This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Deciphering the Gene Expression and Alternative Splicing Basis of Muscle Development Through Interpretable Machine Learning Models
by
, ,
Xiaodong Tan
1,2,†
,
Minjie Huang
1,2,†,
Yuting Jin
1,2,
Jiahua Li
1,2,
Jie Dong
1,2,* and
Deqian Wang
1,2,* 1
Institute of Animal Husbandry and Veterinary Science, Zhejiang Academy of Agricultural Sciences, Hangzhou 310021, China
2
Key Laboratory of Livestock and Poultry Resources (Poultry) Evaluation and Utilization, Ministry of Agriculture and Rural Affairs, Hangzhou 310021, China
*
Authors to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Biology 2025, 14(8), 1059; https://doi.org/10.3390/biology14081059
Submission received: 3 July 2025
/
Revised: 9 August 2025
/
Accepted: 12 August 2025
/
Published: 15 August 2025
(This article belongs to the Section Bioinformatics)
Simple Summary
Chicken is the most consumed meat globally and represents the most cost-effective protein source. Enhancing chicken production is crucial for ensuring food supply and security. While large-scale expansion of farming significantly increases environmental burdens, selective breeding employing molecular biology and genetics is the most efficient and vital approach. In this study, we investigated local chicken breeds (Xianju chicken) and commercial broilers. We identified genes and regulatory mechanisms differentiating high and low breast muscle weight. Combining these findings with machine learning methods revealed that these genes exhibit high accuracy in predicting meat production performance. Our findings provide important targets for chicken genomic selection and design breeding, enabling the improvement of chicken meat production efficiency through specific combinations.
Abstract
In chickens, meat yield is a crucial trait in breeding programs. Identifying key molecular markers associated with increased muscle yield is essential for breeding strategies. This study applied transcriptome sequencing and machine learning methods to examine gene expression and alternative splicing (AS) events in muscle tissues of commercial broilers and local chickens. On the basis of differentially expressed genes (DEGs) and differentially spliced transcripts (DSTs) significantly related to breast muscle weight percentage (BrP), high-accuracy prediction models were developed by evaluating 10 machine learning models (e.g., eXtreme Gradient Boosting (XGBoost), Generalized Linear Model Network (Glmnet)). Feature importance was assessed using the Shapley Additive exPlanations (SHAP) method. The results revealed that 50 DEGs and 95 DSTs contributed significantly to BrP prediction. The XGBoost model achieved over 90% accuracy when using DEGs, and the Glmnet model reached 95% accuracy when using DSTs. Through Shapley evaluation, genes and AS events (e.g., ENSGALG00010012060, HINTW, and VIPR2-201) were identified as having the highest contributions to BrP prediction. Additionally, the breed effect was effectively mitigated. This study introduces new candidate genes and AS targets for the molecular breeding of poultry breast muscle traits, offering a paradigm shift from traditional gene mining approaches to artificial intelligence-driven predictive methods.
