Identifying perturbations that boost T-cell infiltration into tumours via counterfactual learning of their spatial proteomic profiles
-
1.
California Institute of Technology
-
2.
Cedars-Sinai Medical Center
Abstract
Cancer progression can be slowed down or halted via the activation of either endogenous or engineered T cells and their infiltration of the tumour microenvironment. Here we describe a deep-learning model that uses large-scale spatial proteomic profiles of tumours to generate minimal tumour perturbations that boost T-cell infiltration. The model integrates a counterfactual optimization strategy for the generation of the perturbations with the prediction of T-cell infiltration as a self-supervised machine learning problem. We applied the model to 368 samples of metastatic melanoma and colorectal cancer assayed using 40-plex imaging mass cytometry, and discovered cohort-dependent combinatorial perturbations (CXCL9, CXCL10, CCL22 and CCL18 for melanoma, and CXCR4, PD-1, PD-L1 and CYR61 for colorectal cancer) that support T-cell infiltration across patient cohorts, as confirmed via in vitro experiments. Leveraging counterfactual-based predictions of spatial omics data may aid the design of cancer therapeutics.
Copyright and License
© 2025, The Author(s). This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
Acknowledgement
We thank I. Strazhnik for her support with figure illustrations. We thank J. Linton and M. Elowitz for support with flow cytometry workflow. We also appreciate the Ekihiro Seki lab in Cedars-Sinai Medical Center for kindly providing the HCT116 cell line. We thank A. Merchant, A. Regev, L. Cai, B. Wold, M. Polonsky, F. Eberhardt and all members of the Thomson lab for insightful discussion that greatly improved this work. We gratefully acknowledge the support of the National Institutes of Health’s Information Technology for Cancer Research (ITCR) programme and the Merkin Institute for Translational Research.
Contributions
Z.J.W. designed the model and computational experiments in consultation with A.M.X. and M.W.T. Z.J.W. and M.W.T. wrote the paper, with input from all authors. A.S.F. and Y.-J.C. performed the experiments and data preprocessing. A.B. performed the spectral analysis. Z.J.W. and M.W.T. were responsible for the overall direction and planning of the project. M.W.T. provided funding support for the project.
Supplemental Material
Supplementary discussion, figures and tables.
Files
| Name | Size | Download all |
|---|---|---|
|
md5:c07c1095ba5056653f4c578eecedba9e
|
4.2 MB | Preview Download |
|
md5:29f59f287bc790ea9041ad69bb1b1295
|
1.4 MB | Preview Download |
Additional details
- National Cancer Institute
- Informatics Technology for Cancer Research (ITCR) -
- Accepted
-
2025-01-16Accepted
- Available
-
2025-03-05Published online
- Caltech groups
- Division of Biology and Biological Engineering (BBE)
- Publication Status
- Published