Enhancing breast cancer outcomes with machine learning-driven glutamine metabolic reprogramming signature.

Background: This study aims to identify precise biomarkers for breast cancer to improve patient outcomes, addressing the limitations of traditional staging in predicting treatment responses. Methods: Our analysis encompassed data from over 7,000 breast cancer patients across 14 datasets, which included in-house clinical data and single-cell data from 8 patients (totaling 43,766 cells). We utilized an integrative approach, applying 10 machine learning algorithms in 54 unique combinations to analyze 100 existing breast cancer signatures. Immunohistochemistry assays were performed for empirical validation. The study also investigated potential immunotherapies and chemotherapies. Results: Our research identified five consistent glutamine metabolic reprogramming (GMR)-related genes from multi-center cohorts, forming the foundation of a novel GMR-model. This model demonstrated superior accuracy in predicting recurrence and mortality risks compared to existing clinical and molecular features. Patients classified as high-risk by the model exhibited poorer outcomes. IHC validation in 30 patients reinforced these findings, suggesting the model's broad applicability. Intriguingly, the model indicates a differential therapeutic response: low-risk patients may benefit more from immunotherapy, whereas high-risk patients showed sensitivity to specific chemotherapies like BI-2536 and ispinesib. Conclusions: The GMR-model marks a significant leap forward in breast cancer prognosis and the personalization of treatment strategies, offering vital insights for the effective management of diverse breast cancer patient populations.

Endoplasmic reticulum stress in breast cancer: a predictive model for prognosis and therapy selection.

Background: Breast cancer (BC) is a leading cause of mortality among women, underscoring the urgent need for improved therapeutic predictio. Developing a precise prognostic model is crucial. The role of Endoplasmic Reticulum Stress (ERS) in cancer suggests its potential as a critical factor in BC development and progression, highlighting the importance of precise prognostic models for tailored treatment strategies. Methods: Through comprehensive analysis of ERS-related gene expression in BC, utilizing both single-cell and bulk sequencing data from varied BC subtypes, we identified eight key ERS-related genes. LASSO regression and machine learning techniques were employed to construct a prognostic model, validated across multiple datasets and compared with existing models for its predictive accuracy. Results: The developed ERS-model categorizes BC patients into distinct risk groups with significant differences in clinical prognosis, confirmed by robust ROC, DCA, and KM analyses. The model forecasts survival rates with high precision, revealing distinct immune infiltration patterns and treatment responsiveness between risk groups. Notably, we discovered six druggable targets and validated Methotrexate and Gemcitabine as effective agents for high-risk BC treatment, based on their sensitivity profiles and potential for addressing the lack of active targets in BC. Conclusion: Our study advances BC research by establishing a significant link between ERS and BC prognosis at both the molecular and cellular levels. By stratifying patients into risk-defined groups, we unveil disparities in immune cell infiltration and drug response, guiding personalized treatment. The identification of potential drug targets and therapeutic agents opens new avenues for targeted interventions, promising to enhance outcomes for high-risk BC patients and paving the way for personalized cancer therapy.

Integrating PANoptosis insights to enhance breast cancer prognosis and therapeutic decision-making.

Background: Despite advancements, breast cancer outcomes remain stagnant, highlighting the need for precise biomarkers in precision medicine. Traditional TNM staging is insufficient for identifying patients who will respond well to treatment. Methods: Our study involved over 6,900 breast cancer patients from 14 datasets, including in-house clinical data and single-cell data from 8 patients (37,451 cells). We integrated 10 machine learning algorithms in 55 combinations and analyzed 100 existing breast cancer signatures. IHC assays were conducted for validation, and potential immunotherapies and chemotherapies were explored. Results: We pinpointed six stable Panoptosis-related genes from multi-center cohorts, leading to a robust Panoptosis-model. This model outperformed existing clinical and molecular features in predicting recurrence and mortality risks, with high-risk patients showing worse outcomes. IHC validation from 30 patients confirmed our findings, indicating the model's broader applicability. Additionally, the model suggested that low-risk patients benefit more from immunotherapy, while high-risk patients are sensitive to specific chemotherapies like BI-2536 and ispinesib. Conclusion: The Panoptosis-model represents a major advancement in breast cancer prognosis and treatment personalization, offering significant insights for effectively managing a wide range of breast cancer patients.