L2 Eastern and Western phylogeography and two Afro-Palearctic bird migratory flyways. Future studies linking avian and mosquito species susceptibility, migratory connectivity patterns, and phylogeographic inference are suggested to elucidate the dynamics of emerging viruses.

Harmonization of supervised machine learning practices for efficient source attribution of Listeria monocytogenes based on genomic data.

BACKGROUND: Genomic data-based machine learning tools are promising for real-time surveillance activities performing source attribution of foodborne bacteria such as Listeria monocytogenes. Given the heterogeneity of machine learning practices, our aim was to identify those influencing the source prediction performance of the usual holdout method combined with the repeated k-fold cross-validation method. METHODS: A large collection of 1 100 L. monocytogenes genomes with known sources was built according to several genomic metrics to ensure authenticity and completeness of genomic profiles. Based on these genomic profiles (i.e. 7-locus alleles, core alleles, accessory genes, core SNPs and pan kmers), we developed a versatile workflow assessing prediction performance of different combinations of training dataset splitting (i.e. 50, 60, 70, 80 and 90%), data preprocessing (i.e. with or without near-zero variance removal), and learning models (i.e. BLR, ERT, RF, SGB, SVM and XGB). The performance metrics included accuracy, Cohen's kappa, F1-score, area under the curves from receiver operating characteristic curve, precision recall curve or precision recall gain curve, and execution time. RESULTS: The testing average accuracies from accessory genes and pan kmers were significantly higher than accuracies from core alleles or SNPs. While the accuracies from 70 and 80% of training dataset splitting were not significantly different, those from 80% were significantly higher than the other tested proportions. The near-zero variance removal did not allow to produce results for 7-locus alleles, did not impact significantly the accuracy for core alleles, accessory genes and pan kmers, and decreased significantly accuracy for core SNPs. The SVM and XGB models did not present significant differences in accuracy between each other and reached significantly higher accuracies than BLR, SGB, ERT and RF, in this order of magnitude. However, the SVM model required more computing power than the XGB model, especially for high amount of descriptors such like core SNPs and pan kmers. CONCLUSIONS: In addition to recommendations about machine learning practices for L. monocytogenes source attribution based on genomic data, the present study also provides a freely available workflow to solve other balanced or unbalanced multiclass phenotypes from binary and categorical genomic profiles of other microorganisms without source code modifications.