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

2026-03-18

AI Summary

Existing methods for predicting gene expression from histopathology images overlook the fundamental biological principle that gene expression arises from the composition of cell types, resulting in predictions lacking interpretability and structural constraints. This work proposes CPNN, a novel model that, for the first time, incorporates cell-type prototypes derived from single-cell RNA sequencing as priors to learn cell composition weights directly from histopathology images and explicitly models the mapping between these prototypes and bulk gene expression. Evaluated across three slide-level and three spatial transcriptomics datasets, CPNN achieves state-of-the-art performance in terms of Spearman correlation coefficient. Moreover, it enables visualization of cell-type contributions, yielding biologically meaningful and interpretable gene expression predictions.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Probabilistic Circuits and Graphical Models
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• gene expression estimation
• pathology images
• cell-type resolution
• spatial transcriptomics
• single-cell RNA-seq

Innovation

• cell-type prototype
• gene expression estimation
• pathology image analysis
• single-cell RNA-seq
• interpretable deep learning