Research Projects

Assessment of Landscape Disturbance and Weather Patterns in Mapping Disease Transmission Risk Near Open Cattle Feedlots
Vitor Martins, PhD, Department of Agriculture and Biological Engineering, Mississippi State University
This research aims to understand and map the risk of mosquito-borne disease transmission around open cattle feedlots in the United States, particularly in states with high concentrations of feedlots, such as North Carolina and Texas. By leveraging geospatial modeling and a range of satellite-derived weather patterns and landscape datasets, the study intends to identify environmental factors affecting mosquito proliferation and potential disease transmission. Key objectives include building baseline information about open cattle feedlot locations using a deep learning object detection algorithm, integrating climate and landscape variables from satellite data, and developing geospatial models to map disease transmission hotspots. The project will utilize various datasets including precipitation, temperature, humidity, soil moisture, and land cover, among others. Ultimately, the research aims to provide valuable insights into disease transmission risks and support targeted prevention and control measures to sustain cattle production in the U.S. Test Performance of Normal Saline as a Transport Medium for Detection of Tritrichomonas foetus in Cattle Herds
David Smith, DVM, PhD, Department of Pathobiology and Population Medicine College of Veterinary Medicine, Mississippi State University
Bovine trichomoniasis is a venereal infection of cattle responsible for significant reproductive losses in infected herds, and an important regulatory disease of cattle in the United States. A recent PCR-based diagnostic test has promise for more accurate classification of infected cattle; however, the test was validated using phosphate-buffered saline (PBS) as the transport media. Even though PBS is a common laboratory reagent, it is not common in veterinary practices and is more expensive than the readily available 0.9% (normal) saline. The objective of this research is to compare the diagnostic performance of PCR with normal saline compared to PBS as the transport medium. Use of Arthropods Vectors to Classify Cattle Herds by Anaplasmosis Infection Status
David Smith, DVM, PhD, Department of Pathobiology and Population Medicine College of Veterinary Medicine, Mississippi State University
Bovine anaplasmosis is a blood borne infection of cattle. Infection is common in the southeastern and northwestern United States and emerging into the central region of the US. Long-term feeding of antimicrobial drugs is a common practice for the control of anaplasmosis in endemic regions and is therefore an important concern for antimicrobial stewardship. Currently, epidemiological research to test temporal and spatial factors associated with the spread of anaplasmosis requires costly handling of cattle to collect blood samples to determine herd infection status. The objective of this research is to test the diagnostic value of collecting mechanical (tabanid flies) and biological (Dermacentor ticks) vectors to more easily determine cattle herd infection status with less expense and less risk for injury to cattle. Thermography as a Means of Early Disease Detection
Kimberly Woodruff, DVM, PhD, Department of Pathobiology and Population Medicine College of Veterinary Medicine, Mississippi State University
Whereas taking a rectal temperature is recognized as the most accurate means of assessing body temperature, it is impractical to use this method for frequent screening for disease, in herds with large numbers of animals, or in animals in which handling causes stress and an artificial rise in temperature. Early detection of fever or inflammation may be a way to detect disease early, allowing for quicker removal of the animal from the population and faster access to treatment and care.

Infrared thermography has been used as a means of detecting variations in temperature and areas of inflammation in both humans and animals. Studies have been performed detailing the use of thermography in individual animals, however few studies exist detailing the use of thermography at the herd level and there are few studies describing the sensitivity and specificity of disease detection in animals on an individual animal or herd level.

Researchers at MSU-CVM are evaluating the use of infrared thermography as a non-invasive method to evaluate body temperature in animals without restraint. Once validated, this method can be used for monitoring many animal populations such as animal shelters, livestock herds, and wildlife. Development of Non-Invasive Test or European Foul Brood
Kimberly Woodruff, DVM, PhD, Department of Pathobiology and Population Medicine College of Veterinary Medicine, Mississippi State University
American foulbrood (Paenibacillus larvae) and European foulbrood (Melissococcus plutonius) are two of the most common diseases of honeybees. American foulbrood (AFB) contributes to major hive loss every year as there is no treatment available, requiring destruction of infected hives. As the forms of control and prevention for the two bacteria vary, it is important to differentiate the two diseases, and important to understand the epidemiology of the two diseases, including their distribution across the United States. Testing is available for both diseases but require samples from inside the hive. We are proposing to develop rapid screening tests for both diseases using samples that can be collected from outside the hive, for instance, from the outside of the entrance into the hive. Once a less invasive means of disease detection is developed, we can monitor the disease status in multiple areas and map the prevalence and spread of the disease and look for associations of disease and environmental factors. Cross Sectional Study to Determine Risk Factors for Anaplasmosis and Other Endemic Disease of Cattle
Isaac Jumper, DVM, PhD, Department of Pathobiology and Population Medicine College of Veterinary Medicine, Mississippi State University
Describing the prevalence of diseases common to beef cattle in the state of Mississippi is critical to developing effective prevention and control strategies. Diseases such as caused by Anaplasma marginale (i.e., bovine anaplasmosis), bovine viral diarrhea virus, bovine leukemia virus, bluetongue virus, leptospirosis, Neospora caninum, and gastrointestinal nematode parasites are production-limiting diseases on beef cow-calf operations, and risk factors for these diseases are poorly understood. Our project aims to describe how commonly cattle in beef cow-calf herds across Mississippi have been exposed to these pathogens and identify health or management factors that may be related to these diseases. We have collected blood samples from 2,126 adult cows across 40 herds, and fecal samples from1,666 adult cows from 36 herds across the state. At the time these samples were collected, we also gathered information from the owners/managers of these cattle that describes cattle health and management practices on the operation. We are currently in the process of analyzing, summarizing, and preparing this data for publication. AI-Driven Livestock Health Monitoring
Nisha Pillai, PhD Department of Computer Science and Engineering, Mississippi State University
Managing livestock effectively requires keeping track of their health and location to improve productivity and ensure their well-being. Using drones (UAVs) and computer vision can make this process easier by providing a non-invasive way to monitor animals across large and difficult terrains. However, training artificial intelligence (AI) models to recognize and track livestock requires a lot of labeled data, which is often hard to get. To solve this problem, our project uses a smart learning approach called reinforcement learning to select the best pre-trained AI model for livestock detection. We also developed a method to improve training data by adjusting for different lighting, environments, and animal behaviors. This makes the AI model more reliable, even when there’s limited data. By combining advanced AI techniques with adaptable learning strategies, our research aims to improve disease detection and livestock tracking, helping farmers manage their animals more efficiently. This approach supports sustainable farming and better animal health through smarter, technology-driven solutions. Predictive Genotype to Phenotype Models
Mahalingam Ramkumar, PhD Department of Computer Science and Engineering, Mississippi State University
Genome to phenome (G2P) is the link between an organism’s DNA (genome) and its physical traits or behaviors (phenotypes). This project focuses on analyzing a massive collection of Salmonella genomes—over 545,000 samples—to improve how we study bacterial genetics. We’re working on two key goals:

• The first is to develop a more scalable approach for building pan genome graphs (PGG) - the collective set of genes and genetic variants in a species - by using byte pair encoding (BPE) to compress common patterns.
• The second is to construct a large language model for Salmonella, utilizing all available labels like serotypes, toxicity, antibiotic resistance, etc. The goal is to fine-tune the Salmonella model for creating reliable models for other Prokaryotes with substantially smaller whole genome sequences (WGS).

EpiTwin: Crafting Exact Digital Twins of Vesicular Stomatitis Virus (VSV) Transmission
Chen Zhiqian, PhD Department of Computer Science and Engineering, Mississippi State University
Vesicular stomatitis virus (VSV) causes significant economic impact on U.S. livestock, particularly in border states, due to regulatory restrictions following outbreaks. Current surveillance provides limited data that constrains understanding of VSV transmission dynamics. We present EpiTwin, a unified generative framework that constructs digital twins of VSV outbreaks by leveraging advanced machine learning to extract latent information from sparse data. Our method reconstructs unobserved transmission events and projects potential outbreak scenarios under varying environmental and movement conditions. This framework offers a risk-free laboratory for testing control strategies and provides concise symbolic representations of disease dynamics for informed decision-making in diverse settings. Currently, we has been developing interpretable mathematical model to predict and understand the spread of VSV. Our approach combines graph-based methods with symbolic regression to extract meaningful patterns from ecological and spatial data. The model provides interpretable equations that explain the virus’s spread dynamics, aiding in more effective prevention strategies. Recombination and Diversity in Bovine Coronavirus
Florencia Meyer, PhD Department of Biochemistry, Molecular Biology, Entomology & Plant Pathology
Bovine coronavirus (BCoV) is an enteropathogenic and respiratory virus commonly associated with the bovine respiratory disease. Like most RNA viruses, coronaviruses accumulate nucleotide changes at a higher rate than other viruses during replication. A rapid mutation rate combined with the potential for recombination often leads to the emergence of variants with enhanced replication or transmission capability. When closely related coronaviruses infect the same host, the opportunity for the emergence of new zoonotic strains increases. Bovine coronavirus is closely related to human coronavirus associated with the seasonal common cold and to coronaviruses of domestic production species, and has been found in a variety of wildlife species. This project investigates the genetic diversity of this virus within dairy farm systems in Mississippi and Georgia and assess BCoV’s potential to recombine by integrating analyses of genomic sequence variation with geographical and environmental data such as seasonality, weather, outbreaks, or other stressors. Our long-term goal is to better understand how the virus spreads to develop predictive models that would allow us to rapidly identify variants of concern. Minimizing Disease Transmission in Poultry through Rapid Detection and Predictive Models
Li Zhang, PhD Department of Poultry Science, Mississippi State University
This project aims to better detect, control, and prevent respiratory diseases in poultry and cattle, which can harm animal health and reduce farm productivity. By studying bacteria like Mycoplasma and E. coli we will seek to understand how they spread, change over time, and impact livestock. By using genetic analysis, disease tracking, and environmental data, we will work to identify where outbreaks are likely to happen and predict how these diseases will spread. The end goal is to develop better tools and models to help farmers and veterinarians detect and manage these diseases more effectively to keep animals healthier and make agriculture more sustainable. Stream Networks as Predictors of Waterborne Pathogen Phylodynamic
Michael Sandel, PhD Department of Wildlife, Fisheries, and Aquaculture, Mississippi State University
Waterborne infectious diseases present an ongoing challenge to human and animal health. The current lack of effective predictors of microbial dispersal in freshwater ecosystems—partly due to the unique dendritic geometric complexity of stream networks—necessitates further investigation. This study examines the effects of hydrologic connectivity on bacterial dissemination within stream networks through a hierarchical analysis of bacterial community composition in the Noxubee River watershed of Mississippi. Using environmental DNA (eDNA) detection methods, we aim to develop a comprehensive stream network model to assess the relative abundance of bacterial communities in conjunction with the National Water Model (NWM). By incorporating hydrologic data alongside bacterial relative abundances, we seek to determine the spatiotemporal factors influencing microbial dispersion.

This study encompasses 54 sampling sites within a 200 km² area, representing a stratified survey of the Noxubee Watershed. eDNA metabarcoding facilitates the analysis of alpha and beta diversity to identify trends along the watershed. Leveraging the fractal geometry of stream networks enhances the understanding of self-similar patterns and their influence on the movement and coalescence of microbial communities across varying spatial scales. The broad applicability of these predictive mechanisms will be tested by comparing the Noxubee River model with the Wind River Watershed in Wyoming. Thus, this study aims to provide an enhanced understanding of microbial dynamics within freshwater ecosystems and improve management strategies for mitigating the impacts of waterborne pathogens. Using Computer Vision and Radar to Understand and Predict Parasite Spread
Garrett Street, PhD Department of Wildlife, Fisheries, and Aquaculture, Mississippi State University
This project focuses on the movements of commercial honeybees as it affects colony health and persistence through the spread of parasitic Varroa mites and the diseases they carry. First, using an AI-driven computer vision system we will monitor marked honeybees within and between colonies to identify the frequency and determinants of movement behaviors contributing to Varroa spread (i.e. drifting, when bees from one colony migrate into another; and robbing, when healthy colonies invade weaker colonies to steal royal jelly and honey). Second, using a novel scanning harmonic radar system, we will monitor the movements of individually tagged bees throughout the landscape to characterize bee movements based on habitat preferences and landscape conditions, and identify how foraging behaviors and movement combine to affect pollination services, the likelihood of encountering pesticides, and overall colony health. Integration of Multiple Data Streams to Create Robust Spatial Predictions of CWD Risk
Melanie Boudreau, PhD Department of Wildlife, Fisheries, and Aquaculture, Mississippi State University
Within the southeastern US, Chronic Wasting Disease (CWD) has been detected in white–tailed deer. As a valued game species, deer have been extensively studied allowing for the cumulation of large datasets that can be used to parameterize animal space use and disease transmission. We aim to add to leverage existing knowledge to combine spatially explicit environmental, animal interaction, and epidemiological information into a predictive model of CWD spatial risk. Seeing through the Murky Waters: Understanding Catfish Disease Susceptibility as a Function of Behavior and Pond Environmental Conditions
Melanie Boudreau, PhD Department of Wildlife, Fisheries, and Aquaculture, Mississippi State University
Commercial production of ictalurid catfishes is the largest aquaculture industry in the United States. During potentially hypoxic pond conditions at night, or during high summer temperatures, catfish may be physiologically more susceptible to disease, although the ability of catfish to behaviorally mitigate this risk is unknown. Our team aims to use biologging technology to further understand the impact of environmental conditions on catfish movement and how that links to disease susceptibility.