SPARC: A mechanism-aware spatial representation from routine histology predicts cancer survival and therapy response
Ayed, A.; Cohn, G.; Bertramo, N.; Boland, G.; Gainor, J.; Yilmaz, O. H.; Barzilay, R.
Show abstract
Understanding the molecular mechanisms that drive treatment response is central to personalized cancer care, but assays such as spatial transcriptomics are not yet scalable in routine clinical practice. A critical question, then, is whether this deeper molecular insight can be extracted directly from routine histology. Here, we introduce SPARC, a framework that infers spatially resolved activity maps for 40 gene expression programs directly from H&E slides. Integrating predicted program maps with morphological features improves survival prediction in 17 of 18 cancer types across 8,383 patients and matches a multi-omic method requiring paired RNA sequencing. SPARC also stratifies bevacizumab response in ovarian cancer (odds ratio = 8.08) and trastuzumab response in breast cancer (odds ratio = 3.44), while H&E image-only baselines yield non-significant separation between responders and non-responders. Unsupervised anal-ysis of predicted maps reveals canonical tumor microenvironment compartments and spatial interaction patterns directly from tissue morphology, linking predictive perfor-mance of clinical outcomes to underlying biological mechanisms.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Integrative ensemble modelling of cetuximab sensitivity in colorectal cancer PDXs 95%
- Multiplexed RNA-FISH-guided Laser Capture Microdissection RNA Sequencing Improves Breast Cancer Molecular Subtyping, Prognostic Classification, and Predicts Response to Antibody Drug Conjugates 95%
- Spatial domain analysis predicts risk of colorectal cancer recurrence and infers associated tumor microenvironment networks 95%
Similar papers in this journal
Similar papers in this journal
- SpaPheno: Linking Spatial Transcriptomics to Clinical Phenotypes with Interpretable Machine Learning 96%
- Pan-cancer detection of driver genes at the single-patient resolution 95%
- Multimodal integration of single cell ATAC-seq data enables highly accurate delineation of clinically relevant tumor cell subpopulations 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.