Exploring the predictive capability of advanced machine learning in identifying severe disease phenotype in Salmonella enterica

Karanth, Shraddha; Tanui, Collins Kipngetich; Meng, Jianghong; Pradhan, Abani K.

doi:10.1016/j.foodres.2021.110817

Cited by 18 publications

(15 citation statements)

References 69 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These genes may also enhance the persistence of L. monocytogenes in different food sources. Eight out of the twenty most important genes were hypothetical genes, which is in line with the findings of prior studies [36,39]. Thus, future studies in-volving the characterization of each gene to understand its importance in L. monocytogenes adaptation and stress response along the food supply chain are warranted.…”

Section: Important Top Twenty Predictor Genessupporting

confidence: 83%

“…With the increasing usage of genome sequencing technologies, it is possible to identify genetic patterns indicative of the food source of pathogens. Recently, machine learning models have been used to identify molecular markers from foodborne pathogens linked with different hosts/phenotypes, which could be used to trace the source of human infections [26,36,37,39]. In the current study, we investigated the potential of machine learning to predict the food source origins of bacterial strains isolated from human cases of listeriosis using machine learning analyses of cgMLST data.…”

Section: Source Attribution Modelmentioning

confidence: 99%

“…Our feature-reduced cgMLST data was randomly split into a training set (70%) and a testing set (30%). Four machine learning algorithms-random forest, logit boost, stochastic gradient boosting, and support vector machine radial kernel-have been successfully applied in studies analyzing WGS data [36,37,39,76] and were therefore used in training our data. We used 10-fold cross-validation, which randomly partitions the training data set into 10 equal folds-nine folds used for model training and one fold to estimate model performance-to obtain the model with the best performance.…”

Section: Machine Learningmentioning

confidence: 99%

“…Basically, by exploring and identifying patterns in data, ML can be used in the classification, regression, or clustering of data to draw meaningful inferences from the same. Genome sequencing information, coupled with machine learning, has been used to predict the risk of listeriosis in humans [37], the host specificity of S. enterica and E. coli [38], and host disease severity based on S. enterica gene presence/absence [36,39], and in the source attribution of S. Typhimurium [26]. With the increase in usage of genome sequencing for exploratory and integrated surveillance activities, generating massive amounts of data, as well as standardization of data collection activities (providing us with useful metadata and other useful information), machine learning and big data analytical tools become the need of the hour to provide a better understanding and improvement of current knowledge in foodborne disease epidemiology.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Machine Learning Model for Food Source Attribution of Listeria monocytogenes

et al. 2022

Self Cite

View full text Add to dashboard Cite

Despite its low morbidity, listeriosis has a high mortality rate due to the severity of its clinical manifestations. The source of human listeriosis is often unclear. In this study, we investigate the ability of machine learning to predict the food source from which clinical Listeria monocytogenes isolates originated. Four machine learning classification algorithms were trained on core genome multilocus sequence typing data of 1212 L. monocytogenes isolates from various food sources. The average accuracies of random forest, support vector machine radial kernel, stochastic gradient boosting, and logit boost were found to be 0.72, 0.61, 0.7, and 0.73, respectively. Logit boost showed the best performance and was used in model testing on 154 L. monocytogenes clinical isolates. The model attributed 17.5 % of human clinical cases to dairy, 32.5% to fruits, 14.3% to leafy greens, 9.7% to meat, 4.6% to poultry, and 18.8% to vegetables. The final model also provided us with genetic features that were predictive of specific sources. Thus, this combination of genomic data and machine learning-based models can greatly enhance our ability to track L. monocytogenes from different food sources.

show abstract

Section: Important Top Twenty Predictor Genessupporting

confidence: 83%

Section: Source Attribution Modelmentioning

confidence: 99%

Section: Machine Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Machine Learning Model for Food Source Attribution of Listeria monocytogenes

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Previous studies have used genomics to identify serovar groups of public health concern. Karanth et al analyzed a limited number of genomes and serovars originating from humans, poultry, and swine to characterize virulent serovars [23]. This analysis had the benefit of using the entire genome of Salmonella to group isolates by disease presentation; however, the computational resources required prevent its application to a large number of isolates.…”

Section: Introductionmentioning

confidence: 99%

The genomic and epidemiological virulence patterns ofSalmonella entericaserovars in the United States

Fenske

Pouzou

Pouillot

et al. 2022

Preprint

View full text Add to dashboard Cite

The serovars of Salmonella enterica display dramatic differences in pathogenesis and host preferences. Grouping Salmonella isolates and serovars by their public health risk can provide better Salmonella control targets along the food chain. We collated a curated set of 12,337 S. enterica isolate genomes from human, beef, and bovine sources in the US. After annotating a virulence gene catalog for each isolate, we used unsupervised random forest methods to estimate the proximity (similarity) between isolates based upon the genomic presentation of putative virulence traits We then grouped isolates (virulence clusters) using hierarchical clustering (Ward's method), used non-parametric bootstrapping to assess cluster stability, and externally validated the virulence clusters against epidemiological virulence measures from FoodNet, the National Outbreak Reporting System (NORS), and US federal sampling of beef products. We identified five stable virulence clusters of S. enterica serovars. Cluster 1 serovars yielded an annual incidence rate of domestically acquired sporadic cases roughly one and a half times higher than the other four clusters combined. Compared to other clusters, cluster 1 also had a higher proportion of infections leading to hospitalization and was implicated in more foodborne and beef-associated outbreaks, despite being isolated at a similar frequency from beef products as other clusters. We also identified subpopulations within 11 serovars. Remarkably, we found S. Infantis and S. Typhimurium subpopulations that significantly differed in genome length and clinical case presentation. Further, we found that the presence of the pESI plasmid accounted for the genome length differences between the S. Infantis subpopulations. Our results demonstrate that S. enterica strains with the highest incidence of human infections share a common virulence repertoire. This work could be used in combination with foodborne surveillance information to best target serovars of public health concern.

show abstract

Advanced data analytics and “omics” techniques to control enteric foodborne pathogens

Karanth,

Pradhan

2024

Advances in Food and Nutrition Research

View full text Add to dashboard Cite

Exploring the predictive capability of advanced machine learning in identifying severe disease phenotype in Salmonella enterica

Cited by 18 publications

References 69 publications

A Machine Learning Model for Food Source Attribution of Listeria monocytogenes

A Machine Learning Model for Food Source Attribution of Listeria monocytogenes

The genomic and epidemiological virulence patterns ofSalmonella entericaserovars in the United States

Advanced data analytics and “omics” techniques to control enteric foodborne pathogens

Contact Info

Product

Resources

About