LATEST IN SCIENCE

Abstract: Immunosenescence increases susceptibility to infection and reduces vaccine responsiveness, yet bulk transcriptomic clocks obscure the cellular heterogeneity underlying this process. Here, we present IDEAL-Age, an interpretable deep learning framework that operates directly on single-cell PBMC transcriptomes. Benchmarking against 35 methods across independent cohorts demonstrates superior predictive performance. The framework's interpretability uncovers linear and non-linear gene contribution trajectories that reveal phase-specific physiological transitions, and identifies youth-associated or aging-associated cellular roles. Application to systemic lupus erythematosus reveals accelerated immunological aging driven by interferon-associated monocyte shifts. IDEAL-Age establishes a high-resolution computational framework for deciphering systemic immune aging.

Abstract: Extracellular vesicles (EVs) are nanoscale, membrane-bound particles that transport diverse biomolecules-including proteins, nucleic acids, lipids, and metabolites-between cells, thereby orchestrating key processes in cancer progression. Tumor-derived EVs modulate angiogenesis, epithelial-to-mesenchymal transition, extracellular matrix remodeling, fibroblast activation, and immune evasion, shaping the tumor microenvironment, and driving metastasis as well as therapy resistance. With their stability in biofluids and cargo reflective of cellular origin, EVs have emerged as powerful non-invasive biomarkers for early detection, disease monitoring, and prognosis across multiple cancer types. Recent advances in enrichment, characterization, and molecular profiling technologies-ranging from ultracentrifugation and microfluidics to proteomics, RNA sequencing, and surface-enhanced Raman spectroscopy, have greatly expanded the diagnostic potential of EVs. Integration with machine learning further enhances sensitivity, specificity, and tumor classification, while multiomic and multiplex platforms enable high-throughput and clinically relevant applications. This review highlights the multifaceted roles of EVs in cancer biology, catalogs emerging biomarkers, and compares state-of-the-art detection technologies, offering a comprehensive reference for advancing EV-based diagnostics and precision oncology.