Explainable machine learning-guided integrated multiomics analysis reveals macrophage-driven immune suppression in breast cancer

Despite thorough characterizations of cellular compositions within the breast tumor microenvironment (TME), their implications for disease progression and patient prognosis remain poorly understood. Unraveling these effects is vital for identifying potential targets to improve treatment outcomes. In this study, we devise an explainable machine learning (XML) pipeline to scrutinize the associations between TME cellular constituents and relapse-free survival (RFS). By applying this pipeline to estimated cell fractions in the METABRIC and TCGA datasets and comparing these results with associations to pathological complete response (pCR) after neoadjuvant chemotherapy (NAC), we create a comprehensive catalog of the TME’s role based on 5000 patient samples. Our findings reveal an unexpected dichotomy in which macrophages correlate positively with pCR but negatively with RFS, particularly within estrogen receptor-positive (ER+) and Luminal A and B (LumA/B) cancer subtypes. We show that this pattern is driven by heterogeneity in breast tumors characterized by increasing levels of macrophage infiltration. Through imaging mass cytometry (IMC) data analysis, we find that macrophages tend to accumulate in the vicinity of HLA-ABChi epithelial cells as their frequency increases in tumor tissues and that they also express elevated levels of HLA-ABC protein. In both IMC and single-cell RNA sequencing (scRNA-seq) data, we uncover a significant association between these HLA-ABChi macrophages and regulatory and exhausted T cells (TReg and TEx), suggesting their involvement in immune suppression, likely by creating a chronically activated immunosuppressive TME. Subsequent cell-cell communication analysis predicts interactions between HLA-ABChi macrophages and TEx cells via the ligands SIGLEC9, ALCAM, and CSF1, and with TReg cells through APP, ANGPTL4, and SIGLEC9 signaling. Considering the clinical relevance of macrophages in ER+ (LumA/B) subtypes, this work enhances the characterization of macrophage-associated immune suppression in these tumors and identifies potential targets for immunomodulatory strategies. Understanding the implications of the tumour microenvironment (TME) for cancer progression remains crucial. Here, the authors develop an explainable machine learning pipeline to analyse the associations between TME composition and relapse-free survival (RFS) in breast cancer, and show that macrophages correlate positively with pathological complete response but negatively with RFS.