EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Machine Learning-Based Analysis of Differentially Expressed Genes in the Muscle Transcriptome Between Beef Cattle and Dairy Cattle

Shuai Li iD, Yaqiang Guo iD, Chenxi Huo iD, Lin Zhu, Caixia Shi, Risu Na, Mingjuan Gu iD, Wenguang Zhang

International Journal of Molecular Sciences · 2025

DOI: 10.3390/ijms26115046 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2025. Verfasst von Shuai Li und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Animal Science, Inner Mongolia Agricultural University, Hohhot 010010, China. Hauptthemen laut MEDLINE: Machine Learning, Transcriptome, Gene Expression Profiling, Muscle, Skeletal. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Natural Science Foundation of Inner Mongolia,the Technology Plan Project in Inner Mongolia Autonomous Region,the Inner Mongolia Open Competition Projects,T…, Natural Science Foundation of Inner Mongolia, Technology Plan Project in Inner Mongolia Autonomous Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Muscle is a crucial component of cattle, playing a vital role in determining the final quality of beef. This study aimed to identify candidate genes associated with muscle growth and lipid metabolism in beef and dairy cattle by utilizing the public database of the National Center for Biotechnology Information (NCBI) to download bovine muscle transcriptome data. Through differential expression analysis, weighted gene co-expression network analysis (WGCNA), and SHapley Additive exPlanation (SHAP) explains machine learning models, we integrated and screened for relevant genes. The results showed a total of 2588 differentially expressed genes (DEGs), with 933 upregulated and 1655 downregulated in beef cattle compared to dairy cattle. In the WGCNA, the purple, black, green, red, brown, and blue modules were identified as significant modules. Based on the results of five different machine learning models, the Adaptive Boosting (AdaBoost) model demonstrated superior classification performance (accuracy = 0.84) compared to the other four models and was therefore selected as the optimal model. SHAP analysis was then employed to interpret the results, yielding the top 500 SHAP genes. In combination with DEGs and WGCNA, a total of 117 genes were identified. Subsequent functional enrichment analysis of these 117 genes revealed significant enrichment in pathways such as lipoprotein metabolic process, muscle contraction, and cytoskeleton in muscle cells, followed by interaction network analysis of genes and pathways. Ultimately, the APOA1, ACTB, S1PR1, PKLR, and SLC27A6 genes were identified as potential key regulators of lipid metabolism and muscle growth in beef and dairy cattle. In summary, this study provides a feasible method for handling large-scale transcriptome data and lays a foundation for future research on meat quality and improving the economic benefits of Holstein cattle.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningTranscriptomeGene Expression ProfilingMuscle, SkeletalAnimalsCattleGene Regulatory NetworksLipid MetabolismRed MeatGene Expression Regulation

Stichwörter der Autor:innen

SHAPmachine learningmuscletranscriptome

Autor:innen und Institutionen

  • College of Animal Science, Inner Mongolia Agricultural University, Hohhot 010010, China.
  • Inner Mongolia Engineering Research Center of Genomic Big Data for Agriculture, Hohhot 010010, China.
  • College of Life Science, Inner Mongolia Agricultural University, Hohhot 010010, China.

ORCID-Profile: Shuai Li, Yaqiang Guo, Chenxi Huo, Mingjuan Gu

Förderung

  • the Natural Science Foundation of Inner Mongolia,the Technology Plan Project in Inner Mongolia Autonomous Region,the Inner Mongolia Open Competition Projects,T…
  • Natural Science Foundation of Inner Mongolia
  • Technology Plan Project in Inner Mongolia Autonomous Region
  • Inner Mongolia Open Competition Projects
  • Tongliao City Open Competition Projects
  • College of Animal Science, Inner Mongolia Agricultural University
  • Inner Mongolia Autonomous Region Science and Technology Plan Project

Zitieren

APA

Li, S., Guo, Y., Huo, C., Zhu, L., Shi, C., Na, R., Gu, M., & Zhang, W. (2025). Machine Learning-Based Analysis of Differentially Expressed Genes in the Muscle Transcriptome Between Beef Cattle and Dairy Cattle. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms26115046

Vancouver

Li S, Guo Y, Huo C, Zhu L, Shi C, Na R, et al. Machine Learning-Based Analysis of Differentially Expressed Genes in the Muscle Transcriptome Between Beef Cattle and Dairy Cattle. International Journal of Molecular Sciences. 2025. doi:10.3390/ijms26115046

BibTeX
@article{Li2025,
  author = {Li, Shuai and Guo, Yaqiang and Huo, Chenxi and Zhu, Lin and Shi, Caixia and Na, Risu and Gu, Mingjuan and Zhang, Wenguang},
  title = {Machine Learning-Based Analysis of Differentially Expressed Genes in the Muscle Transcriptome Between Beef Cattle and Dairy Cattle},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  doi = {10.3390/ijms26115046}
}
Kostenlos starten →