Spatial patterns in the tumor microenvironment identify therapy response in breast cancer using weakly supervised learning

Description

The tumor microenvironment (TME) influences treatment response in breast cancer, yet identifying spatial patterns predictive of treatment response remains a challenge. Here we applied cyclic immunofluorescence proteomics to phenotype approximately 5.5×105 single cells from pre-treatment tissue biopsies of 13 ER-positive breast cancer patients. For each cancer cell, a radial distribution-based neighborhood was constructed by calculating the distribution of identified phenotypes up to a radius of 200 µm, resulting in a total of 2.0×105 neighborhoods. To identify responder-associated neighborhood patterns, an ensemble of neural networks combining autoencoding and multiple-instance learning was trained on sample-level response labels to neoadjuvant chemotherapy with bevacizumab. The resulting model distinguished responders from non-responders in cross-validation, ranked held-out responders above non-responders, and revealed spatially heterogeneous responder-like areas within tumors. These findings demonstrate that weakly supervised learning of spatial proteomic data can identify clinically relevant TME structures associated with treatment response.

Authors

DOI: 10.5281/zenodo.20341000

Publication Date: 2026-05-22

Back to publications list


About