{"type":"ScholarlyArticle","title":"Image-Enhanced Hybrid Encoding with Reinforced Contrastive Learning for Spatial Domain Identification in Spatial Transcriptomics","authors":[{"name":"Daoyuan Wang","slug":"daoyuan-wang","given":"Daoyuan","family":"Wang","affiliation":"School of Computer Science and Engineering , Central South University , Changsha 410083 , China"},{"name":"Lu Gao","slug":"lu-gao","given":"Lu","family":"Gao","affiliation":"School of Computer Science and Engineering , Central South University , Changsha 410083 , China"},{"name":"Wenlan Chen","slug":"wenlan-chen","given":"Wenlan","family":"Chen","affiliation":"School of Computer Science and Engineering , Central South University , Changsha 410083 , China"},{"name":"Cheng Liang","slug":"cheng-liang","given":"Cheng","family":"Liang","affiliation":"School of Information Science and Engineering , Shandong Normal University , Jinan 250358 , China"},{"name":"Fei Guo","slug":"fei-guo","given":"Fei","family":"Guo","affiliation":"School of Computer Science and Engineering , Central South University , Changsha 410083 , China"}],"abstract":"Spatial transcriptomics integrates spatial, gene expression, and multichannel immunohistochemistry image data, enabling advanced insights into cellular organization. However, existing methods often struggle to effectively fuse these multimodal data, limiting their potential for accurate spatial domain identification. Here, we propose IE-HERCL (Image-Enhanced Hybrid Encoding with Reinforced Contrastive Learning), a novel framework designed to address this challenge. Specifically, IE-HERCL employs hybrid encoding to capture both the non-spatial features and spatial dependencies for both gene and image modalities via autoencoders and GraphSAGE, respectively. These features are then fused using cross-view attention mechanisms to generate the unified informative embedding. To enhance the representation learning capability, we introduce a reinforced contrastive learning strategy to mitigate the influences of false negative samples, where we detect potential positive counterparts with high-order random walks. In addition, the cluster alignment is dynamically refined through optimal transport, which ensures that the fused consensus representation is coherent and robust, enabling accurate spatial domain identification. Our approach achieves state-of-the-art performance on five image-enhanced spatial transcriptomics datasets, demonstrating its robustness and effectiveness in multimodal integration and spatial domain identification. IE-HERCL offers a powerful and innovative solution for advancing spatial transcriptomics analysis. The code is released on https://github.com/wdyi701/IE-HERCL.","doi":"10.24963/ijcai.2025/864","url":"https://ijcai.org/proceedings/2025/864","pdf":"https://ijcai.org/proceedings/2025/0864.pdf","markdown":"https://ijcai.org/proceedings/2025/864.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/864","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":864,"pages":{"first":7769,"last":7777},"keywords":["Multidisciplinary Topics and Applications: MTA: Bioinformatics","Machine Learning: ML: Multi-view learning","Machine Learning: ML: Clustering","Machine Learning: ML: Unsupervised learning"],"videos":[],"references":[{"position":1,"raw":"[Budhkar et al., 2024] Aishwarya Budhkar, Ziyang Tang, Xiang Liu, Xuhong Zhang, Jing Su, and Qianqian Song. xsigra: explainable model for single-cell spatial data eluci- dation. Briefings in Bioinformatics, 25(5):bbae388, 2024.","title":"xsigra: explainable model for single-cell spatial data elucidation","authors":"Budhkar","year":"2024","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cao and Gao, 2022] Zhi-Jie Cao and Ge Gao. Multi- omics single-cell data integration and regulatory infer- ence with graph-linked embedding. Nature Biotechnology, 40(10):1458-1466, 2022.","title":"Multiomics single-cell data integration and regulatory inference with graph-linked embedding","authors":"Gao ; ] Zhi-Jie Cao, Ge Cao, Gao","year":"2022","venue":"Nature Biotechnology","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Dong and Zhang, 2022] Kangning Dong and Shihua Zhang. Deciphering spatial domains from spatially resolved tran- scriptomics with an adaptive graph attention auto-encoder. Nature communications, 13(1):1739, 2022.","title":"Deciphering spatial domains from spatially resolved transcriptomics with an adaptive graph attention auto-encoder","authors":"Dong, Zhang, Kangning Dong, Shihua Zhang","year":"2022","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Hamilton et al., 2017] Will Hamilton, Zhitao Ying, and Jure Leskovec. Inductive representation learning on large graphs. Advances in neural information processing sys- tems, 30, 2017.","title":"Inductive representation learning on large graphs","authors":"Hamilton","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Hu et al., 2021] Jian Hu, Xiangjie Li, Kyle Coleman, Amelia Schroeder, Nan Ma, David J Irwin, Edward B Lee, Russell T Shinohara, and Mingyao Li. Spagcn: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph con- volutional network. Nature methods, 18(11):1342-1351, 2021.","title":"Spagcn: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network","authors":"Jian Hu, Xiangjie Li, Kyle Coleman, Amelia Schroeder, Nan Ma, David J Irwin, Edward B Lee, Russell T Shinohara, Mingyao Li","year":"2021","venue":"Nature methods","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hu et al., 2024] Yaofeng Hu, Kai Xiao, Hengyu Yang, Xi- aoping Liu, Chuanchao Zhang, and Qianqian Shi. Spa- tially contrastive variational autoencoder for decipher- ing tissue heterogeneity from spatially resolved transcrip- tomics. Briefings in Bioinformatics, 25(2):bbae016, 2024.","title":"Spatially contrastive variational autoencoder for deciphering tissue heterogeneity from spatially resolved transcriptomics","authors":"Yaofeng Hu, Kai Xiao, Hengyu Yang, Xiaoping Liu, Chuanchao Zhang, Qianqian Shi","year":"2024","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Huang et al., 2024] Jinjin Huang, Xiaoqian Fu, Zhuangli Zhang, Yinfeng Xie, Shangkun Liu, Yarong Wang, Zhi- hong Zhao, and Youmei Peng. A graph self-supervised residual learning framework for domain identification and data integration of spatial transcriptomics. Communica- tions Biology, 7(1):1123, 2024.","title":"A graph self-supervised residual learning framework for domain identification and data integration of spatial transcriptomics","authors":"Jinjin Huang, Xiaoqian Fu, Zhuangli Zhang, Yinfeng Xie, Shangkun Liu, Yarong Wang, Zhihong Zhao, Youmei Peng","year":"2024","venue":"Communications Biology","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Jia et al., 2024] Yuran Jia, Junliang Liu, Li Chen, Tianyi Zhao, and Yadong Wang. Thitogene: a deep learning method for predicting spatial transcriptomics from histological images. Briefings in Bioinformatics, 25(1):bbad464, 2024.","title":"Thitogene: a deep learning method for predicting spatial transcriptomics from histological images","authors":"Yuran Jia, Junliang Liu, Li Chen, Tianyi Zhao, Yadong Wang","year":"2024","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Jiang et al., 2024] Xi Jiang, Shidan Wang, Lei Guo, Ben- cong Zhu, Zhuoyu Wen, Liwei Jia, Lin Xu, Guanghua Xiao, and Qiwei Li. iimpact: integrating image and molec- ular profiles for spatial transcriptomics analysis. Genome Biology, 25(1):147, 2024.","title":"iimpact: integrating image and molecular profiles for spatial transcriptomics analysis","authors":"Xi Jiang, Shidan Wang, Lei Guo, Bencong Zhu, Zhuoyu Wen, Liwei Jia, Lin Xu, Guanghua Xiao, Qiwei Li","year":"2024","venue":"Genome Biology","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Long et al., 2023] Yahui Long, Kok Siong Ang, Mengwei Li, Kian Long Kelvin Chong, Raman Sethi, Chengwei Zhong, Hang Xu, Zhiwei Ong, Karishma Sachaphibulkij, and Ao Chen. Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with graphst. Nature Communications, 14(1):1155, 2023.","title":"Spatially informed clustering, integration, and deconvolution of spatial transcriptomics with graphst","authors":"Yahui Long, Siong Kok, Mengwei Ang, Kian Li, Kelvin Long, Raman Chong, Chengwei Sethi, Hang Zhong, Zhiwei Xu, Karishma Ong, Ao Sachaphibulkij, Chen","year":"2023","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Long et al., 2024] Yahui Long, Kok Siong Ang, Raman Sethi, Sha Liao, Yang Heng, Lynn van Olst, Shuchen Ye, Chengwei Zhong, Hang Xu, and Di Zhang. Deciphering spatial domains from spatial multi-omics with spatialglue. Nature Methods, pages 1-10, 2024.","title":"Deciphering spatial domains from spatial multi-omics with spatialglue","authors":"Yahui Long, Siong Kok, Raman Ang, Sha Sethi, Yang Liao, Lynn Heng, Shuchen Van Olst, Chengwei Ye, Hang Zhong, Di Xu, Zhang","year":"2024","venue":"Nature Methods","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Ma and Zhou, 2022] Ying Ma and Xiang Zhou. Spatially informed cell-type deconvolution for spatial transcrip- tomics. Nature biotechnology, 40(9):1349-1359, 2022.","title":"Spatially informed cell-type deconvolution for spatial transcriptomics","authors":"Ying Ma, Xiang Zhou","year":"2022","venue":"Nature biotechnology","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Nie et al., 2024] Wan Nie, Yingying Yu, Xueying Wang, Ruohan Wang, and Shuai Cheng Li. Spatially informed graph structure learning extracts insights from spatial tran- scriptomics. Advanced Science, 11(45):2403572, 2024.","title":"Spatially informed graph structure learning extracts insights from spatial transcriptomics","authors":"Wan Nie, Yingying Yu, Xueying Wang, Ruohan Wang, Shuai Cheng, Li","year":"2024","venue":"Advanced Science","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ren et al., 2022] Honglei Ren, Benjamin L Walker, Zixuan Cang, and Qing Nie. Identifying multicellular spatiotem- poral organization of cells with spaceflow. Nature commu- nications, 13(1):4076, 2022.","title":"Identifying multicellular spatiotemporal organization of cells with spaceflow","authors":"Honglei Ren, L Benjamin, Zixuan Walker, Qing Cang, Nie","year":"2022","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Satija et al., 2015] Rahul Satija, Jeffrey A Farrell, David Gennert, Alexander F Schier, and Aviv Regev. Spatial re- construction of single-cell gene expression data. Nature biotechnology, 33(5):495-502, 2015.","title":"Spatial reconstruction of single-cell gene expression data","authors":"Rahul Satija, Jeffrey A Farrell, David Gennert, Alexander F Schier, Aviv Regev","year":"2015","venue":"Nature biotechnology","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Shi et al., 2023] Xuejing Shi, Juntong Zhu, Yahui Long, and Cheng Liang. Identifying spatial domains of spatially resolved transcriptomics via multi-view graph convolutional networks. Briefings in Bioinformatics, 24(5):bbad278, 2023.","title":"Identifying spatial domains of spatially resolved transcriptomics via multi-view graph convolutional networks","authors":"Shi","year":"2023","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Singhal et al., 2024] Vipul Singhal, Nigel Chou, Joseph Lee, Yifei Yue, Jinyue Liu, Wan Kee Chock, Li Lin, Yun- Ching Chang, Erica Mei Ling Teo, and Jonathan Aow. Banksy unifies cell typing and tissue domain segmentation for scalable spatial omics data analysis. Nature Genetics, 56(3):431-441, 2024.","title":"Banksy unifies cell typing and tissue domain segmentation for scalable spatial omics data analysis","authors":"Vipul Singhal, Nigel Chou, Joseph Lee, Yifei Yue, Jinyue Liu, Wan Kee Chock, Li Lin, Yun-Ching Chang, Erica Mei, Ling Teo, Jonathan Aow","year":"2024","venue":"Nature Genetics","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Sun et al., 2025] Xue Sun, Wei Zhang, Wenrui Li, Na Yu, Daoliang Zhang, Qi Zou, Qiongye Dong, Xianglin Zhang, Zhiping Liu, and Zhiyuan Yuan. Spagra: Graph augmenta- tion facilitates domain identification for spatially resolved transcriptomics. Journal of Genetics Genomics, 52(1):93- 104, 2025.","title":"Spagra: Graph augmentation facilitates domain identification for spatially resolved transcriptomics","authors":"Xue Sun, Wei Zhang, Wenrui Li, Na Yu, Daoliang Zhang, Qi Zou, Qiongye Dong, Xianglin Zhang, Zhiping Liu, Zhiyuan Yuan","year":"2025","venue":"Journal of Genetics Genomics","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Tang et al., 2023a] Ziyang Tang, Zuotian Li, Tieying Hou, Tonglin Zhang, Baijian Yang, Jing Su, and Qianqian Song. Sigra: single-cell spatial elucidation through an image- augmented graph transformer. Nature Communications, 14(1):5618, 2023.","title":"Sigra: single-cell spatial elucidation through an imageaugmented graph transformer","authors":"Tang","year":"2023","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Tang et al., 2023b] Ziyang Tang, Tonglin Zhang, Baijian Yang, Jing Su, and Qianqian Song. spaci: deciphering spatial cellular communications through adaptive graph model. Briefings in Bioinformatics, 24(1):bbac563, 2023.","title":"spaci: deciphering spatial cellular communications through adaptive graph model","authors":"Tang","year":"2023","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2024a] Tao Wang, Han Shu, Jialu Hu, Yongtian Wang, Jing Chen, Jiajie Peng, and Xuequn Shang. Ac- curately deciphering spatial domains for spatially resolved transcriptomics with stcluster. Briefings in Bioinformatics, 25(4):bbae329, 2024.","title":"Accurately deciphering spatial domains for spatially resolved transcriptomics with stcluster","authors":"Wang","year":"2024","venue":"Briefings in Bioinformatics","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2024b] Tianqi Wang, Huitong Zhu, Yunlan Zhou, Weihong Ding, Weichao Ding, Liangxiu Han, and Xueqin Zhang. Graph attention automatic encoder based on contrastive learning for domain recognition of spa- tial transcriptomics. Communications Biology, 7(1):1351, 2024.","title":"Graph attention automatic encoder based on contrastive learning for domain recognition of spatial transcriptomics","authors":"Wang","year":"2024","venue":"Communications Biology","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Wolf et al., 2018] F Alexander Wolf, Philipp Angerer, and Fabian J Theis. Scanpy: large-scale single-cell gene ex- pression data analysis. Genome biology, 19:1-5, 2018.","title":"Scanpy: large-scale single-cell gene expression data analysis","authors":"Alexander Wolf, Philipp Angerer, Fabian J Theis","year":"2018","venue":"Genome biology","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Yang et al., 2024] Wenyi Yang, Pingping Wang, Shouping Xu, Tao Wang, Meng Luo, Yideng Cai, Chang Xu, Guangfu Xue, Jinhao Que, and Qian Ding. Deciphering cell-cell communication at single-cell resolution for spa- tial transcriptomics with subgraph-based graph attention network. Nature Communications, 15(1):7101, 2024.","title":"Deciphering cell-cell communication at single-cell resolution for spatial transcriptomics with subgraph-based graph attention network","authors":"Wenyi Yang, Pingping Wang, Shouping Xu, Tao Wang, Meng Luo, Yideng Cai, Chang Xu, Guangfu Xue, Jinhao Que, Qian Ding","year":"2024","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Yu et al., 2024] Jixiang Yu, Nanjun Chen, Ming Gao, Xi- angtao Li, and Ka-Chun Wong. Unsupervised gene-cell collective representation learning with optimal transport. In Proceedings of the AAAI Conference on Artificial Intel- ligence, volume 38, pages 356-364, 2024.","title":"Unsupervised gene-cell collective representation learning with optimal transport","authors":"Jixiang Yu, Nanjun Chen, Ming Gao, Xiangtao Li, Ka-Chun Wong","year":"2024","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Yu et al., 2025] Zhuohan Yu, Yuning Yang, Xingjian Chen, Ka-Chun Wong, Zhaolei Zhang, Yuming Zhao, and Xi- angtao Li. Accurate spatial heterogeneity dissection and gene regulation interpretation for spatial transcriptomics using dual graph contrastive learning. Advanced Science, 12(3):e2410081, 2025.","title":"Accurate spatial heterogeneity dissection and gene regulation interpretation for spatial transcriptomics using dual graph contrastive learning","authors":"Yu","year":"2025","venue":"Advanced Science","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Yuan et al., 2024] Zhiyuan Yuan, Fangyuan Zhao, Senlin Lin, Yu Zhao, Jianhua Yao, Yan Cui, Xiao-Yong Zhang, and Yi Zhao. Benchmarking spatial clustering methods with spatially resolved transcriptomics data. Nature Meth- ods, 21(4):712-722, 2024.","title":"Benchmarking spatial clustering methods with spatially resolved transcriptomics data","authors":"Zhiyuan Yuan, Fangyuan Zhao, Senlin Lin, Yu Zhao, Jianhua Yao, Yan Cui, Xiao-Yong Zhang, Yi Zhao","year":"2024","venue":"Nature Methods","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Yuan, 2024] Zhiyuan Yuan. Mender: fast and scalable tis- sue structure identification in spatial omics data. Nature Communications, 15(1):207, 2024.","title":"Mender: fast and scalable tissue structure identification in spatial omics data","authors":"Zhiyuan Yuan","year":"2024","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Zeng et al., 2022] Yuansong Zeng, Rui Yin, Mai Luo, Jian- ing Chen, Zixiang Pan, Yutong Lu, Weijiang Yu, and Yuedong Yang. Deciphering spatial domains by integrat- ing histopathological image and tran-scriptomics via con- trastive learning. bioRxiv, page 2022.09. 30.510297, 2022.","title":"Deciphering spatial domains by integrating histopathological image and tran-scriptomics via contrastive learning","authors":"Yuansong Zeng, Rui Yin, Mai Luo, Jianing Chen, Zixiang Pan, Yutong Lu, Weijiang Yu, Yuedong Yang","year":"2022","venue":"bioRxiv","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Zhong et al., 2024] Chengwei Zhong, Kok Siong Ang, and Jinmiao Chen. Interpretable spatially aware dimension reduction of spatial transcriptomics with stamp. Nature Methods, pages 1-12, 2024.","title":"Interpretable spatially aware dimension reduction of spatial transcriptomics with stamp","authors":"Chengwei Zhong, Kok Siong Ang, Jinmiao Chen","year":"2024","venue":"Nature Methods","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Zhou et al., 2025] Yuansheng Zhou, Xue Xiao, Lei Dong, Chen Tang, Guanghua Xiao, and Lin Xu. Cooperative in- tegration of spatially resolved multi-omics data with cos- mos. Nature Communications, 16(1):27, 2025.","title":"Cooperative integration of spatially resolved multi-omics data with cosmos","authors":"Yuansheng Zhou, Xue Xiao, Lei Dong, Chen Tang, Guanghua Xiao, Lin Xu","year":"2025","venue":"Nature Communications","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zhu et al., 2024a] James Zhu, Yunguan Wang, Woo Yong Chang, Alicia Malewska, Fabiana Napolitano, Jeffrey C Gahan, Nisha Unni, Min Zhao, Rongqing Yuan, and Fangjiang Wu. Mapping cellular interactions from spa- tially resolved transcriptomics data. Nature methods, 21(10):1830-1842, 2024.","title":"Mapping cellular interactions from spatially resolved transcriptomics data","authors":"Zhu","year":"2024","venue":"Nature methods","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhu et al., 2024b] Shijia Zhu, Naoto Kubota, Shidan Wang, Tao Wang, Guanghua Xiao, and Yujin Hoshida. Stie: Single-cell level deconvolution, convolution, and cluster- ing in in situ capturing-based spatial transcriptomics. Na- ture communications, 15(1):7559, 2024.","title":"Stie: Single-cell level deconvolution, convolution, and clustering in in situ capturing-based spatial transcriptomics","authors":"Zhu","year":"2024","venue":"Nature communications","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhu et al., 2024c] Y. Zhu, X. He, C. Tang, X. Liu, Y. Liu, and K. He. Multi-view adaptive fusion net- work for spatially resolved transcriptomics data clustering. IEEE Transactions on Knowledge and Data Engineering, 36(12):8889-8900, 2024.","title":"Multi-view adaptive fusion network for spatially resolved transcriptomics data clustering","authors":"Zhu","year":"2024","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}