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: Single-cell RNA-sequencing (RNA-seq) enables high-resolution gene regulatory network (GRN) analysis in specific cell types, but data sparsity, noise, and complex regulatory relationships remain major challenges. Existing methods often focus on pairwise gene associations and insufficiently capture global network topology. This study aims to develop a deep graph framework for single-cell GRN inference by integrating global regulatory structure with biologically informed distributional regularization.

Methods: We propose ZINB-GRAN, a graph adversarial framework for single-cell GRN inference. It constructs a weighted gene co-expression matrix as a prior regulatory graph and reformulates GRN inference as a link prediction task. A graph convolutional encoder learns latent gene representations, while a decoder reconstructs network topology. To enhance biological consistency, a multilayer perceptron-based discriminator aligns encoder-derived representations with a continuous zero-inflated negative binomial (ZINB)-derived prior generated through ZINB sampling, logarithmic transformation, normalization, and Gaussian perturbation.

Results: ZINB-GRAN jointly optimizes network reconstruction and latent distribution alignment using mask-based supervised classification and adversarial losses. This strategy improves regulatory structure discrimination and robustness in sparse single-cell data. Benchmarking on simulated and real datasets shows that ZINB-GRAN outperforms most existing GRN inference methods and identifies cell type-specific GRNs and key regulatory factors in human peripheral blood mononuclear cells (PBMCs) and triple-negative breast cancer.

Conclusion: ZINB-GRAN integrates global network topology, graph convolutional representation learning, and continuous ZINB-derived prior regularization for single-cell GRN inference. By aligning latent representations with a biologically motivated prior, it improves the robustness and interpretability of GRN reconstruction and provides a useful tool for cell-specific network inference, key regulator identification, and biomarker discovery.

In recent years, attention mechanisms have gained widespread application and significant advancements in the field of biological sequence analysis. This paper systematically summarizes the fundamental principles of attention mechanisms and their latest research progress in biological sequence analysis. First, the development history of attention mechanisms is introduced, with a focus on classic mechanisms such as self-attention, cross-attention, and multi-head attention, along with their improved variants. Next, a brief overview of the classification and characteristics of bioinformatics databases is provided. Subsequently, the application of attention mechanisms in the analysis of DNA, RNA, and protein sequences is highlighted. In the realm of DNA sequence analysis, attention mechanisms have been applied to tasks such as epigenetic analysis and regulatory element identification; in RNA sequence analysis, they play a crucial role in single-cell RNA sequencing, RNA function prediction, and structure prediction; in protein sequence analysis, attention mechanisms are widely used in protein classification, function prediction, structure prediction, site prediction, and interaction prediction. Furthermore, this paper summarizes the applications of attention mechanisms in other biological sequence analysis tasks, such as multi-omics analysis and enzyme analysis. The attention mechanisms can significantly improve the accuracy, interpretability, and computational efficiency of biological sequence analysis, providing powerful computational tools for bioinformatics research.

Aims: The Pro-Glu (PE) and Pro-Pro-Glu (PPE) protein family of Mycobacterium tuberculosis plays a critical role in virulence, immune evasion, and host-pathogen interactions. However, the high guanine-cytosine-content and repetitive sequences of these proteins have long hindered accurate gene identification and functional annotation. This study aims to develop an effective computational framework to improve the identification of PE/PPE proteins.

Methods: We propose PIONEER, a structure-aware deep learning framework that integrates embeddings from the pre-trained protein language model ESM Cambrian (ESMC) with structural features. PIONEER represents proteins as residue-level graphs that encode both sequence semantics and three-dimensional topological structure, enabling effective modelling of hierarchical geometric relationships.

Results: Benchmarking demonstrates that PIONEER outperforms 16 traditional machine learning algorithms and the existing deep learning model across multiple evaluation metrics, including accuracy, Matthew’s correlation coefficient, and F1 scores. Ablation experiments confirm the complementary contributions of ESMC embeddings and secondary structure features to model performance. The t-SNE-based visualization results reveal the contributions of features across different network layers to the identification of PE/PPE proteins.

Conclusion: PIONEER improves the accuracy of PE/PPE protein identification by integrating sequence and structural information within a structure-aware graph learning framework. This method provides an effective computational tool for functional annotation, investigation of pathogenicity mechanisms, and vaccine target discovery in M. tb.

Aims: To develop a robust and clinically feasible framework for cancer survival prediction using only histopathology images while leveraging transcriptomic knowledge during training.

Aims: To develop a robust and clinically feasible framework for cancer survival prediction using only histopathology images while leveraging transcriptomic knowledge during training.

Methods: The study proposed Adaptive Multi-modality Knowledge Distillation (AMKD), a framework designed to transfer complementary molecular-level information from transcriptomic data to pathology-based models. The AMKD framework consists of two essential elements. First, a gene-guided pathology enhancement module is designed to inject genomics-aware information from a multimodal teacher into pathology features. Second, an adaptive redundancy reduction loss is introduced to regulate knowledge distillation by accounting for prediction discrepancies between teacher and student models. This design allows the student model to retain biologically meaningful knowledge during training and remain effective with only histopathology data at inference.

Results: Comprehensive experiments on four The Cancer Genome Atlas (TCGA) cancer cohorts demonstrate that AMKD achieves state-of-the-art survival prediction performance, with an average concordance index (C-index) of 0.669, surpassing both unimodal pathology-based and fully multi-modal approaches. External validation on the independent Clinical Proteomic Tumor Analysis Consortium head and neck squamous cell carcinoma (CPTAC-HNSC) cohort further confirms the robustness and cross-dataset generalization ability of the proposed framework. Ablation studies further confirm the effectiveness of each proposed component in enhancing cross-modal knowledge transfer and improving generalization under incomplete modality scenarios.

Conclusion: The proposed AMKD framework provides a clinically practical solution for robust cancer survival analysis when transcriptomic data are unavailable. By adaptively distilling multi-modal knowledge into a pathology-based model, AMKD bridges the gap between research and clinical applicability, enabling scalable and cost-effective prognostic prediction in real-world settings.

Aims: Since distal enhancers are involved in regulating target genes through physical contacting with proximal promoters, identifying enhancer-promoter interactions (EPIs) is critical to deepening our understanding of gene expression. However, high-throughput experimental methods for identifying EPIs are time-consuming and expensive. Therefore, computational methods for predicting EPIs would be valuable and important, but also face a lot of challenges.

Methods: In this paper, we propose a novel deep learning-based method, namely EPIPAM, to predict EPIs only using genomic sequences. EPIPAM firstly uses a deep convolutional neural network to extract high-level sequence features, and then uses a position attention mechanism to compute the positional correlation coefficients of two subregions separately coming from enhancers and promoters, aiming to focus on important regions of them.

Results: Benchmarking comparisons on six different cell lines show that EPIPAM performs better than the state-of-the-art methods in the task of EPIs prediction. More importantly, we notice that, almost without exception, the predictive performance of all methods is really poor once applying a strategy of splitting training and test data by chromosome. Therefore, we explain the possible reason that leads to this situation by systematically exploring the structure of EPI datasets, and indirectly analyze the difficulty of predicting EPIs only using genomic sequences through ChIA-PET contact datasets.

Conclusion: This study presents a novel deep learning-based method to predict EPIs only using genomic sequences. Although the proposed method achieves higher predictive accuracy, it suffers from several limitations, such as highly selective matching bias, negative sample selection issues, and constraints of pre-trained vectors.