journal article·2026-07Open access

Combining Spatial Multi‐Omics Data to Decipher Spatial Domains and Elucidate Cell Heterogeneity Based on Self‐Supervised Graph Learning

Yuejing Lu, Rui Qiao, Ying Li, Junhong Li, Nuoya Yue, Jing Ge, Jiao Wang, Luonan Chen, Peiluan Li

Advanced Science· Volume 13· Issue 42

Abstract

ABSTRACT Spatial multi‐omics technologies enable in situ molecular profiling but face challenges in integrating multi‐modal data for spatial domain identification and cell heterogeneity analysis. We propose SOTMGF, a self‐supervised, goal‐directed multi‐view graph fusion framework for spatial multi‐omics data. SOTMGF includes five modules: pre‐clustering, sparse feature processing, multi‐view feature extraction and fusion (integrating molecular expression, spatial location, disease microenvironment, and molecular associations), and multi‐modality integration. The self‐training process and graph embedding are optimized iteratively within a unified framework, enabling mutual benefits across several components. SOTMGF outperformed existing methods in spatial domain identification, data denoising, and detection of spatially variable molecular features. Innovatively, it jointly analyzes spatial transcriptomics (ST) and proteomics (SP) from the same tissue, computationally generates spatial ATAC‐seq via Tangram, reconstructs spatial pseudo‐expression to identify spatial dark genes/proteins (SDGs/SDPs), and iteratively optimizes self‐training and graph embedding in a unified framework. SOTMGF outperforms existing methods in spatial domain detection and denoising, reveals mRNA‐protein discordance, predicts key transcription factors, and aids biomarker and therapeutic target discovery, advancing spatial biology research, molecular regulatory mechanisms, and therapeutic discovery.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Single-cell and spatial transcriptomics · Bioinformatics and Genomic Networks · Cell Image Analysis Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

School of Mathematics and Statistics Henan University of Science and Technology Luoyang China

School of Artificial Intelligence Wuhan University Wuhan China

College of Electronic and Information Engineering Shenzhen University Shenzhen Guangdong China

School of Life Sciences Shanghai University Shanghai China

Shanghai Immune Therapy Institute Renji Hospital, Shanghai Jiao Tong University School of Medicine Shanghai China

School of Life Science and Technology Shandong Vocational University of Foreign Affairs Jinan China

Department of Rehabilitation Medicine The Affiliated Taian City Central Hospital of Qingdao University Shandong China

Key Laboratory of Biotechnology and Bioengineering of State Ethnic Affairs Commission Northwest Minzu University Lanzhou Gansu China

School of Mathematical Sciences and School of AI Shanghai Jiao Tong University Shanghai China

Tianfu Jincheng Laboratory Chengdu China

Key Laboratory of Systems Health Science of Zhejiang Province, Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou China

Guangdong Provincial Key Laboratory of Mathematical and Neural Dynamical Systems Great Bay University Dongguan China

Funding

National Natural Science Foundation of China · National Key Research and Development Program of China · Natural Science Foundation of Henan Province · Natural Science Foundation of Shandong Province

References (73)

Show source-provided references
1. 10.1126/science.abq496410.1126/science.abq4964 ↗
2. 10.1038/s41576‐023‐00580‐210.1038/s41576‐023‐00580‐2 ↗
3. 10.1016/j.ccell.2023.01.01010.1016/j.ccell.2023.01.010 ↗
4. 10.1038/s41467‐018‐04724‐510.1038/s41467‐018‐04724‐5 ↗
5. 10.1038/s41467‐022‐29439‐610.1038/s41467‐022‐29439‐6 ↗
6. 10.1038/s41467‐022‐31739‐w10.1038/s41467‐022‐31739‐w ↗
7. conST: An Interpretable Multi‐Modal Contrastive Learning Framework for Spatial Transcriptomics
8. 10.1093/nar/gkac90110.1093/nar/gkac901 ↗
9. 10.34133/research.022810.34133/research.0228 ↗
10. 10.1038/s41590‐023‐01471‐810.1038/s41590‐023‐01471‐8 ↗
11. 10.1038/s41587‐022‐01536‐310.1038/s41587‐022‐01536‐3 ↗
12. 10.1038/s41592‐021‐01358‐210.1038/s41592‐021‐01358‐2 ↗
13. 10.1038/s41467‐022‐34867‐510.1038/s41467‐022‐34867‐5 ↗
14. 10.1038/s41590‐023‐01678‐910.1038/s41590‐023‐01678‐9 ↗
15. 10.1038/s41592‐024‐02316‐410.1038/s41592‐024‐02316‐4 ↗
16. 10.1038/s41592‐024‐02574‐210.1038/s41592‐024‐02574‐2 ↗
17. 10.1038/s41587‐022‐01273‐710.1038/s41587‐022‐01273‐7 ↗
18. 10.1038/s41592‐023‐01909‐910.1038/s41592‐023‐01909‐9 ↗
19. 10.1093/nar/gkz43010.1093/nar/gkz430 ↗
20. 10.1038/s41568‐019‐0196‐710.1038/s41568‐019‐0196‐7 ↗
21. 10.1093/nar/gkz44610.1093/nar/gkz446 ↗
22. 10.7150/jca.2231910.7150/jca.22319 ↗
23. 10.7150/ijbs.5347710.7150/ijbs.53477 ↗
24. 10.1126/sciadv.abq483110.1126/sciadv.abq4831 ↗
25. 10.1158/0008‐5472.CAN‐05‐106910.1158/0008‐5472.CAN‐05‐1069 ↗
26. 10.1177/106689691142703510.1177/1066896911427035 ↗
27. 10.3390/ijms2315870210.3390/ijms23158702 ↗
28. NOTCH4 is a Potential Therapeutic Target for Triple‐Negative Breast Cancer
29. 10.1186/s12943‐018‐0797‐x10.1186/s12943‐018‐0797‐x ↗
30. 10.1038/s41392‐024‐01828‐x10.1038/s41392‐024‐01828‐x ↗
31. 10.1186/s13073‐024‐01283‐x10.1186/s13073‐024‐01283‐x ↗
32. 10.1007/BF0190807510.1007/BF01908075 ↗
33. 10.1016/j.jmva.2006.11.01310.1016/j.jmva.2006.11.013 ↗
34. 10.1016/0377‐0427(87)90125‐710.1016/0377‐0427(87)90125‐7 ↗
35. 10.1038/s41593‐020‐00787‐010.1038/s41593‐020‐00787‐0 ↗
36. 10.1093/bioinformatics/btaf30310.1093/bioinformatics/btaf303 ↗
37. 10.1038/s41586‐021‐03775‐x10.1038/s41586‐021‐03775‐x ↗
38. 10.1093/nargab/lqae10010.1093/nargab/lqae100 ↗
39. 10.1242/dev.127.5.101710.1242/dev.127.5.1017 ↗
40. 10.1038/nn76110.1038/nn761 ↗
41. 10.1016/j.neuroscience.2018.06.03210.1016/j.neuroscience.2018.06.032 ↗
42. 10.1038/4679410.1038/46794 ↗
43. 10.1111/j.1440‐169X.2008.00993.x10.1111/j.1440‐169X.2008.00993.x ↗
44. 10.1016/j.biocel.2008.03.01410.1016/j.biocel.2008.03.014 ↗
45. 10.1038/s41598‐018‐32134‐610.1038/s41598‐018‐32134‐6 ↗
46. 10.1210/me.2005‐051810.1210/me.2005‐0518 ↗
47. 10.1007/s00441‐018‐2859‐110.1007/s00441‐018‐2859‐1 ↗
48. 10.1016/j.cub.2006.01.05510.1016/j.cub.2006.01.055 ↗
49. 10.1038/s41587‐021‐00935‐210.1038/s41587‐021‐00935‐2 ↗
50. 10.1038/s41467‐022‐33619‐910.1038/s41467‐022‐33619‐9 ↗
51. 10.1038/nri376610.1038/nri3766 ↗
52. 10.1146/annurev‐immunol‐032713‐12021110.1146/annurev‐immunol‐032713‐120211 ↗
53. 10.1101/cshperspect.a02852210.1101/cshperspect.a028522 ↗
54. 10.3389/fimmu.2019.0107810.3389/fimmu.2019.01078 ↗
55. 10.1186/s12885‐022‐10485‐810.1186/s12885‐022‐10485‐8 ↗
56. 10.14715/cmb/2020.66.5.3210.14715/cmb/2020.66.5.32 ↗
57. 10.1126/science.117600910.1126/science.1176009 ↗
58. 10.1038/s41598‐018‐35710‐y10.1038/s41598‐018‐35710‐y ↗
59. 10.1002/ctm2.161110.1002/ctm2.1611 ↗
60. 10.1016/j.gendis.2022.05.02010.1016/j.gendis.2022.05.020 ↗
61. 10.1146/annurev.immunol.21.120601.14094610.1146/annurev.immunol.21.120601.140946 ↗
62. 10.1126/science.aaa609010.1126/science.aaa6090 ↗
63. 10.1016/j.cell.2020.09.05610.1016/j.cell.2020.09.056 ↗
64. 10.1038/s41592‐021‐01264‐710.1038/s41592‐021‐01264‐7 ↗
65. 10.1038/s41467‐021‐24469‐y10.1038/s41467‐021‐24469‐y ↗
66. 10.1186/s13059‐024‐03213‐x10.1186/s13059‐024‐03213‐x ↗
67. 10.34133/research.008010.34133/research.0080 ↗
68. C.Wang S.Pan R.Hu G.Long J.Jiang andC.Zhang “Attributed Graph Clustering: A Deep Attentional Embedding Approach ”In Proceedings of the 28th International Joint Conference on Artificial Intelligence(2019):3670–3676 https://dl.acm.org/doi/10.5555/3367471.3367551.10.24963/ijcai.2019/509 ↗
69. 10.1089/cmb.2021.031610.1089/cmb.2021.0316 ↗
70. 10.1109/TCSVT.2022.323260410.1109/TCSVT.2022.3232604 ↗
71. 10.1016/j.gpb.2020.05.00510.1016/j.gpb.2020.05.005 ↗
72. 10.1038/s41586‐021‐03705‐x10.1038/s41586‐021‐03705‐x ↗
73. 10.1186/s12864‐022‐08601‐w10.1186/s12864‐022‐08601‐w ↗