Aims:Single-cell RNA sequencing (scRNA-seq) has emerged as a cornerstone technology in tumor microenvironment research. Accurate cell-type annotation is fundamental to downstream scRNA-seq analysis. However, automated tools are often highly sensitive to dataset noise and show limited adaptability in cross-patient scenarios. To address these challenges, we propose scAdaptAnno, a graph-based target domain adaptation framework for cross-patient single-cell annotation.

Methods:In the graph construction phase, scAdaptAnno integrates both gene expression similarity and biological prior knowledge to build a more biologically meaningful cell graph. By leveraging cell representations enriched with biological priors to mitigate noise in gene expression data and by implementing a bidirectional adaptation mechanism, the model achieves source-free target domain alignment.

Results:We performed comprehensive benchmarking against nine leading methods across multiple datasets spanning various cancer types. The results demonstrate that scAdaptAnno achieves state-of-the-art performance.

Conclusion:scAdaptAnno is a robust and accurate single-cell annotation tool that excels in cross-patient cell-type annotation transfer. By integrating biologically informed graph construction and bidirectional source-free domain adaptation, it delivers reliable, noise-resistant performance across diverse tumor microenvironments, providing an effective solution for automated cell-type annotation in multi-patient scRNA-seq studies.

Aims: Circular RNAs (circRNAs) have been shown to be closely associated with the occurrence and progression of various diseases. However, most existing circRNA-disease association prediction methods are limited to homogeneous networks and are unable to effectively capture deep semantic associations through high-order meta-paths. This study aims to develop an efficient computational method for accurately predicting potential circRNA-disease associations.

Methods: We propose a meta-relation-aware heterogeneous graph learning framework for circRNA-disease association prediction. Specifically, known circRNA-disease associations are first used to compute Gaussian interaction profile kernel similarity and extract node attribute features, based on which a heterogeneous graph network is constructed. A graph neural network is then employed to perform multi-layer message passing on the heterogeneous graph, aggregating neighborhood information to achieve deep fusion of multi-source features and generate node embeddings that encode both local and global structural information. Finally, the learned embeddings are fed into a gradient boosting decision tree classifier, and an ensemble strategy is adopted to improve prediction accuracy. Five-fold cross-validation is used for performance evaluation.

Results: Experimental results on three benchmark datasets, CircR2Disease V2.0, circAtlas 3.0, and circRNADisease V2.0, show that the proposed model achieves area under the receiver operating characteristic curve (AUC) values of 92.17%, 91.83%, and 91.73%, respectively. The model outperforms traditional methods in terms of accuracy, precision, and recall. Furthermore, ablation studies validate the effectiveness of the meta-relation-aware strategy.

Conclusions: Overall, this work provides an efficient and reliable computational framework for molecular association prediction and biomarker discovery in the biomedical domain.

Aims:Alternative splicing serves as a primary mechanism for diversifying the proteome, making the prediction of distinct isoform functions critical for understanding complex disease mechanisms. However, determining the specific functional roles of isoforms remains hindered by high sequence homology among variants and the sparsity of isoform-level annotations.

Methods:In this study, we propose SpliceEM, a deep learning framework for isoform function prediction at single-cell resolution. SpliceEM utilizes a splicing event-aware encoder with cross-modal attention to separate functional signals from global protein sequences. A Heterogeneous Graph Transformer captures the dependencies among isoforms, genes, and Gene Ontology terms. To bridge the annotation gap, we incorporate a self-distillation framework guided by an Exponential Moving Average teacher model and Multi-Instance Learning, optimized by an Asymmetric Loss and hierarchical constraints.

Results:Benchmarking on human datasets demonstrates that SpliceEM outperforms existing methods in isoform function prediction, particularly in identifying rare functional terms under data-sparse conditions. Furthermore, splicing-function analysis reveals that specific splicing events, such as skipped exons and alternative first exons, act as prominent drivers in oncogenic signaling cascades and context-specific functional switching.

Conclusion:SpliceEM provides a computational foundation for exploring transcriptomic functional diversity. By shifting the focus from global sequences to localized splicing events and utilizing hierarchical biological priors, it offers high-resolution insights into cell-type-specific molecular mechanisms and potential therapeutic targets.

Antibody polyreactivity refers to the ability of a monoclonal antibody to non-specifically bind to a diverse range of antigens. While this property may be an intrinsic mechanism of the immune response, it poses significant challenges in therapeutic antibody development, often leading to off-target effects, poor pharmacokinetics, and potential toxicity. This review compiles the data resources related to polyreactive antibodies and places a particular emphasis on computational models for predicting antibody polyreactivity. The latter includes empirical models based on physicochemical properties, traditional machine learning models, deep learning networks, and protein language models. Through delineating the complexity of antibody polyreactivity, this review emphasizes the critical role and growing potential of computational prediction tools in selecting and engineering antibody drug candidates at early stages, thereby reducing development risks and accelerating the development of safer and better therapeutic antibodies.

Aims: Translating pre-clinical findings into clinical evidence is essential for cancer research. Although succinyl-CoA ligase ADP-forming subunit beta (SUCLA2) has been implicated in metastasis through stress granule assembly in pre-clinical models, direct clinical evidence linking SUCLA2-alone or in interaction with stress granule components such as ubiquitin-specific peptidase 10 (USP10)-to distant metastasis-free survival (DMFS) remains limited. This study aimed to evaluate whether the SUCLA2-USP10 interaction correlates with breast cancer DMFS and whether treatment modifies this association.

Methods: We analyzed four independent breast cancer cohorts with DMFS data (GSE17705, GSE45255, GSE7390, and GSE11121). Patients were stratified into four subgroups based on median SUCLA2 and USP10 expression levels: low-SUCLA2/low-USP10 (LL), low-SUCLA2/high-USP10 (LH), high-SUCLA2/low-USP10 (HL), and high-SUCLA2/high-USP10 (HH). Stratified Cox regression was applied, with cohort as the stratification factor, to examine whether the prognostic impact of these subgroups differed between treated and untreated patients.

Results: A significant interaction was observed between treatment status and SUCLA2-USP10 subgroup membership, specifically for the LH subgroup (p = 0.00038). In untreated patients, the LH subgroup exhibited a significantly higher risk for DMFS (HR = 2.45), whereas in treated patients, this elevated risk was completely abrogated (HR = 0.71). Neither SUCLA2 nor USP10 alone showed a consistent association with DMFS across the four cohorts.

Conclusion: These findings provide clinical evidence that the SUCLA2-USP10 interaction, rather than either factor alone, correlates with breast cancer DMFS. The treatment-modulated risk reversal observed in the LH subgroup supports the development of anti-metastatic strategies targeting this interaction.