Meng-Meng Wei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Meng-Meng Wei has a total of 45 co-authors. Here are the top co-authors by number of shared publications:
- Lei Wang
School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou 221116, China
17 shared publications Zhu-Hong You
School of Computer Science, Northwestern Polytechnical University , Xi’an, 710129
7 shared publications- Xin-Fei Wang
College of Computer Science and Technology, Jilin University, Changchun, China
6 shared publications - Zhu-Hong You
School of Computer Science, Northwestern Polytechnical University, Xi’an 710129, China
6 shared publications - Bo-Wei Zhao
Zhejiang University
5 shared publications Chang-Qing Yu
5 shared publications
Latest Publications
- Open Access
- 2 November 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (6)
Biosemantic graph transfer learning for cross-patient cell type annotation and cell–cell interaction analysis in tumor single-cell RNA sequencing
The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context and rely on incomplete datasets of ligand–receptor interactions, limiting accurate cell type annotation and cell–cell communication inference. This study addresses these challenges using a novel graph neural network model that enhances cell-type prediction and cell-interaction analysis. Our study utilized a dataset consisting of 49 024 cells from 19 patients across three cancer types: leukemia, breast invasive carcinoma, and colorectal cancer. The proposed scGSL model demonstrated robust performance, achieving an average accuracy of 84.83%, precision of 86.23%, recall of 81.51%, and an F1 score of 80.92% across all datasets. These metrics represent a significant enhancement over existing methods, which typically exhibit lower performance metrics. Additionally, by reviewing existing literature on gene interactions within the TME, the scGSL model proves to robustly identify biologically meaningful gene interactions in an unsupervised manner, validated by significant expression differences in key gene pairs across various cancers. The source code and data used in this study can be found at https://github.com/LiYuechao1998/scGSL.
- 2 November 2026
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 27 (6)
Open AccessBiosemantic graph transfer learning for cross-patient cell type annotation and cell–cell interaction analysis in tumor single-cell RNA sequencing
The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context and rely on incomplete datasets of ligand–receptor interactions, limiting accurate cell type annotation and cell–cell communication inference. This study addresses these challenges using a novel graph neural network model that enhances cell-type prediction and cell-interaction analysis. Our study utilized a dataset consisting of 49 024 cells from 19 patients across three cancer types: leukemia, breast invasive carcinoma, and colorectal cancer. The proposed scGSL model demonstrated robust performance, achieving an average accuracy of 84.83%, precision of 86.23%, recall of 81.51%, and an F1 score of 80.92% across all datasets. These metrics represent a significant enhancement over existing methods, which typically exhibit lower performance metrics. Additionally, by reviewing existing literature on gene interactions within the TME, the scGSL model proves to robustly identify biologically meaningful gene interactions in an unsupervised manner, validated by significant expression differences in key gene pairs across various cancers. The source code and data used in this study can be found at https://github.com/LiYuechao1998/scGSL.
- Open Access
- 26 October 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (11)
Multi-view state-space modeling for zero-shot circRNA–miRNA interaction prediction
Motivation: CircRNA–miRNA interactions (CMIs) play regulatory roles in human diseases and provide clues for therapeutic target discovery. However, most existing prediction methods rely on circRNA–miRNA pairs and overlook disease-level regulatory contexts, which limits their ability to characterize cross-pathway dependencies in zero-shot inference. Results: We propose MV-S2M, a multi-view state-space modeling framework that integrates molecular attributes to enhance relational reasoning, enabling zero-shot CMI prediction. Specifically, MV-S2M performs structure-aware diffusion to enrich molecular priors and constructs disease-mediated semantic subgraphs. It then incorporates state-space modeling to capture long-range dependencies and view-specific regulatory patterns. The learned multi-view representations are fused through a linear projection and fed into an MLP for CMI prediction. Extensive experiments on multiple benchmark datasets demonstrate that MV-S2M achieves state-of-the-art performance under both zero-shot and conventional settings. Cold-start evaluations reveal distinct generalization behavior across different unseen-entity settings. Case studies illustrate the contribution of meta-path-guided semantic subgraphs to CMI prediction. Availability and implementation: The code and data are publicly available at https://github.com/591286260/MV and https://doi.org/10.5281/zenodo.22858403.
- 26 October 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (11)
Open AccessMulti-view state-space modeling for zero-shot circRNA–miRNA interaction prediction
Motivation: CircRNA–miRNA interactions (CMIs) play regulatory roles in human diseases and provide clues for therapeutic target discovery. However, most existing prediction methods rely on circRNA–miRNA pairs and overlook disease-level regulatory contexts, which limits their ability to characterize cross-pathway dependencies in zero-shot inference. Results: We propose MV-S2M, a multi-view state-space modeling framework that integrates molecular attributes to enhance relational reasoning, enabling zero-shot CMI prediction. Specifically, MV-S2M performs structure-aware diffusion to enrich molecular priors and constructs disease-mediated semantic subgraphs. It then incorporates state-space modeling to capture long-range dependencies and view-specific regulatory patterns. The learned multi-view representations are fused through a linear projection and fed into an MLP for CMI prediction. Extensive experiments on multiple benchmark datasets demonstrate that MV-S2M achieves state-of-the-art performance under both zero-shot and conventional settings. Cold-start evaluations reveal distinct generalization behavior across different unseen-entity settings. Case studies illustrate the contribution of meta-path-guided semantic subgraphs to CMI prediction. Availability and implementation: The code and data are publicly available at https://github.com/591286260/MV and https://doi.org/10.5281/zenodo.22858403.
- Open Access
NARVGA: A Hybrid Framework Integrating Matrix Factorisation and Adversarial Graph Learning for circRNA-Disease Association Prediction
Circular RNAs (circRNAs) participate in gene regulation and disease progression, but experimental mapping of circRNA-disease associations (CDAs) remains costly and incomplete. We developed NARVGA, a hybrid prediction framework that combines non-negative matrix factorisation (NMF) with an adversarially regularised variational graph autoencoder (ARVGA). Functional, semantic and Gaussian interaction-profile kernel similarities are integrated; K-means-derived co-membership graphs reduce diffuse similarity connections; ARVGA learns nonlinear topological embeddings; and NMF captures complementary low-rank association patterns. An Extra Trees classifier then scores candidate circRNA-disease pairs. In the original transductive stratified five-fold benchmark on CircR2Disease, NARVGA achieved an area under the receiver operating characteristic curve (AUC) of 0.9868, an area under the precision–recall curve (AUPR) of 0.9887, 94.32% accuracy and a 94.44% F1-score. Ablation analysis identified cluster sparsification as the largest individual contributor, with additional gains from adversarial regularisation and low-rank augmentation. Without task-specific retuning, the model obtained AUCs of 0.9503 on LncRNADisease and 0.9700 on HMDDv4. Performance was stable across GCN depths and cluster settings, and 19 of the 20 highest-ranked hepatocellular carcinoma candidates had supporting published evidence. NARVGA provides a within-network prioritisation tool for RNA-disease association studies, although prospective validation, hard-negative assessment and independent-cohort testing remain necessary.
Open AccessNARVGA: A Hybrid Framework Integrating Matrix Factorisation and Adversarial Graph Learning for circRNA-Disease Association Prediction
Circular RNAs (circRNAs) participate in gene regulation and disease progression, but experimental mapping of circRNA-disease associations (CDAs) remains costly and incomplete. We developed NARVGA, a hybrid prediction framework that combines non-negative matrix factorisation (NMF) with an adversarially regularised variational graph autoencoder (ARVGA). Functional, semantic and Gaussian interaction-profile kernel similarities are integrated; K-means-derived co-membership graphs reduce diffuse similarity connections; ARVGA learns nonlinear topological embeddings; and NMF captures complementary low-rank association patterns. An Extra Trees classifier then scores candidate circRNA-disease pairs. In the original transductive stratified five-fold benchmark on CircR2Disease, NARVGA achieved an area under the receiver operating characteristic curve (AUC) of 0.9868, an area under the precision–recall curve (AUPR) of 0.9887, 94.32% accuracy and a 94.44% F1-score. Ablation analysis identified cluster sparsification as the largest individual contributor, with additional gains from adversarial regularisation and low-rank augmentation. Without task-specific retuning, the model obtained AUCs of 0.9503 on LncRNADisease and 0.9700 on HMDDv4. Performance was stable across GCN depths and cluster settings, and 19 of the 20 highest-ranked hepatocellular carcinoma candidates had supporting published evidence. NARVGA provides a within-network prioritisation tool for RNA-disease association studies, although prospective validation, hard-negative assessment and independent-cohort testing remain necessary.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5512-5523
MuSeL: A Multi-Scale Adaptive Graph Representation Learning Framework for Microbe-Drug Association Prediction
Microbe-drug association (MDA) prediction is of great importance for understanding drug action mechanisms and exploring microbiome-based therapeutic strategies. However, when confronted with extremely sparse biological networks with pronounced structural heterogeneity, existing methods often struggle to simultaneously model global topological dependencies and local structural disparities. To address these challenges, we propose MuSeL, a multi-scale adaptive graph representation learning framework that jointly mitigates the above issues from two complementary perspectives: global topology modeling and local structure optimization. Specifically, we develop a spectral kernel attention mechanism that leverages the normalized Laplacian and chebyshev polynomial expansion to efficiently capture multi-scale global topological relations in the spectral domain. Meanwhile, we construct a structure-aware self-adaptive sampling module that dynamically adjusts neighborhood sampling based on node clustering coefficients and degree centrality, thereby improving the reliability of local structural and feature representations. Finally, the fused multi-scale node embeddings are fed into a prediction module to estimate MDA scores. Extensive experiments show that outperforms existing mainstream models, while ablation studies and case analyses further validate its effectiveness and robustness. Overall, MuSeL provides a practical computational framework for prioritizing candidate MDAs, supporting downstream biological validation and drug repurposing research.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 5512-5523
Open AccessMuSeL: A Multi-Scale Adaptive Graph Representation Learning Framework for Microbe-Drug Association Prediction
Microbe-drug association (MDA) prediction is of great importance for understanding drug action mechanisms and exploring microbiome-based therapeutic strategies. However, when confronted with extremely sparse biological networks with pronounced structural heterogeneity, existing methods often struggle to simultaneously model global topological dependencies and local structural disparities. To address these challenges, we propose MuSeL, a multi-scale adaptive graph representation learning framework that jointly mitigates the above issues from two complementary perspectives: global topology modeling and local structure optimization. Specifically, we develop a spectral kernel attention mechanism that leverages the normalized Laplacian and chebyshev polynomial expansion to efficiently capture multi-scale global topological relations in the spectral domain. Meanwhile, we construct a structure-aware self-adaptive sampling module that dynamically adjusts neighborhood sampling based on node clustering coefficients and degree centrality, thereby improving the reliability of local structural and feature representations. Finally, the fused multi-scale node embeddings are fed into a prediction module to estimate MDA scores. Extensive experiments show that outperforms existing mainstream models, while ablation studies and case analyses further validate its effectiveness and robustness. Overall, MuSeL provides a practical computational framework for prioritizing candidate MDAs, supporting downstream biological validation and drug repurposing research.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12361-12371
Multi-Hop Diffusion-Wavelet Semantic Learning for Zero-Shot Circrna-Mirna Interaction Prediction
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 12361-12371
Open AccessMulti-Hop Diffusion-Wavelet Semantic Learning for Zero-Shot Circrna-Mirna Interaction Prediction
- 16 July 2026
- Published by Springer Nature
- p. 79-89
A Hybrid Transformer-GCN Framework for CircRNA-Disease Association Prediction
- 16 July 2026
- Published by Springer Nature
- p. 79-89
A Hybrid Transformer-GCN Framework for CircRNA-Disease Association Prediction
- 15 July 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (14) , 8663-8677
Functionally Guided Graph Learning for Robust Cross-Patient Cell-Type Annotation in Single-Cell RNA Sequencing
Cross-patient cell-type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to pronounced interpatient heterogeneity and distribution shifts across patient-specific cellular contexts. Conventional annotation approaches often rely on proximity-driven graph construction or expression similarity, which may introduce spurious cell–cell connections and lead to unstable knowledge transfer across patients. To address this limitation, we propose PathoGraph, a functionally guided graph learning framework for robust cross-patient cell-type annotation. The proposed method integrates KEGG-7-based biosemantic graph structure learning with cross-patient representation adaptation. Specifically, pathway-derived functional semantic profiles are incorporated to refine patient-specific cell graphs, encouraging biologically coherent neighborhoods and suppressing noise introduced by purely expression-based similarity. Based on the refined graphs, a cross-patient representation adaptation mechanism further aligns embeddings between labeled reference patients and unlabeled query patients to facilitate reliable annotation transfer. Experiments on three cross-patient scRNA-seq data sets, including leukemia, breast invasive carcinoma, and colorectal cancer data sets, demonstrate that PathoGraph achieves stable annotation performance across 32 directed reference-to-query transfer tasks. Across all tasks, PathoGraph obtained an average ACC of 84.28% and an F1-score of 84.08%, showing competitive and stable performance compared with representative marker-based, correlation-based, and model-based annotation methods. Ablation studies further show that removing the biosemantic graph learning module reduces the average accuracy to 83.48%, highlighting the importance of functional-guided graph refinement. In addition, post hoc functional relevance analyses in immune-cell and cancer-associated contexts suggest that the learned cell–cell graphs capture biologically relevant neighborhood structures beyond expression-driven proximity. The source code and processed data are publicly available at: https://github.com/LiYuechao1998/PathoGraph.
- 15 July 2026
- Published by American Chemical Society (ACS) in Journal of Chemical Information and Modeling
- Vol. 66 (14) , 8663-8677
Functionally Guided Graph Learning for Robust Cross-Patient Cell-Type Annotation in Single-Cell RNA Sequencing
Cross-patient cell-type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to pronounced interpatient heterogeneity and distribution shifts across patient-specific cellular contexts. Conventional annotation approaches often rely on proximity-driven graph construction or expression similarity, which may introduce spurious cell–cell connections and lead to unstable knowledge transfer across patients. To address this limitation, we propose PathoGraph, a functionally guided graph learning framework for robust cross-patient cell-type annotation. The proposed method integrates KEGG-7-based biosemantic graph structure learning with cross-patient representation adaptation. Specifically, pathway-derived functional semantic profiles are incorporated to refine patient-specific cell graphs, encouraging biologically coherent neighborhoods and suppressing noise introduced by purely expression-based similarity. Based on the refined graphs, a cross-patient representation adaptation mechanism further aligns embeddings between labeled reference patients and unlabeled query patients to facilitate reliable annotation transfer. Experiments on three cross-patient scRNA-seq data sets, including leukemia, breast invasive carcinoma, and colorectal cancer data sets, demonstrate that PathoGraph achieves stable annotation performance across 32 directed reference-to-query transfer tasks. Across all tasks, PathoGraph obtained an average ACC of 84.28% and an F1-score of 84.08%, showing competitive and stable performance compared with representative marker-based, correlation-based, and model-based annotation methods. Ablation studies further show that removing the biosemantic graph learning module reduces the average accuracy to 83.48%, highlighting the importance of functional-guided graph refinement. In addition, post hoc functional relevance analyses in immune-cell and cancer-associated contexts suggest that the learned cell–cell graphs capture biologically relevant neighborhood structures beyond expression-driven proximity. The source code and processed data are publicly available at: https://github.com/LiYuechao1998/PathoGraph.
- Open Access
- 10 June 2026
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (12) , 5260
Inferring circRNA–Disease Associations via Sparse Topological Representation Learning and Dual-View Decoding
Circular RNAs (circRNAs) are key regulators in the onset and progression of complex diseases, offering promise as diagnostic and prognostic biomarkers. However, most putative circRNA–disease associations remain experimentally unverified, largely due to the cost and time demands of wet-lab approaches. To bridge this gap, we present STRCDA (Sparse Topological Representation learning for CircRNA–Disease Associations). The pipeline first constructs fused similarity profiles for circRNAs and diseases by integrating diverse biological attributes. These initial matrices are then refined via random walk with restart to capture local features. Subsequently, a sparse-constrained dual-branch graph autoencoder extracts holistic topological embeddings from the refined local features and the known interaction network. Finally, an XGBoost classifier scores potential circRNA–disease pairs. On the CircR2Disease dataset, STRCDA achieves an AUC of 0.9771 and an AUPR of 0.9826 under five-fold cross-validation. Notably, 18 of the top 20 predicted associations were confirmed by independent experimental evidence, highlighting STRCDA’s efficacy as a robust tool for uncovering circRNA function in disease.
- 10 June 2026
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (12) , 5260
Open AccessInferring circRNA–Disease Associations via Sparse Topological Representation Learning and Dual-View Decoding
Circular RNAs (circRNAs) are key regulators in the onset and progression of complex diseases, offering promise as diagnostic and prognostic biomarkers. However, most putative circRNA–disease associations remain experimentally unverified, largely due to the cost and time demands of wet-lab approaches. To bridge this gap, we present STRCDA (Sparse Topological Representation learning for CircRNA–Disease Associations). The pipeline first constructs fused similarity profiles for circRNAs and diseases by integrating diverse biological attributes. These initial matrices are then refined via random walk with restart to capture local features. Subsequently, a sparse-constrained dual-branch graph autoencoder extracts holistic topological embeddings from the refined local features and the known interaction network. Finally, an XGBoost classifier scores potential circRNA–disease pairs. On the CircR2Disease dataset, STRCDA achieves an AUC of 0.9771 and an AUPR of 0.9826 under five-fold cross-validation. Notably, 18 of the top 20 predicted associations were confirmed by independent experimental evidence, highlighting STRCDA’s efficacy as a robust tool for uncovering circRNA function in disease.
- 20 March 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 120
A cross-modal graph structure learning prediction model for CircRNA-MiRNA interactions
- 20 March 2026
- Published by Elsevier in Biomedical Signal Processing and Control
- Vol. 120
A cross-modal graph structure learning prediction model for CircRNA-MiRNA interactions
- Open Access
- 13 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 231-236
scGraphPilot: Functionally Guided Graph Transfer for Robust Cross-Patient Cell Type Annotation
Cross-patient cell type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to strong biological heterogeneity and distribution shifts between patient datasets. Many existing annotation methods rely on transcriptional similarity or marker gene information, which may lead to unstable predictions when transferring knowledge across patients. In this work, we propose scGraphPilot, a graph-based framework designed for robust cross-patient cell type annotation. The proposed method introduces KEGG functional-guided graph learning, where pathway activity signals derived from KEGG categories are incorporated to refine cell–cell graph structures. This mechanism encourages biologically coherent neighborhoods and reduces noisy edges caused by purely expression-based similarity. In addition, a cross-patient representation alignment strategy is employed to enable knowledge transfer from labeled reference datasets to unlabeled query datasets while preserving patient-specific graph topology. Experiments on the leukemia dataset GSE132509 demonstrate that scGraphPilot achieves stable annotation performance across multiple cross-patient transfer tasks and consistently outperforms several representative annotation models in terms of accuracy and robustness. Furthermore, biological validation using known immune-related gene interactions confirms that the learned graph connectivity reflects meaningful cellular communication patterns. These results indicate that integrating functional signals into graph learning provides an effective and interpretable solution for cross-patient cell type annotation in heterogeneous single-cell datasets.
- 13 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 231-236
Open AccessscGraphPilot: Functionally Guided Graph Transfer for Robust Cross-Patient Cell Type Annotation
Cross-patient cell type annotation in single-cell RNA sequencing (scRNA-seq) remains challenging due to strong biological heterogeneity and distribution shifts between patient datasets. Many existing annotation methods rely on transcriptional similarity or marker gene information, which may lead to unstable predictions when transferring knowledge across patients. In this work, we propose scGraphPilot, a graph-based framework designed for robust cross-patient cell type annotation. The proposed method introduces KEGG functional-guided graph learning, where pathway activity signals derived from KEGG categories are incorporated to refine cell–cell graph structures. This mechanism encourages biologically coherent neighborhoods and reduces noisy edges caused by purely expression-based similarity. In addition, a cross-patient representation alignment strategy is employed to enable knowledge transfer from labeled reference datasets to unlabeled query datasets while preserving patient-specific graph topology. Experiments on the leukemia dataset GSE132509 demonstrate that scGraphPilot achieves stable annotation performance across multiple cross-patient transfer tasks and consistently outperforms several representative annotation models in terms of accuracy and robustness. Furthermore, biological validation using known immune-related gene interactions confirms that the learned graph connectivity reflects meaningful cellular communication patterns. These results indicate that integrating functional signals into graph learning provides an effective and interpretable solution for cross-patient cell type annotation in heterogeneous single-cell datasets.