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

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 <i>APOA1</i>, <i>ACTB</i>, <i>S1PR1</i>, <i>PKLR</i>, and <i>SLC27A6</i> 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.

Authors

Institutions

Publication Details

Journal
International Journal of Molecular Sciences
Published
2025-05-23
DOI
https://doi.org/10.3390/ijms26115046
Citations
2
Primary Topic
Muscle Physiology and Disorders
Type
article
Field-Weighted Citation Impact
1.61

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Mingjuan Gu, Caixia Shi, Shuai Li, Wenguang Zhang et al.
2 citations
International Journal of Molecular Sciences
Muscle Physiology and Disorders
1.61
article

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

Mingjuan Gu, Caixia Shi, Shuai Li, Wenguang Zhang, Lin Zhu, Risu Na, Chenxi Huo, Yaqiang Guo
article en
2 citations

Abstract

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 <i>APOA1</i>, <i>ACTB</i>, <i>S1PR1</i>, <i>PKLR</i>, and <i>SLC27A6</i> 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.

International Journal of Molecular SciencesVol. 26(11)
Inner Mongolia Agricultural University (CN), Inner Mongolia Electric Power Survey & Design Institute (China) (CN)
Natural Science Foundation of Inner Mongolia, Inner Mongolia Agricultural University
Openalex Percentile: Top 17%
Muscle Physiology and Disorders
1.61
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.