Search

In this study, we explore how transformer models, which are known for their attention mechanisms, can improve pathogen prediction in pastured poultry farming. By combining farm management practices with microbiome data, our model outperforms traditional prediction methods in terms of the F1 score—an evaluation metric for model performance—thus fulfilling an essential need in predictive microbiology. Additionally, the emphasis is on making our model’s predictions explainable. We introduce a novel approach for identifying feature importance using the model’s attention matrix and the PageRank algorithm, offering insights that enhance our comprehension of established techniques such as DeepLIFT. Our results showcase the efficacy of transformer models in pathogen prediction for food safety and mark a noteworthy contribution to the progress of explainable AI within the biomedical sciences. This study sheds light on the impact of effective farm management practices and highlights the importance of technological advancements in ensuring food safety.

Salmonella spp., a leading cause of foodborne illness, is a formidable global menace due to escalating antimicrobial resistance (AMR). The evaluation of minimum inhibitory concentration (MIC) for antimicrobials is critical for characterizing AMR. The current whole genome sequencing (WGS)-based approaches for predicting MIC are hindered by both computational and feature identification constraints. We propose an innovative methodology called the “Genome Feature Extractor Pipeline” that integrates traditional machine learning (random forest, RF) with deep learning models (multilayer perceptron (MLP) and DeepLift) for WGS-based MIC prediction. We used a dataset from the National Antimicrobial Resistance Monitoring System (NARMS), comprising 4500 assembled genomes of nontyphoidal Salmonella, each annotated with MIC metadata for 15 antibiotics. Our pipeline involves the batch downloading of annotated genomes, the determination of feature importance using RF, Gini-index-based selection of crucial 10-mers, and their expansion to 20-mers. This is followed by an MLP network, with four hidden layers of 1024 neurons each, to predict MIC values. Using DeepLift, key 20-mers and associated genes influencing MIC are identified. The 10 most significant 20-mers for each antibiotic are listed, showcasing our ability to discern genomic features affecting Salmonella MIC prediction with enhanced precision. The methodology replaces binary indicators with k-mer counts, offering a more nuanced analysis. The combination of RF and MLP addresses the limitations of the existing WGS approach, providing a robust and efficient method for predicting MIC values in Salmonella that could potentially be applied to other pathogens.

Bovine Respiratory Disease (BRD) is a multifactorial condition affecting cattle worldwide resulting in high rates of morbidity and mortality. The disease can be triggered by Bovine Herpesvirus-1 (BoHV-1) infection, stress, and the subsequent proliferation and lung colonization by commensal bacteria such as Mannheimia haemolytica, ultimately inducing severe pneumonic inflammation. Due to its polymicrobial nature, the study of BRD microbes requires co-infection models. While several past studies have mostly focused on the effects of co-infection on host gene expression, we focused on the relationship between BRD pathogens during co-infection, specifically on M. haemolytica’s effect on BoHV-1 replication. This study shows that M. haemolytica negatively impacts BoHV-1 replication in a dose-dependent manner in different in vitro models. The negative effect was observed at very low bacterial doses while increasing the viral dose counteracted this effect. Viral suppression was also dependent on the time at which each microbe was introduced to the cell culture. While acidification of the culture medium did not grossly affect cell viability, it significantly inhibited viral replication. We conclude that M. haemolytica and BoHV-1 interaction is dose and time-sensitive, wherein M. haemolytica proliferation induces significant viral suppression when the viral replication program is not fully established.

Zoonotic diseases or zoonoses are infections due to the natural transmission of pathogens between species (animals and humans). More than 70% of emerging infectious diseases are attributed to animal origin. Artificial Intelligence (AI) models have been used for studying zoonotic pathogens and the factors that contribute to their spread. The aim of this literature survey is to synthesize and analyze machine learning, and deep learning approaches applied to study zoonotic diseases to understand predictive models to help researchers identify the risk factors, and develop mitigation strategies. Based on our survey findings, machine learning and deep learning are commonly used for the prediction of both foodborne and zoonotic pathogens as well as the factors associated with the presence of the pathogens.

Due to nutritional benefits and perceived humane ways of treating the animals, the demand for antibiotic-free pastured poultry chicken has continued to be steadily rise. Despite the non-usage of antibiotics in pastured poultry broiler production, antibiotic resistance (AR) is reported in zoonotic poultry pathogens. However, factors that drive multidrug resistance (MDR) in pastured poultry are not well understood. In this study, we used machine learning and deep learning approaches to predict farm management practices and physicochemical properties of feces and soil that drive MDR in zoonotic poultry pathogens. Antibiotic use in agroecosystems is known to contribute to resistance. Evaluation of the development of resistance in environments that are free of antibiotics such as the all-natural, antibiotic-free, pastured poultry production systems described here is critical to understand the background AR in the absence of any selection pressure, i.e., basal levels of resistance. We analyzed 1635 preharvest (feces and soil) samples collected from forty-two pastured poultry flocks and eleven farms in the Southeastern United States. CDC National Antimicrobial Resistance Monitoring System guidelines were used to determine antimicrobial/multidrug resistance profiles of Salmonella, Listeria, and Campylobacter. A combination of two traditional machine learning (RandomForest and XGBoost) and three deep learning (Multi-layer Perceptron, Generative Adversarial Network, and Auto-Encoder) approaches identified critical farm management practices and environmental variables that drive multidrug resistance in poultry pathogens in broiler production systems that represents background resistance. This study enumerates management practices that contribute to AR and makes recommendations to potentially mitigate multidrug resistance and the prevalence of Salmonella and Listeria in pastured poultry.