Wenwen Min
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wenwen Min has a total of 95 co-authors. Here are the top co-authors by number of shared publications:
Fangfang Zhu
School of Health and Nursing Yunnan Open University Kunming Yunnan China
18 shared publications- Juan Liu
Wuhan University
10 shared publications - Shihua Zhang
State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China
9 shared publications Changmiao Wang
6 shared publications- Jun Wan
School of Information Engineering, Zhongnan University of Economics and Law, Wuhan, China
6 shared publications Zhiceng Shi
6 shared publications
Latest Publications
- Open Access
- 29 October 2026
- Published by Wiley in Advanced Science
- p. e78423
SpaCut: Transcript‐Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics
Subcellular Spatial Transcriptomics (SST) offers unprecedented opportunities to decipher tissue architecture at subcellular resolution. Consequently, accurate cell segmentation is a fundamental prerequisite for analyzing SST data, as precise transcript assignment is essential for downstream single‐cell interpretation. Existing methods often overlook the spatial organization of transcripts, rely on simplified geometric priors, or struggle to coordinate transcript‐derived features with morphology‐derived spatial guidance. This limitation restricts their adaptability to irregular cell shapes, often leading to transcript misassignment. To address this, we propose SpaCut, a unified deep learning framework designed to effectively integrate transcriptomic feature learning with dynamic morphological guidance. SpaCut comprises a Gene‐Wise Attention (GWA) module and a Nuclei‐Guided Attentive Fusion (NGAF) module. GWA encodes the high‐dimensional transcript map and aggregates features across multiple depths. NGAF uses the encoded transcript features to modulate distance‐based nuclear softmasks and refine nucleus‐anchored cell boundaries through progressive training. Extensive evaluations across seven datasets from diverse platforms (including Xenium, CosMx, MERSCOPE, and Stereo‐seq) demonstrate that SpaCut significantly outperforms state‐of‐the‐art methods in both segmentation accuracy and consistency with single‐cell reference data. The source code is available at https://github.com/wenwenmin/SpaCut .
- 29 October 2026
- Published by Wiley in Advanced Science
- p. e78423
Open AccessSpaCut: Transcript‐Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics
Subcellular Spatial Transcriptomics (SST) offers unprecedented opportunities to decipher tissue architecture at subcellular resolution. Consequently, accurate cell segmentation is a fundamental prerequisite for analyzing SST data, as precise transcript assignment is essential for downstream single‐cell interpretation. Existing methods often overlook the spatial organization of transcripts, rely on simplified geometric priors, or struggle to coordinate transcript‐derived features with morphology‐derived spatial guidance. This limitation restricts their adaptability to irregular cell shapes, often leading to transcript misassignment. To address this, we propose SpaCut, a unified deep learning framework designed to effectively integrate transcriptomic feature learning with dynamic morphological guidance. SpaCut comprises a Gene‐Wise Attention (GWA) module and a Nuclei‐Guided Attentive Fusion (NGAF) module. GWA encodes the high‐dimensional transcript map and aggregates features across multiple depths. NGAF uses the encoded transcript features to modulate distance‐based nuclear softmasks and refine nucleus‐anchored cell boundaries through progressive training. Extensive evaluations across seven datasets from diverse platforms (including Xenium, CosMx, MERSCOPE, and Stereo‐seq) demonstrate that SpaCut significantly outperforms state‐of‐the‐art methods in both segmentation accuracy and consistency with single‐cell reference data. The source code is available at https://github.com/wenwenmin/SpaCut .
- 20 September 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
HisDiff: Hierarchical Diffusion Modeling for Spatial Gene Expression Prediction from Histology Images
- 20 September 2026
- Published by Elsevier in Pattern Recognition
- Vol. 183
HisDiff: Hierarchical Diffusion Modeling for Spatial Gene Expression Prediction from Histology Images
- Open Access
- 14 September 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 32 (2) , 674-694
SpaViT: Self-Supervised Prediction of High-Resolution Spatial Transcriptomics with Vision Transformer
The spatiotemporal specificity of gene expression highlights the importance of integrating cellular spatial information to better understand the specific functions of cells within tissues. The advent of spatial transcriptomics (ST) technologies has made it possible to quantitatively measure gene expression in cells while also pinpointing their exact locations within tissues. However, widely used ST techniques are frequently limited by low resolution, potentially hindering researchers from fully understanding gene expression patterns, cell type distribution, and their interactions. Here we propose SpaViT, a self-supervised method based on the Transformer architecture for predicting high-resolution gene expression. SpaViT leverages customized self-supervised proxy tasks to learn the continuous patterns of gene expression within tissues and predict high-resolution gene expression profiles. We evaluate the performance of SpaViT on diverse datasets from different platforms with different technologies. The results indicate superior performance of SpaViT in enhancing spatial resolution and predicting gene expression in unmeasured areas compared with other deep learning and traditional interpolation methods. Additionally, SpaViT enhances the spatial patterns of gene expression, aiding researchers in identifying biologically significant differentially expressed genes and pathways.
- 14 September 2026
- Published by Tsinghua University Press in Tsinghua Science and Technology
- Vol. 32 (2) , 674-694
Open AccessSpaViT: Self-Supervised Prediction of High-Resolution Spatial Transcriptomics with Vision Transformer
The spatiotemporal specificity of gene expression highlights the importance of integrating cellular spatial information to better understand the specific functions of cells within tissues. The advent of spatial transcriptomics (ST) technologies has made it possible to quantitatively measure gene expression in cells while also pinpointing their exact locations within tissues. However, widely used ST techniques are frequently limited by low resolution, potentially hindering researchers from fully understanding gene expression patterns, cell type distribution, and their interactions. Here we propose SpaViT, a self-supervised method based on the Transformer architecture for predicting high-resolution gene expression. SpaViT leverages customized self-supervised proxy tasks to learn the continuous patterns of gene expression within tissues and predict high-resolution gene expression profiles. We evaluate the performance of SpaViT on diverse datasets from different platforms with different technologies. The results indicate superior performance of SpaViT in enhancing spatial resolution and predicting gene expression in unmeasured areas compared with other deep learning and traditional interpolation methods. Additionally, SpaViT enhances the spatial patterns of gene expression, aiding researchers in identifying biologically significant differentially expressed genes and pathways.
- 7 September 2026
- Published by Elsevier in Neural Networks
- Vol. 205
FreqFLD: Towards all-in-one facial landmark detection via frequency modulation
- 7 September 2026
- Published by Elsevier in Neural Networks
- Vol. 205
FreqFLD: Towards all-in-one facial landmark detection via frequency modulation
- Open Access
- 20 July 2026
- Published by Wiley in Advanced Science
- Vol. 13 (56) , e76601
Enhancing Super‐Resolution Spatial Transcriptomics Data by Transfer Learning
High‐definition spatial transcriptomics (ST) technologies such as Visium HD enable subcellular tissue characterization but remain constrained by their limited accessibility due to high costs and technical complexity. Existing super‐resolution methods predominantly rely on an image‐guided paradigm, premised on the assumption that gene expression strictly mirrors histological morphology. However, this assumption breaks down for genes with complex spatial distributions lacking distinct visual correlates, often leading to biological artifacts. To address this, we introduce SpotZoomer, a framework that formulates resolution enhancement as a knowledge transfer problem via generative domain adaptation. It leverages public high‐definition ST data as a “teacher” to learn intrinsic spatial expression priors, which are then transferred to coarse spot data to reconstruct high‐fidelity gene profiles that capture molecular details beyond the reach of morphological guidance alone. Extensive benchmarking across 19 datasets demonstrates the substantial value of the reference‐based paradigm implemented by SpotZoomer over the reference‐free image‐only paradigm, achieving improved reconstruction accuracy and biological fidelity while complementing rather than displacing reference‐free methods in settings where high‐resolution priors are unavailable. SpotZoomer thus provides a scalable, data‐driven strategy for upgrading standard ST resources to subcellular resolution.
- 20 July 2026
- Published by Wiley in Advanced Science
- Vol. 13 (56) , e76601
Open AccessEnhancing Super‐Resolution Spatial Transcriptomics Data by Transfer Learning
High‐definition spatial transcriptomics (ST) technologies such as Visium HD enable subcellular tissue characterization but remain constrained by their limited accessibility due to high costs and technical complexity. Existing super‐resolution methods predominantly rely on an image‐guided paradigm, premised on the assumption that gene expression strictly mirrors histological morphology. However, this assumption breaks down for genes with complex spatial distributions lacking distinct visual correlates, often leading to biological artifacts. To address this, we introduce SpotZoomer, a framework that formulates resolution enhancement as a knowledge transfer problem via generative domain adaptation. It leverages public high‐definition ST data as a “teacher” to learn intrinsic spatial expression priors, which are then transferred to coarse spot data to reconstruct high‐fidelity gene profiles that capture molecular details beyond the reach of morphological guidance alone. Extensive benchmarking across 19 datasets demonstrates the substantial value of the reference‐based paradigm implemented by SpotZoomer over the reference‐free image‐only paradigm, achieving improved reconstruction accuracy and biological fidelity while complementing rather than displacing reference‐free methods in settings where high‐resolution priors are unavailable. SpotZoomer thus provides a scalable, data‐driven strategy for upgrading standard ST resources to subcellular resolution.
- 15 July 2026
- Published by Springer Nature
- p. 331-343
SpaAGMF: Adaptive Gated Multi-scale Fusion of Histology and Spatial Transcriptomics for Cancer Region Classification
- 15 July 2026
- Published by Springer Nature
- p. 331-343
SpaAGMF: Adaptive Gated Multi-scale Fusion of Histology and Spatial Transcriptomics for Cancer Region Classification
- Open Access
- 2 July 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (7)
SpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers
Motivation: Spatial transcriptomics (ST) enables the precise mapping of gene expression within tissue architecture, however its application is often limited by low spatial resolution and sparse sampling. While existing deep learning methods leverage histology images, spatial coordinates, or low-resolution expression data to predict high-density profiles, these methods are limited in either capturing the intrinsic constraints between histological context and spatial topology or ignoring the complex local neighborhood relationships between spots. Result: To address these limitations, we propose SpaBiT, a multimodal framework designed to enhance ST resolution via a bidirectional attention mechanism. At its core, SpaBiT employs a bidirectional cross-attention module to facilitate precise information exchange between image features and neighborhood-aware representations learned via a graph attention network. This design explicitly models the synergistic constraints between local morphology and spatial graph topology, yielding high-fidelity, high-density gene expression maps. SpaBiT exhibits competitive performance in reconstructing complex spatial gene expression, outperforming the benchmark models utilized in this study across various quantitative metrics, providing a robust tool for deciphering complex tissue microenvironments. Availability: The source code and datasets are available at https://github.com/wenwenmin/SpaBiT. Supplementary information: Supplementary data are available at Bioinformatics online.
- 2 July 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (7)
Open AccessSpaBiT: Enhancing Spatial Transcriptomics Resolution via Bidirectional Attention Transformers
Motivation: Spatial transcriptomics (ST) enables the precise mapping of gene expression within tissue architecture, however its application is often limited by low spatial resolution and sparse sampling. While existing deep learning methods leverage histology images, spatial coordinates, or low-resolution expression data to predict high-density profiles, these methods are limited in either capturing the intrinsic constraints between histological context and spatial topology or ignoring the complex local neighborhood relationships between spots. Result: To address these limitations, we propose SpaBiT, a multimodal framework designed to enhance ST resolution via a bidirectional attention mechanism. At its core, SpaBiT employs a bidirectional cross-attention module to facilitate precise information exchange between image features and neighborhood-aware representations learned via a graph attention network. This design explicitly models the synergistic constraints between local morphology and spatial graph topology, yielding high-fidelity, high-density gene expression maps. SpaBiT exhibits competitive performance in reconstructing complex spatial gene expression, outperforming the benchmark models utilized in this study across various quantitative metrics, providing a robust tool for deciphering complex tissue microenvironments. Availability: The source code and datasets are available at https://github.com/wenwenmin/SpaBiT. Supplementary information: Supplementary data are available at Bioinformatics online.
- 26 June 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Multi-view masked graph representation learning with semantic alignment for spatial multi-omics clustering
- 26 June 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
Multi-view masked graph representation learning with semantic alignment for spatial multi-omics clustering
- Open Access
- 29 May 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (6)
HisCMCL: cross-modal contrastive learning with hierarchical multi-scale fusion for spatial expression prediction
Motivation: High costs and operational complexity limit the clinical application of spatial transcriptomics (ST). Inferring ST from pathology images is a promising alternative, the core of which lies in effectively aligning image and gene expression features. However, existing models are mostly limited to single-scale and single-slice modeling. This not only fails to connect microscopic cells with macroscopic tissues but also restricts generalization due to the inability to extract cross-sample shared features. Furthermore, the inherent representational differences between modalities further exacerbate the difficulty of feature alignment. Results: To address these challenges, we propose HisCMCL, a multimodal framework. The model combines multi-scale features with a cross-attention mechanism to jointly capture local morphology and global context. Additionally, it fuses spatial location information and utilizes a contrastive learning strategy to facilitate the effective alignment of image and transcriptomic features. Evaluations on four public datasets demonstrate that HisCMCL outperforms existing baseline methods in predictive performance. It exhibits good structural consistency in identifying cancer and immune markers and delineating tumor regions, offering new insights for spatial expression inference. Availability and implementation: The code of HisCMCL is available at https://github.com/wenwenmin/HisCMCL.
- 29 May 2026
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 42 (6)
Open AccessHisCMCL: cross-modal contrastive learning with hierarchical multi-scale fusion for spatial expression prediction
Motivation: High costs and operational complexity limit the clinical application of spatial transcriptomics (ST). Inferring ST from pathology images is a promising alternative, the core of which lies in effectively aligning image and gene expression features. However, existing models are mostly limited to single-scale and single-slice modeling. This not only fails to connect microscopic cells with macroscopic tissues but also restricts generalization due to the inability to extract cross-sample shared features. Furthermore, the inherent representational differences between modalities further exacerbate the difficulty of feature alignment. Results: To address these challenges, we propose HisCMCL, a multimodal framework. The model combines multi-scale features with a cross-attention mechanism to jointly capture local morphology and global context. Additionally, it fuses spatial location information and utilizes a contrastive learning strategy to facilitate the effective alignment of image and transcriptomic features. Evaluations on four public datasets demonstrate that HisCMCL outperforms existing baseline methods in predictive performance. It exhibits good structural consistency in identifying cancer and immune markers and delineating tumor regions, offering new insights for spatial expression inference. Availability and implementation: The code of HisCMCL is available at https://github.com/wenwenmin/HisCMCL.
- 21 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 329
SpaMGCL: Neighborhood-aware masked graph contrastive learning for spatial transcriptomics analysis
- 21 May 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 329
SpaMGCL: Neighborhood-aware masked graph contrastive learning for spatial transcriptomics analysis