Graph deep learning for the characterization of tumour microenvironments from spatial protein profiles in tissue specimens
Open accessPublished version of a preprint
The DOI matches its Crossref record; 50 of the 50 references it cites were found in a registry or an index.
Abstract
Multiplexed immunofluorescence imaging allows the multidimensional molecular profiling of cellular environments at subcellular resolution. However, identifying and characterizing disease-relevant microenvironments from these rich datasets is challenging. Here we show that a graph neural network that leverages spatial protein profiles in tissue specimens to model tumour microenvironments as local subgraphs captures distinctive cellular interactions associated with differential clinical outcomes. We applied this spatial cellular-graph strategy to specimens of human head-and-neck and colorectal cancers assayed with 40-plex immunofluorescence imaging to identify spatial motifs associated with cancer recurrence and with patient survival after treatment. The graph deep learning model was substantially more accurate in predicting patient outcomes than deep learning approaches that model spatial data on the basis of the local composition of cell types, and it generated insights into the effect of the spatial compartmentalization of tumour cells and granulocytes on patient prognosis. Local graphs may also aid in the analysis of disease-relevant motifs in histology samples characterized via spatial transcriptomics and other -omics techniques.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“These systems are capable of identifying subtle patterns and anomalies that may elude human observation, enabling earlier detection of conditions such as tumors, fractures, and neurological disorders.86”
From A foundational architecture for AI agents in healthcare (2025) · cites this paper as [86]
In the citing paper
“For spatial omics analysis, a graph-based deep learning algorithm has been developed to predict patient outcomes from spatial proteomics profiling [138], facilitating the identification of disease–phenotype-specific tumor microenvironment patterns.”
From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [138]
In the citing paper
“Prognostic AI models for colorectal cancer have been developed for various data modalities, including MRI (88), histopathology (89-91), and multiplex imaging (92,93).”
From Artificial Intelligence in Oncology: Current Landscape, Challenges, and Future Directions (2024) · cites this paper as [92]
Citations
Cites
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016
PyTorch: An Imperative Style, High-Performance Deep Learning Library
Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.01703 · Cited by 31,473
Fast unfolding of communities in large networks
Blondel, V. D., Guillaume, J.-L., Lambiotte, R., & Lefebvre, E. (2008) · Journal of Statistical Mechanics: Theory and Experiment · doi:10.1088/1742-5468/2008/10/p10008 · Cited by 21,424 · cited 1×
“We constructed a k -nearest neighbour graph ( k = 30) on the top 20 PCs of the expression matrix and then performed Louvain graph clustering 41 on the result.”
MethodA Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“GNNs 17,18 , a class of deep learning methods designed for graph structures, have been applied to a variety of analysis tasks, including cell-type prediction 19 , representation learning 20 , cellular communication modelling 21 and tissue structure detection 22 .”
BackgroundSelf-citationUMAP: Uniform Manifold Approximation and Projection
McInnes, L., Healy, J., Saul, N., & Großberger, L. (2018) · Journal of Open Source Software · doi:10.21105/joss.00861 · Cited by 9,826
UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
McInnes, L., Healy, J., & Melville, J. (2018) · arXiv · doi:10.48550/arxiv.1802.03426 · Cited by 7,101
Neural Message Passing for Quantum Chemistry
Gilmer, J., Schoenholz, S. S., Riley, P. F., Vinyals, O., & Dahl, G. E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1704.01212 · Cited by 3,440 · cited 1×
“GNNs 17,18 , a class of deep learning methods designed for graph structures, have been applied to a variety of analysis tasks, including cell-type prediction 19 , representation learning 20 , cellular communication modelling 21 and tissue structure detection 22 .”
BackgroundSlide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution
Rodriques, S. G., Stickels, R. R., Goeva, A., Martin, C. A., Murray, E., Vanderburg, C. R., Welch, J., Chen, L. M., Chen, F., & Macosko, E. Z. (2019) · Science · doi:10.1126/science.aaw1219 · Cited by 2,424
Regev, A., Teichmann, S. A., Lander, E. S., Amit, I., Benoist, C., Birney, E., Bodenmiller, B., Campbell, P., Carninci, P., Clatworthy, M., et al. (2017) · eLife · doi:10.7554/elife.27041 · Cited by 2,232 · cited 1×
“Comprehensive results from human cell consortia efforts 37,38 , as well as computational methods that accommodate unseen cell types 19 , could potentially be incorporated to overcome these limitations.”
BackgroundArgiris, A., Karamouzis, M. V., Raben, D., & Ferris, R. L. (2008) · The Lancet · doi:10.1016/s0140-6736(08)60728-x · Cited by 2,224
Research works printed but not linked: 8
- Xu, K., Hu, W., Leskovec, J. & Jegelka, S. How powerful are graph neural networks? In Proc.7th International Conference on Learning Representations (OpenReview, 2019); https://openreview.net/forum?id=ryGs6iA5Km
- Kvamme, H., Borgan, Ø. & Scheel, I. Time-to-event prediction with neural networks and Cox regression. J. Mach. Learn. Res. 20, 1–30 (2019).
- Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In Proc. 3rd International Conference on Learning Representations (ICLR, 2015); https://www.iclr.cc/archive/www/2015.html
- Kipf, T. N., & Welling, M. Semi-supervised classification with graph convolutional networks. In Proc. 5th International Conference on Learning Representations (OpenReview, 2017); https://openreview.net/forum?id=SJU4ayYgl
- Veličković, P. et al. Graph attention networks. In Proc. 6th International Conference on Learning Representations (OpenReview, 2018); https://openreview.net/forum?id=rJXMpikCZ
- Hamilton, W., Ying, Z., & Leskovec, J. Inductive representation learning on large graphs. In Proc. 31st International Conference on Neural Information Processing Systems 1025–1035 (Curran Associates, 2017).
- Li, Y., Tarlow, D., Brockschmidt, M. & Zemel, R. Gated graph sequence neural networks. In Proc. 4th International Conference on Learning Representations (OpenReview, 2016); https://openreview.net/forum?id=HSgW989Kp-q
- Vinyals, O., Bengio, S. & Kudlur, M. Order matters: sequence to sequence for sets. In Proc. 4th International Conference on Learning Representations (ICLR, 2016); https://www.iclr.cc/archive/www/2016.html
Cited by
Swanson, K., Wu, E., Zhang, A., Alizadeh, A. A., & Zou, J. (2023) · Cell · doi:10.1016/j.cell.2023.01.035 · Cited by 597
“One method of combining the two is through biomedical technologies such as CODEX and spatial transcriptomics, which overlay spatially resolved proteomics and transcriptomics data on images, allowing models to process omics data in image form.(49,88,135) Another promising direction is the development of multimodal mode…”
BackgroundMethodSelf-citationHow to build the virtual cell with artificial intelligence: Priorities and opportunities
Bunne, C., Roohani, Y., Rosen, Y., Gupta, A., Zhang, X., Roed, M., Alexandrov, T., AlQuraishi, M., Brennan, P., Burkhardt, D. B., et al. (2024) · Cell · doi:10.1016/j.cell.2024.11.015 · Cited by 393
“152,153 In both cases, the graph represents how nodes are physically proximal to each other.”
Artificial intelligence for digital and computational pathology
Song, A. H., Jaume, G., Williamson, D. F. K., Lu, M. Y., Vaidya, A., Miller, T. R., & Mahmood, F. (2023) · Nature Reviews Bioengineering · doi:10.1038/s44222-023-00096-8 · Cited by 356
“5b), learn the correspondence between global and local level details 40 or reconstruct randomly masked regions in patches 213 , all of which originated from SSL techniques developed for natural images.”
BackgroundProfiling cell identity and tissue architecture with single-cell and spatial transcriptomics
Gulati, G. S., D’Silva, J. P., Liu, Y., Wang, L., & Newman, A. M. (2025) · Nature Reviews Molecular Cell Biology · doi:10.1038/s41580-024-00768-2 · Cited by 293
“…regions that exhibit distinct intercellular signalling patterns 206 , capture similarities and differences in tissue architecture between different lymphoid organs 207 , and identify multicellular neighbourhood motifs associated with treatment outcomes in retrospective cancer cohorts 203,205 .”
InfluentialCellCharter reveals spatial cell niches associated with tissue remodeling and cell plasticity
Varrone, M., Tavernari, D., Santamaria-Martínez, A., Walsh, L. A., & Ciriello, G. (2024) · Nature Genetics · doi:10.1038/s41588-023-01588-4 · Cited by 210
“SPACE-GM uses a GNN to perform supervised learning on patient clinical outcome 33 .”
Metadata
- Authors
- Wu, Z., Trevino, A. E., Wu, E., Swanson, K., Kim, H. J., D’Angio, H. B., Preska, R., Charville, G. W., Dalerba, P. D., Egloff, A. M., Uppaluri, R., Duvvuri, U., Mayer, A. T., & Zou, J.
- Affiliations
- Stanford University (US)
- Stanford Medicine (US)
- Columbia University (US)
- Brigham and Women's Hospital (US)
- University of Pittsburgh (US)
- Corresponding author
- Trevino, Alexandro E.
- Mayer, Aaron T.
- Zou, James
- ORCID
- Venue
- Nature Biomedical Engineering
- Published
- 2022-11-10
- Volume
- 6
- Issue
- 12
- Pages
- 1435-1448
- ISSN
- 2157-846X (ISSN-L)
- OpenAlex
- W4308770506
- Cited by
- 154
- References
- 46
- Citations by year
- 2026: 32 · 2025: 52 · 2024: 41 · 2023: 27 · 2022: 2
- FWCI
- 9.96
- Type
- journal article
- Language
- en
- Open access
- green
- doi.org
- Licence
- cc-by-nc-nd
- www.springernature.com/gp/researchers/text-and-data-mining (tdm)
- www.springernature.com/gp/researchers/text-and-data-mining (vor)
- Locations
- Nature Biomedical Engineering (publishedVersion)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- The HKU Scholars Hub (University of Hong Kong) (submittedVersion)
- Funders
- National Science Foundation (1942926, CAREER)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Single-cell and spatial transcriptomics
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Health Sciences › Medicine › Oncology › Cancer Immunotherapy and Biomarkers
- Keywords
- tumor microenvironment, graph neural networks, head and neck cancer, colorectal cancer, tumor recurrence, patient survival prediction, granulocytes, prognosis
- MeSH terms
- Deep Learning, Humans, Neural Networks, Computer, Gene Expression Profiling, Tumor Microenvironment
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Graph deep learning for the characterization of tumour microenvironments from spatial protein profiles in tissue specimens. https://app.cochat.ai/papers/10.1038/s41551-022-00951-w
- The paper
- Wu, Z., Trevino, A. E., Wu, E., Swanson, K., Kim, H. J., D’Angio, H. B., Preska, R., Charville, G. W., Dalerba, P. D., Egloff, A. M., Uppaluri, R., Duvvuri, U., Mayer, A. T., & Zou, J. (2022). Graph deep learning for the characterization of tumour microenvironments from spatial protein profiles in tissue specimens. Nature Biomedical Engineering. https://doi.org/10.1038/s41551-022-00951-w
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.