Machine learning-enhanced assessment of potential probiotics from healthy calves for the treatment of neonatal calf diarrhea

Front Microbiol. 2024 Dec 9:15:1507537. doi: 10.3389/fmicb.2024.1507537. eCollection 2024.

Abstract

Neonatal calf diarrhea (NCD) remains a significant contributor to calf mortality within the first 3 weeks of life, prompting widespread antibiotic use with associated concerns about antimicrobial resistance and disruption of the calf gut microbiota. Recent research exploring NCD treatments targeting gut microbiota dysbiosis has highlighted probiotic supplementation as a promising and safe strategy for gut homeostasis. However, varying treatment outcomes across studies suggest the need for efficient treatment options. In this study, we evaluated the potential of probiotics Limosilactobacillus reuteri, formally known as Lactobacillus reuteri, isolated from healthy neonatal calves to treat NCD. Through in silico whole genome analysis and in vitro assays, we identified nine L. reuteri strains, which were then administered to calves with NCD. Calves treated with L. reuteri strains shed healthy feces and demonstrated restored gut microbiota and normal animal behavior. Leveraging a machine learning model, we evaluated microbiota profiles and identified bacterial taxa associated with calf gut health that were elevated by L. reuteri administration. These findings represent a crucial advancement towards sustainable antibiotic alternatives for managing NCD, contributing significantly to global efforts in mitigating antimicrobial resistance and promoting overall animal health and welfare.

Keywords: gut microbiome; host specificity; machine learning; neonatal calf diarrhea; probiotics.

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. This work was supported by the National Institute of Food and Agriculture, U.S. Department of Agriculture (2015-68003-22971 and 2019-67021-29858 to KJ and 2021-67015-35034 to KG), the Bennink Foundation to KJ (F028417), and National Science Foundation to CB (SCH:2013998).