Integrating mitochondrial and lysosomal gene analysis for breast cancer prognosis using machine learning.

The impact of mitochondrial and lysosomal co-dysfunction on breast cancer patient outcomes is unclear. The objective of this study is to develop a predictive machine learning (ML) model utilizing mitochondrial and lysosomal co-regulators in order to provide a foundation for future studies focused on breast cancer (BC) patients' stratification and personalized interventions. Firstly, Differences and correlations of mitochondrial and lysosome related genes were screened and validated by differential analysis, copy number variation (CNV), single nucleotide polymorphism (SNPs) and correlation analysis. WGCNA and univariate Cox regression were employed to identify prognostic mitochondrial and lysosomal co-regulators. ML was utilized to further selected these regulators and then the coxboost + Survivor-SVM model was identified as the most suitable model for predicting outcomes in BC patients. Subsequently, the association between the immune and mlMSGs score was investigated through scRNA-seq. We found that the overall immunoinfiltration of immune cells was decreased in the high-risk group, it was specifically noted that B cell mlMSGs activity remained diminished in high-risk patients. Finally, the expression and function of the key gene SHMT2 were confirmed through in vitro experiments. This study shows that the ML model demonstrated a strong association with patient outcomes. Analysis conducted through the model has identified decreased B-cell immune infiltration and increased mlMSGs activity as significant factors influencing patient prognosis. These results may offer novel approaches for early intervention and prognostic forecasting in BC.