Virtual spatial transcriptomics from histopathology enables prognostic and therapeutic response prediction in cancer
Preprint
Abstract
Spatial transcriptomics reveals cellular heterogeneity, intercellular communication, and tissue organization, but its cost and limited accessibility restrict clinical use. Here, we present VISTA, a model that integrates multi-scale histological features and spatial context to infer spatial gene expression from H&E-stained tissue images. Across leave-one-section-out cross-validation and independent validation, VISTA robustly predicted thousands of genes and outperformed state-of-the-art methods. Beyond expression reconstruction, VISTA enabled clinically relevant downstream analyses. In TCGA breast cancer samples, it identified survival-associated genes, stratified prognostic risk groups, and revealed adverse tumor-associated spatial subtypes. In our in-house intrahepatic cholangiocarcinoma cohort, it preserved tumor–normal organization and identified CLDN4 and CYP3A4 as complementary spatial biomarkers. In HER2+ breast cancer, it predicted pathological response to neoadjuvant trastuzumab-based therapy and linked response-associated regions to immune and cytokine-related programs. These results support virtual spatial transcriptomics from routine histopathology for oncology applications.Keywords
This publication has 40 references indexed in Scilit:
- Distilling Foundation Models for Robust and Efficient Models in Digital Pathology2025
- Transformer with convolution and graph-node co-embedding: An accurate and interpretable vision backbone for predicting gene expressions from local histopathological imageMedical Image Analysis, 2023
- Transition to invasive breast cancer is associated with progressive changes in the structure and composition of tumor stromaCell, 2022
- A survey on graph-based deep learning for computational histopathologyComputerized Medical Imaging and Graphics, 2022
- Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction Using Patch-Based Graph Convolutional Networks2021
- Multi-scale fully convolutional neural networks for histopathology image segmentation: From nuclear aberrations to the global tissue architectureMedical Image Analysis, 2021
- Sigmoid-weighted linear units for neural network function approximation in reinforcement learningNeural Networks, 2018
- ALKBH1-Mediated tRNA Demethylation Regulates TranslationCell, 2016
- The role of GATA3 in breast carcinomas: a reviewHuman Pathology, 2016
- Recognition of tumor glycans by antigen-presenting cellsCurrent Opinion in Immunology, 2006