EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Screening and dynamic change study of microbial and metabolite markers for calf diarrhea based on multi-omics and machine learning

Xitong Yin iD, Yanlong Niu, Baoxia Chen, Hao Zhang, Rongxia Guo, Chun Niu, Jianguo Kang, Hongmei Shi, Xiangying Kong, Weidong Ma, Zhongfa Ma, Yanming Wei und 1 weitere

mSystems · 19.05.2026 · 11 (5)

DOI: 10.1128/msystems.00005-26 ↗

Kurz gefasst

Fachartikel in der Zeitschrift mSystems, erschienen am 19.05.2026. Verfasst von Xitong Yin und 12 weiteren Autor:innen. Beteiligte Einrichtung: College of Veterinary Medicine, Gansu Agricultural University, Lanzhou, China. Hauptthemen laut MEDLINE: Machine Learning, Diarrhea, Cattle Diseases, Gastrointestinal Microbiome. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neonatal calf diarrhea is a leading cause of calf mortality and substantial economic loss in the livestock industry, yet the dynamic microbial and metabolic signatures accompanying disease onset remain poorly defined. Here, we integrated 16S rRNA high-throughput sequencing, untargeted metabolomics, and machine learning approaches to longitudinally profile fecal samples from neonatal calves at 0, 5, 10, 15, and 20 days of age. Diarrheic calves exhibited significantly reduced gut microbial α-diversity, as indicated by lower Chao1 richness and Shannon index compared with healthy counterparts. At the genus level, Tyzzerella and Fusobacterium emerged as core differential taxa associated with diarrhea and were further validated as robust biomarkers using an XGBoost predictive model. Metabolomic analysis showed that differential metabolites were mainly enriched in pathways including the phosphotransferase system. Notably, dulcitol, N-acetylmuramate, and D-fructose were highlighted as potential contributors to diarrhea, possibly through modulating intestinal osmolality and inflammatory responses. Pearson correlation analysis revealed significant associations between Tyzzerella/Fusobacterium and key metabolites, suggesting coordinated microbe–metabolite interactions during disease progression. Temporal pattern analysis identified an early-life signal: a high abundance of Escherichia–Shigella at birth may act as an important trigger for subsequent diarrhea. In addition, several metabolites displayed distinct age-dependent trajectories, indicating their potential as time-resolved metabolic biomarkers. Collectively, this study delineates dynamic shifts in the gut microbiome and metabolome during neonatal calf diarrhea, identifies Tyzzerella and Fusobacterium , together with characteristic metabolites such as dulcitol and N-acetylmuramate, as candidate biomarkers, and provides a high-performance predictive framework to support early diagnosis and targeted microbiota-based interventions. IMPORTANCE Neonatal calf diarrhea causes substantial early-life mortality and economic losses, yet the dynamic microbiota–metabolite alterations and early-warning biomarkers during disease onset remain poorly defined. Here, we longitudinally profiled fecal microbiota and metabolites in calves from birth to day 20 and integrated machine learning approaches to systematically characterize diarrhea-associated signatures. Diarrheic calves showed reduced α-diversity, and Tyzzerella and Fusobacterium emerged as core differential genera with predictive value validated using an XGBoost model. Differential metabolites were mainly enriched in pathways such as the phosphotransferase system (PTS), and dulcitol and N-acetylmuramate may contribute to diarrhea by modulating intestinal osmolality or inflammatory responses. Notably, a higher abundance of Escherichia–Shigella at birth was potentially associated with subsequent diarrhea risk, while L-glutamic acid, choline, and LysoPC exhibited distinct temporal trajectories. Collectively, these findings provide translational candidate biomarkers to support early warning and microbiota-targeted precision interventions for neonatal calf diarrhea.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningDiarrheaCattle DiseasesGastrointestinal MicrobiomeAnimalsCattleMultiomicsBiomarkersFecesMetabolomicsAnimals, NewbornRNA, Ribosomal, 16SMetabolomeBacteria

Stichwörter der Autor:innen

calf diarrheamachine learningmetabolismmicroorganisms

Substanzen

BiomarkersRNA, Ribosomal, 16S

Autor:innen und Institutionen

  • College of Veterinary Medicine, Gansu Agricultural University, Lanzhou, China.
  • Gansu Gannan Animal Husbandry and Veterinary Workstation, Gannan, China.
  • Qinghai Haibei Animal Husbandry and Veterinary Science Research Institute, Haibei, China.
  • Shaanxi Agricultural and Animal Husbandry Breeding Farm, Baoji, China.
  • Gansu Xin Gaoyuan Agriculture and Animal Husbandry Development Co., Ltd., Lanzhou, China.

ORCID-Profile: Xitong Yin, Yongli Hua

Zitieren

APA

Yin, X., Niu, Y., Chen, B., Zhang, H., Guo, R., Niu, C., Kang, J., Shi, H., Kong, X., Ma, W., Ma, Z., Wei, Y., & Hua, Y. (2026). Screening and dynamic change study of microbial and metabolite markers for calf diarrhea based on multi-omics and machine learning. mSystems, 11(5). https://doi.org/10.1128/msystems.00005-26

Vancouver

Yin X, Niu Y, Chen B, Zhang H, Guo R, Niu C, et al. Screening and dynamic change study of microbial and metabolite markers for calf diarrhea based on multi-omics and machine learning. mSystems. 2026;11(5). doi:10.1128/msystems.00005-26

BibTeX
@article{Yin2026,
  author = {Yin, Xitong and Niu, Yanlong and Chen, Baoxia and Zhang, Hao and Guo, Rongxia and Niu, Chun and Kang, Jianguo and Shi, Hongmei and Kong, Xiangying and Ma, Weidong and Ma, Zhongfa and Wei, Yanming and Hua, Yongli},
  title = {Screening and dynamic change study of microbial and metabolite markers for calf diarrhea based on multi-omics and machine learning},
  journal = {mSystems},
  year = {2026},
  volume = {11},
  number = {5},
  doi = {10.1128/msystems.00005-26}
}
Kostenlos starten →