An official website of the United States government.

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Monitoring the gut microbiome via AI and omics: a new approach to detect infection and AMR and to support novel therapeutics in broiler precision farm


Research on precision livestock farming has been increasingly recognising the importance of studying the gut microbiome, resistome and its metabolites, as an invaluable source of information in relation to animal health and welfare. The population of gut microbiota changes in complex ways, as a consequence of external factors (environment, feed, etc.), but also as a consequence of infection, co-infection, diseases, and therapeutics. In recent work on diseases and antimicrobial resistance (AMR) in broiler farming, we demonstrated that valuable information can be extracted from the bird gut microbiome. Through the development of a custom data mining method based on machine learning (ML), we uncovered evidence of correlations between gut metagenome modifications (metagenome and composition of the microbial community), environmental variables (temperature and humidity) and the likelihood of finding antimicrobial resistance (AMR) in reference pathogens within the farm (E. coli). We discovered evidence of resistance traits shared by birds, environments, and produced meat, and isolated hot-spots where infections and resistances tend to concentrate the most within the farm. In this project, we plan to improve our ML methods to include a much larger set of variables. Within the gut, the metabolome and the possible co-presence of viruses and parasites. Within the farm, illumination and air composition, and data from optical/IR imaging and acoustic sensing. Genomics and metagenomics on many additional types of biological samples (barn floors, operator boots, drinking water, dust, air, water reservoir) will be included. Another novelty aspect will be the development of cloud-based surveillance systems. Technical innovations will be the adoption of cloud services to relieve farms from the burdens of computing and data storage, and the use of digital twins (from Industry 4.0) to support remote surveillance AI, with simple messaging sent back to the farmers.

Dr Tania Dottorini; Dr Michelle Baker, Dr Dong-Hyun Kim, Professor Matthew Loose
University of Nottingham
Start date
End date
Project number