The core technology being developed stems from EnSenSys’s patented ESS Protect platform, which was initially designed to detect viral signatures in human breath. This platform employs advanced hyperspectral imaging techniques, coupled with machine learning algorithms, to analyze subtle molecular changes indicative of viral infections. By adapting this technology to animal health, the researchers aim to deliver a novel diagnostic tool termed ESS Protect – Animal, which will allow for swift and accurate detection of bovine respiratory disease (BRD), a significant threat to cattle health and agricultural productivity worldwide.

Hyperspectral imaging captures data across dozens or hundreds of narrow spectral bands, far beyond what the human eye can perceive, enabling the detection of unique viral or bacterial signatures within biological samples. When applied to cattle breath, this technique reveals spectral patterns that correspond to the presence of infectious agents or inflammatory responses. AI-driven algorithms then process this multidimensional data, distinguishing healthy animals from those showing early signs of disease, even before clinical symptoms manifest. This capability holds enormous potential for controlling outbreaks and reducing economic losses in the livestock industry.

The collaboration between UTIA and EnSenSys exemplifies the power of interdisciplinary research, combining expertise in agriculture, veterinary medicine, artificial intelligence, and sensor technology. Researchers will leverage data collected from a 2024 field study at the UTIA Middle Tennessee AgResearch and Education Center in Spring Hill, Tennessee, where early prototypes of the sensor system were tested on cattle populations under real-world farming conditions. By training robust machine learning models on this foundation, the team aims to refine detection accuracy and build scalable solutions adaptable to a wide range of livestock environments.

As part of the project goals, the team will engineer a field-deployable hyperspectral sensing unit that can be easily integrated into existing farm infrastructure. This device will maintain high sensitivity and specificity while offering portability and durability essential for use in diverse agricultural settings. In parallel, the development of sophisticated AI models capable of real-time data processing will be prioritized to ensure timely diagnostics critical for decision-making by farmers, veterinarians, and animal health officials.

The initiative signifies EnSenSys’s formal entrance into the AI TechX consortium, a collective dedicated to accelerating practical AI applications through synergistic partnerships between academic institutions and industry leaders. LtGen John ‘Glad’ Castellaw, USMC (Ret.) and CEO of EnSenSys, emphasized the strategic importance of this collaboration, highlighting its role in advancing biosensing technologies that safeguard animal health and bolster food security. Such cooperation not only fosters innovation but also establishes a roadmap for transforming theoretical AI research into tangible tools that address pressing challenges in agroecosystems.

Beyond immediate technology development, the project envisions the foundation for a comprehensive AgriAI Center of Excellence at UTIA, positioning the University of Tennessee as a leader in AI-enabled agriculture innovation. This proposed center will function as a hub for integrating cutting-edge AI methodologies with field-specific expertise, delivering predictive analytics, automation capabilities, and precision farming solutions. The broader vision includes empowering agricultural producers to enhance productivity, optimize resource use, and build resilience against environmental and economic uncertainties impacting the sector.

While bovine respiratory disease remains the initial focus, the modular nature of this hyperspectral and AI platform paves the way for expansion into other livestock species and a broader spectrum of infectious diseases. By developing adaptable sensing and computational frameworks, the technology promises scalable applications across various farming operations, aligning with global trends toward precision agriculture and sustainable animal husbandry practices.

The project’s success will hinge on meticulous data acquisition and multidisciplinary analysis, involving veterinarians, sensor specialists, AI researchers, and agricultural scientists. Continuous refinement of the algorithms through iterative field testing will enhance the models’ predictive capabilities and operational robustness. These improvements aim to minimize false positives and negatives, critical for widespread adoption and trust among end-users in the agricultural community.

From a technical perspective, hyperspectral imaging sensors employed in this research capture reflectance spectra spanning visible to near-infrared wavelengths, where biological tissues exhibit distinct vibrational and electronic responses. This spectral granularity enables detection of biomarkers associated with viral infection-induced metabolic alterations in cattle breath condensate. When integrated with machine learning classifiers, such as convolutional neural networks and ensemble learning models, the system can isolate disease-specific spectral signatures from background noise and environmental interference.

Furthermore, the deployment of contactless sensing technologies minimizes stress and pathogen transmission risks during sampling, offering a safer alternative to conventional invasive diagnostic techniques. This advantage aligns with veterinarians’ growing emphasis on animal welfare and biosecurity measures, particularly in large-scale commercial farming operations where rapid and frequent health assessments are critical.

AI TechX’s role as a strategic funding and collaborative platform underscores the increasing recognition of AI’s transformative potential across traditional industries. By bridging academia and industry, AI TechX facilitates resource sharing, accelerates translational research, and nurtures workforce development tailored to meet emerging demands in AI-powered agriculture and biosensing technologies.

The UTIA’s involvement ensures that this research remains grounded in real-world agricultural needs, benefiting from its extensive expertise across the Herbert College of Agriculture, UT College of Veterinary Medicine, UT AgResearch, and UT Extension services. This holistic approach emphasizes the land-grant mission’s core tenets of teaching, research, and outreach, promising Real. Life. Solutions. that resonate with Tennessee’s agricultural stakeholders and serve as a model nationwide.

In summary, the UTIA and EnSenSys partnership supported by the AI TechX Seed Fund represents a visionary step toward integrating artificial intelligence and hyperspectral imaging in livestock health management. The resulting biosensing tools have the potential to revolutionize disease screening protocols, enhance food security, and usher in a new era of precision animal agriculture. As the project progresses from concept to field deployment, it stands to become a landmark example of how cutting-edge science can address vital challenges in sustainable farming and veterinary diagnostics.

Subject of Research: Rapid identification of infectious diseases in cattle using AI and hyperspectral imaging.

Article Title: University of Tennessee and EnSenSys Forge AI-Powered Biosensing Tools for Livestock Disease Detection.

News Publication Date: June 11, 2025.

Image Credits: Photo courtesy Enterprise Sensor Systems LLC.

Keywords: Agriculture, Computer Science, Applied Sciences and Engineering, Technology, Spectroscopy, Engineering.

Published in the prestigious journal Plant Disease, the study led by researchers from the USDA Agricultural Research Service in collaboration with Cornell University employed sophisticated data mining techniques in public genetic databases. By reanalyzing archived plant samples and genetic sequences, the team revealed clear viral footprints that predate CLRDV’s official detection by over a decade. This breakthrough demonstrates how leveraging existing biological data can expose hidden threats before they become widespread crises.

CLRDV, a member of the genus Polerovirus, is known to cause severe leafroll symptoms and dwarfing in cotton, significantly affecting yield and fiber quality. The disease was first officially detected in the U.S. in 2017, leading to concerns about its rapid emergence. However, the retrospective genomic analysis conducted by the team identified viral sequences in cotton samples from Mississippi dating back to 2006, alongside later occurrences in Louisiana (2015) and California (2018). These findings necessitate a reevaluation of CLRDV’s epidemiology in the U.S. Cotton Belt.

Adding to the urgency is the 2023 field survey conducted in Southern California by the research group, which confirmed the current presence of CLRDV in the region. This report marks California’s first verified documentation of the virus, indicating that CLRDV has established itself far beyond its previously understood range. The spatial expansion of this virus underscores the challenges faced by cotton producers in controlling viral pathogens amidst changing environmental and agricultural landscapes.

The study’s methodology highlights the power of bioinformatics in modern plant pathology. By mining genetic repositories and cross-referencing viral sequences, the researchers reconstructed a more comprehensive timeline of CLRDV’s introduction and dissemination within the United States. This approach also reveals the potential of public, accessible databases as crucial tools in emergent pathogen surveillance, enabling scientists to uncover latent threats hidden within existing data.

One particularly surprising dimension of the research was the identification of CLRDV genetic material in the gut content of a cow sampled in California. This finding, though not indicative of infection in the animal, suggests ingestion of virus-contaminated plant material, likely derived from infected cotton byproducts used in feed. This insight extends the ecological context of CLRDV and raises new questions about virus persistence and movement through agricultural systems.

Beyond merely redefining CLRDV’s timeline, the study probes deeper into longstanding agricultural puzzles — most notably, the enigmatic bronze wilt disease in cotton. The presence of CLRDV offers a plausible viral explanation for bronze wilt symptoms, which have been a source of debate in cotton pathology for years. Linking CLRDV to bronze wilt could revolutionize both diagnostic frameworks and management practices, providing a clearer path toward mitigating crop losses associated with this complex symptomatology.

Experts emphasize the critical implications for growers and agricultural stakeholders. Dr. Michelle Heck, a lead scientist on the project, warns that the virus’s historical invisibility should not breed complacency. Instead, understanding why CLRDV remained undetected for so long — despite its apparent widespread distribution — is vital in shaping future disease monitoring and intervention strategies. As the virus’s impact may be underreported, enhanced surveillance and integrated pest management approaches become all the more essential.

This research exemplifies the convergence of plant pathology, molecular biology, and data science, demonstrating how interdisciplinary strategies can unearth hidden biological signals to protect vital agricultural resources. The capacity to retrospectively analyze data transforms our ability to respond proactively to emerging phytopathogens, offering a model for combating viral diseases in other crops and geographic regions.

Looking forward, the study encourages investment in plant health infrastructure and database curation to sustain the efficacy of this modern disease detective work. The ability to detect pathogens hidden within "dark matter" of historical samples affords scientists and policymakers a powerful edge. It calls for global collaboration to build comprehensive, easily searchable repositories to facilitate rapid response in plant health crises.

Ultimately, the revelation of CLRDV’s long-standing presence in U.S. cotton fields is a wake-up call, illustrating that some of the most damaging threats to agriculture may be quietly festering out of sight. The use of bioinformatics and data mining not only rewrites the virus’s history but also charts a proactive path toward safeguarding crop health and ensuring food and fiber security against insidious viral adversaries.

The insights generated from this study set a new standard for the role of open data in plant disease epidemiology, highlighting the untapped insights locked away in archived collections and public datasets. As plant viruses remain a significant threat worldwide, this pioneering work underscores the importance of continual vigilance and innovation, from laboratory benches to cotton fields stretching across continents.

Subject of Research: Cotton leafroll dwarf virus (CLRDV) presence and historical spread in U.S. cotton fields.

Article Title: Data Mining Redefines the Timeline and Geographic Spread of Cotton Leafroll Dwarf Virus

News Publication Date: 20-May-2025

Web References:
https://doi.org/10.1094/PDIS-06-24-1265-SC

References:
Olmedo-Velarde, A., Heck, M., et al. "Data Mining Redefines the Timeline and Geographic Spread of Cotton Leafroll Dwarf Virus." Plant Disease, 20 May 2025. DOI: 10.1094/PDIS-06-24-1265-SC

Image Credits:
Courtesy of Alejandro Olmedo-Velarde and Michelle Heck — © 2025 The American Phytopathological Society.

Keywords:
Cotton, Plant pathology, Virology, Pathogens, Microorganisms, South America, North America, Farming, Sustainable agriculture, Data mining

Striga, commonly referred to as witchweed, is a significant agricultural menace that inflicts severe damage on crops worldwide. This parasitic species is particularly notorious in Africa, where it infests over 50 million hectares of farmland, resulting in annual economic losses estimated at $1.5 billion. It poses a direct threat to over 300 million people who rely on agriculture for sustenance. In regions such as Guangdong and Yunnan in China, Striga has emerged as a growing concern for farmers. The presence of Orobanche, another type of parasitic plant, compounds the threat against vital crops like sunflowers and tomatoes across various northern provinces of China.

Sorghum, a crop that plays a crucial role in food security, is one of the plants vulnerable to Striga infestation. The roots of sorghum release signals known as strigolactones, which serve a dual purpose of aiding the plant in recruiting mycorrhizal fungi for enhanced nutrient uptake while simultaneously attracting Striga seeds from the soil. This recruitment mechanism, however, inadvertently leads to Striga germination, facilitating its infection and subsequent extraction of nutrients from the sorghum plant, thereby undermining crop yield and farmer livelihoods.

In the pursuit of unraveling the genetic basis of sorghum’s susceptibility to Striga, the researchers employed a meticulous analysis of transcriptome data derived from sorghum roots. This analysis was conducted under conditions of phosphorus deficiency and strigolactone treatment. Through this innovative approach, the scientists successfully identified two members of the ABCG family of SL transporter genes, namely Sorghum bicolor SL transporter 1 (SbSLT1) and Sorghum bicolor SL transporter 2 (SbSLT2). These genes were found to encode proteins that play an essential role in regulating the efflux of strigolactones from the sorghum roots.

The groundbreaking discovery that knocking out the SbSLT1 and SbSLT2 genes hinders the secretion of strigolactones has profound implications for Striga control. With the reduction in strigolactones, Striga seeds are unable to detect the signals necessary for their germination. Consequently, plants that lack these specific transporters present a formidable resistance to Striga, representing a potential solution to one of agriculture’s most pressing challenges.

Further investigation utilizing artificial intelligence revealed a conserved phenylalanine residue critical to the transport function within the SL transporters. This residue was found to be present not only in sorghum but also in key SL transporters across other monocotyledonous species such as maize, rice, and millet, as well as in dicot crops like sunflowers and tomatoes. The conservation of this amino acid hints at a uniform mechanism across diverse plant species, suggesting that strategies developed from this research could be applicable to a broad range of crops affected by similar parasitic threats.

To validate their findings, the research team conducted field trials in areas prone to Striga infestation. Remarkably, the results showed that sorghum plants with disrupted SbSLT1 and SbSLT2 genes registered infestation rates that were markedly lower, between 67% to 94%, compared to their wild-type counterparts. Additionally, these engineered varieties experienced a significant reduction in yield loss, ranging from 49% to 52%. These impressive results not only underscore the potential for developing Striga-resistant sorghum varieties but also provide a blueprint for breeders seeking to enhance crop resilience against parasitic plants.

The implications of these findings extend beyond individual crops. As food security becomes an increasingly pressing global concern, particularly in regions heavily afflicted by agricultural pests such as Striga, the identification of genes like SbSLT1 and SbSLT2 present valuable genetic resources for breeding programs. The research emphasizes the urgent need for innovation in combating parasitic threats, which can significantly hinder food production and disrupt ecological systems.

In their conclusions, the researchers expressed hopes that the identification of the SbSLT1 and SbSLT2 transporters could serve as a foundation for developing comprehensive strategies to combat parasitic plants. Such advancements are especially crucial for African and Asian nations where agricultural stability can directly affect regional peace and socio-economic conditions. Collaborative efforts among geneticists, agronomists, and technology experts will be essential as future research seeks to validate the role of these genes in other economically important crops like maize, tomato, and millet.

With climate change and population growth continuing to exert pressure on agricultural systems, addressing the challenges posed by parasitic plants like Striga is more critical than ever. The research led by Prof. XIE Qi is a promising step in the right direction, paving the way for enhanced agricultural practices that could lead to improved crop yields and food security on a global scale.

Importantly, the research team recognizes the importance of interdisciplinary partnerships, calling for future initiatives that leverage genetics, biotechnology, and genomic studies to devise crop varieties that are inherently resistant to parasitic threats. It is a call to action for the global scientific community to collaborate in finding sustainable solutions to agricultural challenges that threaten to undermine food systems worldwide.

In light of these developments, stakeholders across the agricultural sector are urged to pay close attention to advancements in plant genetics. Breeding for resistances harnesses both traditional techniques and modern genomic tools, providing a dual approach to mitigate risks posed by parasitic plants. As knowledge expands and more genetic pathways are discovered, the collective effort could result in a transformative impact on global agriculture, protecting not just sorghum but a multitude of crops from the clutches of parasitism.

This remarkable study represents a synthesis of innovation, collaboration, and applied science, demonstrating that the fight against agricultural parasitism can truly be supported by a combination of cutting-edge research and an understanding of fundamental plant biology. The journey ahead promises to be as significant as the discovery itself, offering hope for farmers worldwide and a pathway toward enhanced resilience in our food systems.

Subject of Research: Cells
Article Title: Resistance to Striga Parasitism through Reduction of Strigolactone Exudation
News Publication Date: 12-Feb-2025
Web References: Link to Article
References: N/A
Image Credits: Credit: XIE Qi
Keywords: Sorghum, Parasitism, Developmental genetics, Gene identification, Crop yields