GuerreroVazquez/muscle_aging_prediction: Muscle Age Prediction v1.0.0 (Thesis Submission)

This release archives the machine learning and differential expression workflow presented in Chapter 2 of the PhD thesis: "Computational approaches for therapeutic target discovery to ameliorate muscle wasting during ageing" (University of Galway, 2025). Key Components: Data Harmonisation: Scripts for batch correction (ComBat) and normalisation of RNA-Seq datasets from the Vastus lateralis. Differential Expression: DESeq2 implementation for Young vs. Middle Age vs. Old comparisons. Machine Learning Models: Training and evaluation pipelines for CatBoost (non-linear) and Ridge Regression (linear) age predictors. Feature Importance: SHAP value analysis to identify personalised gene signatures. Thesis Context: This code enables the reproduction of the results detailed in Section 2.3, including the model performance metrics (Table 2.4) and the core predictive gene signatures (Table 2.6).