Description

Algorithmic Advances for Single-Cell and Spatial Omics Data Analysis
With recent technological breakthroughs in single-cell and spatial transcriptomics, as well as spatial proteomics and other spatially resolved omics platforms, researchers now have access to molecular data at unprecedented resolution in both cellular identity and spatial context. These technologies have opened new frontiers in understanding tissue organization, developmental biology, and disease pathology. However, extracting meaningful insights from these complex, high-dimensional, and often noisy datasets requires the development of novel computational methods and algorithmic frameworks. To date, a wide array of algorithms has been proposed for tasks such as cell type deconvolution, spatial domain detection, gene–gene interaction modeling, cell–cell communications, and integrative multi-modal analysis. As spatial and single-cell data types become increasingly diverse, scalable and robust computational approaches are needed to bridge modalities, leverage spatial information, and reveal previously inaccessible layers of biological regulation.

We invite investigators to contribute Original Research articles focused on designing, applying, or benchmarking algorithms for analyzing single-cell and spatial omics data. Topics of interest include, but are not limited to, the following:

Computational methods for analyzing single-cell and spatial transcriptomics data
Algorithms for spatial domain and tissue architecture identification
Methods for inferring cell–cell communication and signaling networks in spatial context
Methods for exploring the tumor microenvironment from spatial transcriptomics data
Joint analysis of spatial transcriptomics, images and spatial proteomics data, or other omics data
Machine learning and deep learning approaches for multi-omics integration at single-cell resolution
New tools for trajectory inference and lineage tracing with spatial information
Data-driven frameworks for 3D reconstruction and spatial modeling of tissues
Denoising, imputation, deconvolution and normalization methods tailored to spatial and single-cell data
Algorithmic innovations for cross-sample alignment, batch correction, and reference mapping
Applications of advanced computational methods in developmental biology, neuroscience, immunology, and cancer research

This special issue aims to highlight the state-of-the-art in algorithmic development for spatial and single-cell omics, and to foster a community of researchers pushing the boundaries of computational biology through innovative tools and integrative analysis.

Important Dates

Oct 15, 2025: Due date for workshop paper submission
Nov 10, 2025: Notification of paper acceptance to authors
Nov 23, 2025: Camera-ready of accepted papers
Dec 15–18, 2025: Workshops

Program Chairs

Xin Maizie Zhou, Department of Biomedical Engineering and Computer Science, Vanderbilt University
Eric Lu Zhang, Department of Computer Science, Hong Kong Baptist University
Wenji Ma, Shanghai Jiao Tong University School of Medicine
Xiaoqi Zheng, Shanghai Jiao Tong University School of Medicine

Program Committee Members

Zixuan Cang, Department of Mathematics, North Carolina State University
Yanxiang Zhao, Department of Mathematics, George Washington University
Xian Fan Mallory, Department of Computer Science, Florida State University
Yunfei Hu, Department of Computer Science, Vanderbilt University
Wenjun Shen, Department of Bioinformatics, Shantou University
Zhenmiao Zhang, Department of Computer Science, UCSD
Chao Yang, Department of Computer Science, Hong Kong Baptist University
Xikang Feng, School of Software, Northwestern Polytechnic University
Dan Wang, Department of Data Science, Beijing Normal–Hong Kong Baptist University
Jiaxing Chen, Department of Computer Science, Beijing Normal–Hong Kong Baptist University
Xiaofei Zhang, Department of Mathematics, Central China Normal University
Qihuang Zhang, Department of Epidemiology, Biostatistics and Occupational Health, McGill College
Can Luo, Department of Biomedical Engineering, Vanderbilt University
Zhenhan Lin, Department of Computer Science, Vanderbilt University

Keynote Speaker

Jun Ding
Assistant Professor | Meakins-Christie Laboratories, Faculty of Medicine, McGill University.

Keynote Talk Abstract

Title: scGALA advances graph link prediction-based cell alignment for comprehensive data integration and harmonization

Abstract:
Accurate alignment of cells across heterogeneous single-cell datasets remains a fundamental bottleneck in data integration. Existing approaches rely heavily on geometric proximity in expression space and therefore struggle when datasets differ in modality, platform, or contain strong batch effects and non-linear biological relationships. These limitations propagate through downstream analyses, leading to suboptimal batch correction, label transfer, multi-omics integration, and spatial alignment. A unified and robust alignment framework is urgently needed.

In this talk, I will introduce scGALA, a graph-based learning framework that reconceptualizes cell alignment as a masked link-prediction problem. scGALA constructs comprehensive intra- and inter-dataset cell–cell graphs, applies a multi-scale Graph Attention Network to infer reliable correspondences, and refines them with an iterative score-based optimization strategy. This relational formulation enables scGALA to recover biologically coherent mappings that extend beyond local geometric similarity and flexibly incorporate auxiliary information, including multi-omics features and spatial coordinates.

Built on this enhanced alignment backbone, scGALA functions both as a universal integration module and as a standalone system capable of advanced applications, including mosaic tri-omics construction, cross-modality RNA generation from ATAC, and high-resolution spatial transcriptomics enhancement. scGALA provides a robust, scalable, and versatile foundation for harmonizing heterogeneous single-cell datasets, substantially strengthening both conventional and emerging multi-omics analyses.

Workshop Schedule (Beijing Time, December 16, 2025), location: Grand Ballroom 1, 3rd Floor

Time	Paper ID	Title	Presenter / Author
2:00-2:30pm	—	Keynote: scGALA advances graph link prediction-based cell alignment for comprehensive data integration and harmonization	Dr. Jun Ding (McGill University)
2:35-2:55pm	B1479	EMST: An Interpretable Multi-modal Model for Spatial Transcriptomic Data Analysis	Rui Han, Weiwei Yuan, Xuan Wang, and Junyi Li
3:00-3:20pm	B2321	An End-to-End Dual-View Architecture for Spatial Clustering of Spatial Transcriptomics Data by Integrating Histology Images	Xinru Xu, Shengjun Li, and Juan Wang
3:20-3:40pm	B328	scDVCC: Deep Clustering of scRNA-seq Based on Dual-View Contrastive Learning	Shudong Wang, Yue Song, Wenhao Wu, Hengxiao Li, Yulin Zhang, and Shanchen Pang
3:40-4:00pm	B774	An Adaptive Single-cell Sequencing Data Cluster Method under Weight Fusion Constraint	Zhenchang Wang, Shasha Yuan, Feng Li, and Juan Wang
4:00-4:20pm	B1857	scGZDC: Graph-based ZINB Deep Clustering for Single-cell RNA-seq Data	Hui-Bo Tian, Xiang-Zhen Kong, Jin-Xing Liu, Jun-Liang Shang, Juan Wang, and Ling-Yun Dai
4:20-4:40pm	B1953	Consistency-Constrained Contrastive Learning with Hard-Negative for Spatial Domain Identification	Fanghui Zhou, Linjie Wang, Huixia Zhang, and Wei Li
4:40-5:00pm	B2159	SpaMSC: Multi-Scale Subgraph Contrastive Learning for Deciphering Spatial Domains in Spatial Transcriptomics	Daohui Ge, Haonan Li, Wentian Xin, Feng Li, Ping Wang, and Yuzhuo Yuan

Registration

At least one author of an accepted paper must register as a full registration for the paper to be included in the conference proceedings.

Workshop Submission Requirement

Please submit a full-length paper (up to 8 pages in IEEE 2-column format) through the online submission system (you can download the format instruction here). Electronic submissions (in PDF or Postscript format) are required. Selected participants will be asked to submit their revised papers in a format to be specified at the time of acceptance.