Abstract Background Cancer progression and patient survival are influenced by both tumor-intrinsic and microenvironmental factors, including the ability of tumor cells to disseminate and colonize distant organs. Organ-specific metastases, particularly brain metastases (BM), exhibit distinct tumor–microenvironment interactions, therapeutic responses, and clinical outcomes. Integrating metastatic genomic alterations into survival modeling is essential for improving prognostic accuracy. Here, we present an optimized machine learning framework leveraging genomic mutations and copy number variations to predict overall survival (OS) in BM patients. Methods We implemented a rigorous machine learning pipeline for survival prediction. The dataset was randomly divided into training (70%) and independent test (30%) cohorts. Feature selection, model training, and hyperparameter optimization were performed exclusively within the training set. Prognostic features were initially identified using univariable Cox regression (p < 0.05) and refined using machine learning–based selection, retaining features consistently selected across multiple models. Hyperparameters were optimized via 3-fold cross-validation. Model performance was evaluated using the concordance index (C-index) and time-dependent AUC, while Kaplan–Meier analysis assessed risk stratification. Results The cohort comprised 381 BM patients, primarily from lung cancer (51.1%), followed by melanoma (15.2%) and breast cancer (7.9%). Key prognostic features included recurrent single-nucleotide variants in genes such as PTPRT, ARID1A, PREX2, and FAT1. Ridge regression demonstrated the best performance, achieving a C-index of 0.70 in the test cohort. Time-dependent analyses showed AUCs of 0.642, 0.711, and 0.729 at 1, 2, and 3 years, respectively. The model achieved significant risk stratification (HR = 3.45, p < 0.001), with clear separation between predicted risk groups. Conclusions We developed a robust machine learning framework integrating genomic mutations and copy number alterations to predict survival in BM patients. The model demonstrated stable performance and effective risk stratification in an independent cohort, supporting its potential clinical utility for prognostic assessment and precision oncology applications.
M. I. Ali, Z. Majeed, Peng Li et al.· Neuro-Oncology Advances· 0 citations
Abstract Background Brain metastasis (BM) in renal cell carcinoma (RCC) remains a major clinical challenge and is frequently resistant to immune checkpoint inhibitor (ICI) therapy. The metabolic and immunological adaptations enabling tumor survival within the brain microenvironment remain poorly defined. A comprehensive, brain-specific characterization of the tumor–microenvironment is needed to understand immune dysfunction and therapeutic resistance in RCC BM. Methods We generated a large single-nucleus RNA sequencing dataset comprising 184,037 nuclei from 14 RCC BM patients, including matched primary kidney tumors (n = 8) and extracranial metastases (n = 5). Cell populations were identified across tumor, immune, and stromal compartments. Comparative analyses identified BM-specific transcriptional, metabolic, and immune programs. Spatial transcriptomic profiling was conducted on 12 BM samples (13,128 cells) to validate cellular localization and interactions. Ligand–receptor inference was applied to reconstruct intercellular communication. Results RCC BM is associated with extensive immune remodeling of the brain microenvironment and stromal involvement. Tumor cells show neural-like features with evidence of neuroglial cells infiltration, while stromal populations display immunomodulatory phenotypes beyond structural roles. This landscape includes expansion of immunosuppressive myeloid populations, depletion of dendritic cells, absence of tertiary lymphoid structures, and CD8+ T cells exhibiting terminal exhaustion. Across compartments, we observed coordinated metabolic shifts, including enhanced OXPHOS and MYC-associated programs. Spatial and ligand–receptor analyses confirmed interactions providing mechanistic insight and informing therapeutic targeting. Conclusion RCC BM represents a biologically distinct tumor entity shaped by neural adaptation, metabolic reprogramming, and immune dysfunction. Immunosuppressive myeloid signaling, T cell exhaustion, and impaired antigen presentation establish a brain-specific microenvironment limiting immune checkpoint efficacy. These findings highlight context-dependent resistance mechanisms and identify actionable pathways to guide brain-tailored immunotherapy. Importantly, this work supported clinical trials approval testing lenvatinib plus pembrolizumab and zanzalitinib in RCC BM patients.
M. I. Ali, Z. Akpinar, Jose A. Ovando-Ricardez et al.· Neuro-Oncology Advances· 0 citations