Proximity-guided graph learning reveals tumour-associated proximity antigens
- 1InduPro, Cambridge, MA USA
- 2InduPro, Seattle, WA USA
Abstract
The spatial organization of membrane proteins is an underexplored dimension of cell surface biology1,2. Spatial proximity shapes cellular function and therapeutic targetability2,3, yet efforts to identify tumour-associated antigens (TAAs) have largely focused on expression alone4. Here, we developed an industrialized surface protein proximity-mapping workflow to interrogate TAAs within their membrane microenvironments. Using this workflow, we generated 248 proximity maps across 12 receptor tyrosine kinases and 28 tumour cell systems. The resulting atlas enabled the development of MetaMap, a correlation-based analytical framework that defines spatial protein communities and infers conserved proximity relationships among non-targeted proteins, and establishes the concept of tumour-associated proximity antigens (TAPAs), a class of co-targets defined by disease-specific spatial proximity to TAAs rather than expression alone. Integrating these proximity-derived relationships within a multimodal prioritization framework, we identified and validated EGFR–CDCP1 as a TAA–TAPA pair that enhances tumour cell killing across therapeutic modalities. Together, this work advances disease-associated membrane proximity as a guiding principle for the design of precision multispecific therapeutics.
Related
- Environmental complexity reveals memory-guided search as the locus of learning in prey capture
- Active-learning-guided optimization of cell-free systems for genome-wide transcriptomic profiling reveals progressive layers of regulation
- AI-guided deep visual proteomics reveals recurrence-associated morpho-molecular signatures within triple-negative breast cancers
- Longitudinal linear-epitope profiling of SLE identifies novel antigens associated with disease and disease activity
- CUBE: Multimodal Representation Learning Reveals Biological Structure Across Histomorphology, Spatial Protein Phenotypes, and Transcriptome-Associated Signals
BibTeX
@article{scandore2026proximityguided,
title = {{Proximity-guided graph learning reveals tumour-associated proximity antigens}},
author = {Cody Scandore and Clare F. Malone and Christopher K. May and Anna K. de Regt and Jeff Guernsey and Hayley Ma and Noah Dephoure and Ben Setter and Rebecca A. Howell and Kendall R. Johnson and Carol L. Farr and Sophia Romero and Lydia Vignale and Tali Vittum and Emma Dawson and Tsadik Habtetsion and Francesca Nardi and Brian Woodruff and Martin Mathay and Julia Swanson and Mikaela Rusnak and Quynh Ton and Payam E. Farahani and Robert W. Gene and Jason Misurelli and Zach Caldwell and Hengyu Xu and Michael Hornsby and Marc A. Gavin and Heath E. Klock and Ertan Eryilmaz and Pamela M. Holland and Scott A. Lesley and Rob C. Oslund and Olugbeminiyi O. Fadeyi},
journal = {Nature},
year = {2026},
month = sep,
doi = {10.1038/s41586-026-11003-7},
url = {https://doi.org/10.1038/s41586-026-11003-7},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Proximity-guided graph learning reveals tumour-associated proximity antigens
AU - Cody Scandore
AU - Clare F. Malone
AU - Christopher K. May
AU - Anna K. de Regt
AU - Jeff Guernsey
AU - Hayley Ma
AU - Noah Dephoure
AU - Ben Setter
AU - Rebecca A. Howell
AU - Kendall R. Johnson
AU - Carol L. Farr
AU - Sophia Romero
AU - Lydia Vignale
AU - Tali Vittum
AU - Emma Dawson
AU - Tsadik Habtetsion
AU - Francesca Nardi
AU - Brian Woodruff
AU - Martin Mathay
AU - Julia Swanson
AU - Mikaela Rusnak
AU - Quynh Ton
AU - Payam E. Farahani
AU - Robert W. Gene
AU - Jason Misurelli
AU - Zach Caldwell
AU - Hengyu Xu
AU - Michael Hornsby
AU - Marc A. Gavin
AU - Heath E. Klock
AU - Ertan Eryilmaz
AU - Pamela M. Holland
AU - Scott A. Lesley
AU - Rob C. Oslund
AU - Olugbeminiyi O. Fadeyi
PY - 2026
DA - 2026/09/09
JO - Nature
DO - 10.1038/s41586-026-11003-7
UR - https://doi.org/10.1038/s41586-026-11003-7
AB - The spatial organization of membrane proteins is an underexplored dimension of cell surface biology1,2. Spatial proximity shapes cellular function and therapeutic targetability2,3, yet efforts to identify tumour-associated antigens (TAAs) have largely focused on expression alone4. Here, we developed an industrialized surface protein proximity-mapping workflow to interrogate TAAs within their membrane microenvironments. Using this workflow, we generated 248 proximity maps across 12 receptor tyrosine kinases and 28 tumour cell systems. The resulting atlas enabled the development of MetaMap, a correlation-based analytical framework that defines spatial protein communities and infers conserved proximity relationships among non-targeted proteins, and establishes the concept of tumour-associated proximity antigens (TAPAs), a class of co-targets defined by disease-specific spatial proximity to TAAs rather than expression alone. Integrating these proximity-derived relationships within a multimodal prioritization framework, we identified and validated EGFR–CDCP1 as a TAA–TAPA pair that enhances tumour cell killing across therapeutic modalities. Together, this work advances disease-associated membrane proximity as a guiding principle for the design of precision multispecific therapeutics.
SN - 0028-0836
SN - 1476-4687
ER -