Spatially guided translation from histology images to transcriptomic profiles using foundation model-driven contrastive learning

The useful part

by Zi Huai Huang, Ziyang Xu, Pingzhao Hu Spatial transcriptomics (ST) enhances single-cell RNA sequencing by revealing transcript distribution, offering critical insights into heterogeneous diseases such as breast cancer. However, the high cost and lengthy processes of generating high-quality ST data limit clinical application. We introduce FOCST, a foundation model-driven framework for ST imputation that leverages spatial guided contrastive learning.

How it works

• These are integrated with expression data in a unified embedding space via contrastive learning, enabling cross-modal prediction and imputation.
• To further enhance spatial awareness, a graph neural network incorporates positional information, improving regional detection and interpretability.Benchmarking demonstrates FOCST's superior performance...