Most models of neoadjuvant chemotherapy (NACT) for breast cancer (BC) suffer from insufficient data and lack interpretability. Additionally, there is a notable absence of reports from China in this field. This study is also the first to integrate the Advanced Lung Cancer Inflammation Index (ALI) into such a model to evaluate its effectiveness. Data from 3,036 female BC patients receiving NACT at Heilongjiang Provincial Tumor Hospital (2008-2019, median follow-up 7.28 years) were analyzed. After screening, 2,909 patients were randomized into training and validation cohorts (7:3). Using eXtreme Gradient Boosting (XGBoost), Gradient Boosting Classifier (GBC), Support Vector Machine (SVM) models, and SHapley Additive exPlanations (SHAP), the best predicting pathological complete response (pCR) model was identified, and key features were interpreted. The Least Absolute Shrinkage and Selection Operator (LASSO) Cox algorithm, combined with XGBoost and Random Forest (RF) models, identified 9 overlapping prognostic features, enhancing the nomogram's predictive accuracy for overall survival (OS). Kaplan-Meier (KM) analysis revealed varying prognostic outcomes. The XGBoost model performed best in predicting pCR, with Area Under Curve (AUC) values of 0.88 and 0.72 in the training and validation sets, respectively. SHAP analysis indicated that ER, HER2 status, ALI, and albumin (Alb) level were the four most important features. The prognostic model was also validated by high AUC values in both training and test sets. KM analysis indicated that lower ALI, non-pCR, and triple-negative BC manifested as worse clinical outcomes. However, the adverse impact of ALI on the prognosis of this cohort was mainly reflected in the long-term recurrence outcomes and non-pCR groups. This study is the first to introduce ALI into the prediction model for BC completing NACT and develop a large-sample model based on XGBoost. Owing to the particularity of the indicators, training and validation were conducted on real clinical data.

Ovarian cancer (OC) remains therapeutic challenge due to its complex molecular heterogeneity and therapy-induced adaptive resistance. While non-apoptotic cell death and senescence pathways contribute to tumor evolution and immunosuppression, their integration into predictive models for multi-target drug design and immunotherapy optimization is underexplored. Machine learning was used to identify key genes that governing cell death and senescence (CDS). The resulting Cell Death and Senescence Learning Signature (CDSLS) was validated across multiple OC cohorts (n = 1858) and immunotherapy datasets. Multi-omics analyses, including single-cell RNA sequencing, were used to map the tumor microenvironment and identify conserved therapeutic targets. Functional validation of the hub gene RB1 included in vitro and in vivo experiments to assess its role in senescence, DNA damage, and T-cell activation. Patients with high scores predicting poor survival and immunosuppression. Knocking down RB1 promoted proliferation and suppressed senescence, while overexpression induced senescence, amplified DNA damage signaling, and enhanced CD8+ T cell activation. In vivo, RB1-overexpressing tumors showed restrained growth and elevated immune infiltration. Targeted affinity small molecule compounds (e.g., ZINC001175043471) were predicted using artificial intelligence tools to target RB1. Drug sensitivity analysis linked CDSLS to differential responses to brivanib, azacitidine, and other agents. Our framework supports the use of AI in identifying conserved binding sites, predicting mutational escape, and provide a basis for future analysis for OC.

Background Platelet-related exosomes (PREs) are microparticles secreted by platelets into the bloodstream and are implicated in various cancer processes. This study aims to identify critical genes involved in Breast Cancer (BC)-associated PREs and to evaluate their role in cancer prognosis. PLA2G4A was identified as a key gene through the use of machine learning techniques and various genomic analyses, providing a foundation for precision medicine in BC treatment. Methods Download cancer-related data from databases such as UCSC Xena and ExMdb, use LASSO Cox regression and various machine learning algorithms to screen genes associated with BC survival, and perform functional and pathway enrichment analysis. The expression, immune relevance, diagnostic efficacy, and drug sensitivity of the PLA2G4A gene in pan-cancer and BC were specifically analyzed. The function of PLA2G4A in BC was validated through experiments, and its drug response and molecular docking were predicted using various databases and software tools. Results Machine learning methods and LASSO Cox regression were applied to analyze the relationship between gene expression and BC survival. PLA2G4A was identified as a key gene associated with cancer prognosis, supported by analyses of differential gene expression, survival outcomes, single nucleotide variations (SNVs), and copy number variations (CNVs). Biological pathway analyses through KEGG, GO, and GSEA highlighted PLA2G4A’s involvement in key cancer-related processes. In vitro studies, including cell scratch assays, Transwell migration assays, and EdU proliferation tests, demonstrated that overexpression of PLA2G4A inhibited the proliferation and migration of BC cells. Conclusions PLA2G4A plays a crucial role in the progression of BC, acting as a potential tumor-suppressor gene. The findings support its potential as a prognostic biomarker and further investigation is needed to explore its therapeutic potential in clinical settings.