Discovery of phenotype-associated subpopulations is critical for targeted therapies and prognostic biomarker discovery, which requires multi-scale gene expression. Deep learning advancements have enabled cost-effective genetic alteration inference from whole-slide images (WSIs), but most methods operate at a single scale. This study presents BiSCALE, a deep-learning framework that predicts gene expression from WSIs at both tissue (bulk) and near-cellular (spot) levels and links these predictions to clinical phenotypes. The framework integrates a WSI foundation encoder with a Vision-Mamba fusion module and a two-stage training strategy to bridge scale and distribution differences between bulk and spot data. Trained on 2109 bulk tumor samples and 141 000 spatial transcriptomics spots across three cancer types, BiSCALE outperforms established bulk and spatial baselines, generalizes well to independent cohorts, and demonstrates strong concordance between predicted bulk and spot expression profiles. It recovers biologically relevant pathway activity and supports downstream applications, including patient-level risk stratification from bulk WSIs and spot-level cell-identity annotation. BiSCALE also identifies phenotype-associated subpopulations, including niches linked to recurrence and hypoxia. These results establish BiSCALE as a cost-effective approach for multi-scale gene analysis and phenotype-associated feature discovery from routine pathology. All code used in this study are available at: https://github.com/Hailong-Zheng/BiSCALE.
Building similarity graph...
Analyzing shared references across papers
Loading...
Hailong Zheng
Capital Medical University
Jiajing Xie
Fujian Agriculture and Forestry University
Luqi Wang
Southern Medical University
Southern Medical University
Fujian Agriculture and Forestry University
Shanxi Medical University
Building similarity graph...
Analyzing shared references across papers
Loading...
Zheng et al. (Wed,) studied this question.
synapsesocial.com/papers/69a1351ded1d949a99abebc8 — DOI: https://doi.org/10.1002/advs.202521151