Single-cell RNA sequencing (scRNA-seq) reveals cell heterogeneity, with cell clustering playing a key role in identifying cell types and marker genes. Recent advances, especially graph neural networks (GNNs)-based methods, have significantly improved clustering performance. However, the analysis of scRNA-seq data remains challenging due to noise, sparsity, and high dimensionality. Compounding these challenges, GNNs often suffer from over-smoothing, limiting their ability to capture complex biological information. In response, we propose scSiameseClu, a novel Siamese Clustering framework for interpreting single-cell RNA-seq data, comprising of 3 key steps: (1) Dual Augmentation Module, which applies biologically informed perturbations to the gene expression matrix and cell graph relationships to enhance representation robustness; (2) Siamese Fusion Module, which combines cross-correlation refinement and adaptive information fusion to capture complex cellular relationships while mitigating over-smoothing; and (3) Optimal Transport Clustering, which utilizes Sinkhorn distance to efficiently align cluster assignments with predefined proportions while maintaining balance. Comprehensive evaluations on seven real-world datasets demonstrate that scSiameseClu outperforms state-of-the-art methods in single-cell clustering, cell type annotation, and cell type classification, providing a powerful tool for scRNA-seq data interpretation.

Background: Glioblastoma (GBM) is one of the most challenging malignancies in all of neoplasms. These malignancies are associated with unfavorable clinical outcomes and significantly compromised patient wellbeing. The immunological landscape within the tumor microenvironment (TME) plays a critical role in determining GBM prognosis. By mining data from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases and correlating them with immune responses in the TME, genes associated with the immune microenvironment with potential prognostic value were obtained. Method: We selected GSE16011 as the training set. Gene expression profiles were substrates scored by both ESTIMATE and xCell, and immune cell subpopulations in GBM were analyzed by CIBERSORT. Gene expression profiles associated with low immune scores were performed by lasso regression, Cox analysis and random forest (RF) to identify a prognostic model for the multiple genes associated with immune infiltration in GBM. Then we constructed a nomogram to optimize the prognostic model using GSE7696 and TCGA-GBM as validation sets and evaluated these data for gene mutation and gene enrichment analysis. Result: The prognostic correlation between the six genes (MEOX2, PHYHIP, RBBP8, ST18, TCF12, and THRB) and GBM was finally found by lasso regression, Cox regression, and RF, and the online database obtained that all six genes were differentially expressed in GBM. Therefore, a prognostic correlation model was constructed based on the six genes. Kaplan–Meier (KM) survival analysis showed that this prognostic model had excellent prognostic ability. Conclusions: Prognostic models based on tumor microenvironment and immune score stratification and the construction of related genes have potential applications for prognostic analysis of GBM patients.

Cellular senescence (CS) is increasingly recognized as an important cell-state programme involved in breast cancer progression and therapeutic response, but its context-dependent molecular heterogeneity limits its application in prognostic assessment. In this study, GeneCompass-based all-gene in silico perturbation analysis was performed to identify candidate genes predicted to induce senescence or rejuvenation, thereby expanding the known senescence-related gene set. Machine learning further established a seven-gene prognostic signature that may serve as an adjunctive tool for prognostic assessment across multiple cohorts. The time-dependent AUCs at 1, 3, and 5 years were 0.707, 0.700, and 0.684 in the training cohort; 0.657, 0.661, and 0.629 in the test cohort; and 0.611, 0.646, and 0.637 in the external validation cohort, respectively. Single-cell and spatial transcriptomic analyses suggested that the risk component of the prognostic signature reflects not only malignant epithelial cell states but also stromal–vascular remodelling in the tumor microenvironment. Among the signature genes, ADGRF5 exhibited the most pronounced expression alteration, and its knockdown suppressed malignant phenotypes in breast cancer cells. These findings provide an AI-assisted strategy for senescence biomarker discovery and highlight ADGRF5 as a candidate functional risk gene associated with breast cancer progression.