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.

Aims: Single-cell RNA sequencing 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.