HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology

2026-07-22

AI Summary

This work addresses the limitations of existing methods that overlook tissue structural heterogeneity and lack quantification of prediction confidence when inferring spatial gene expression from H&E images. The authors propose a dual-graph architecture: in the spot graph, domain-aware edge-weighted graph convolution is introduced, leveraging Leiden clustering to distinguish intra-domain, inter-domain, and boundary connections; in the gene graph, STRING protein–protein interaction priors are integrated with tissue-specific co-expression patterns, enabling hierarchical propagation from marker to genome-wide genes via attention gating. Uncertainty is estimated using evidential deep learning. This approach is the first to explicitly model tissue architecture as a typed-edge graph, significantly outperforming 13 baselines across six Visium tissue types with the highest expression correlation, while calibrated uncertainty effectively identifies low-confidence regions for pathological review.

Abstract

Spatial transcriptomics assays remain costly and technically demanding, restricting transcriptome-wide profiling to specialist settings and preventing routine clinical deployment. Predicting spatially resolved gene expression from H&E histology could close this gap, yet current methods largely ignore the underlying tissue architecture and rarely quantify how their predictions can be trusted. We introduce HierarchicalDAEW, a dual-graph architecture that addresses both gaps. On the spot graph, a Domain-Aware Edge-Weighted convolutional operator learns separate projections for inter-domain, intra-domain, and boundary edges derived from Leiden clustering, allowing the model to treat tissue heterogeneity as an explicit structural signal rather than an implicit one. A second gene-level graph then fuses protein-protein interaction priors from STRING-DB with tissue-specific co-expression through learned attention gating, propagating predictions from a landmark gene set to a broader gene panel. Reliability is handled through evidential uncertainty estimation, which produces far better calibrated confidence intervals than Monte Carlo dropout under identical conditions. Across six human Visium sections spanning breast, colorectal, prostate, and cerebellar tissue, and against thirteen published baselines, HierarchicalDAEW achieves the strongest correlation with ground-truth expression, with gains that hold up under multi-seed reproducibility checks and negative controls that rule out positional shortcuts. Ablations further confirm that both the domain-aware edge typing and the hierarchical depth are necessary to this improvement, and calibrated uncertainty estimates identify low-confidence predictions for pathologist review before clinical action.

Problem

• spatial gene expression prediction
• H&E histology
• tissue architecture
• prediction uncertainty
• spatial transcriptomics

Innovation

• Domain-Aware Edge-Weighted Graph Convolution
• Evidential Uncertainty Estimation
• Hierarchical Graph Architecture
• Spatial Gene Expression Prediction
• Tissue Architecture Modeling