Cell-Type Prototype-Informed Neural Network for Gene Expression Estimation from Pathology Images

TL;DR

This paper introduces CPNN, a neural network that incorporates cell-type prototypes from single-cell data to improve gene expression estimation from pathology images, offering better accuracy and interpretability.

Contribution

The novel CPNN framework explicitly models cell-type contributions using prototypes, integrating single-cell data with histology images for enhanced gene expression prediction.

Findings

CPNN outperforms existing methods in Spearman correlation across datasets.

The model provides interpretable insights into cell-type contributions.

High performance on both slide-level and spatial transcriptomics data.

Abstract

Estimating slide- and patch-level gene expression profiles from pathology images enables rapid and low-cost molecular analysis with broad clinical impact. Despite strong results, existing approaches treat gene expression as a mere slide- or spot-level signal and do not incorporate the fact that the measured expression arises from the aggregation of underlying cell-level expression. To explicitly introduce this missing cell-resolved guidance, we propose a Cell-type Prototype-informed Neural Network (CPNN) that leverages publicly available single-cell RNA-sequencing datasets. Since single-cell measurements are noisy and not paired with histology images, we first estimate cell-type prototypes-mean expression profiles that reflect stable gene-gene co-variation patterns.CPNN then learns cell-type compositional weights directly from images and models the relationship between prototypes and observed bulk or spatial expression, providing a biologically grounded and structurally regularized prediction framework. We evaluate CPNN on three slide-level datasets and three patch-level spatial transcriptomics datasets. Across all settings, CPNN achieves the highest performance in terms of Spearman correlation. Moreover, by visualizing the inferred compositional weights, our framework provides interpretable insights into which cell types drive the predicted expression. Code is publicly available at https://github.com/naivete5656/CPNN.