analiza aiqbench
This paper presents a multi-scale graph neural network that predicts bulk, spatial, and single-cell gene expression from standard histopathology slides, using a pathology foundation model for features. Its main technical contribution is a hybrid training scheme that pairs direct supervision with consistency losses across biological scales. Reported accuracy is strongest at the slide level and on Xenium data, with only moderate performance at single-cell resolution, so the practical value depends on validation beyond the three tissue types studied.
From WSIs to Bulk, Spatial and Single-Cell Transcriptomics via Multi-Scale Graph Neural Networks
arXiv:2610.41692v1 Announce Type: new Abstract: Understanding the spatial distribution of gene expression is key to studying complex diseases like cancer. While Spatial Transcriptomics (ST) and Single-Cell Transcriptomics (scT) provide high-resolution insights, they remain expensive and scarce. In contrast, standard histopathology Whole-Slide Images (WSIs) paired with bulk RNA sequencing are widely available. This work introduces a Multi-Scale Graph Neural Network (GNN) capable of simultaneously predicting bulk, spatial, and single-cell transcriptomics directly from WSIs. By extracting morphological features using a Pathology Foundation Model (PFM) (UNI2-h) and constructing spatial graphs at both patch and cell levels, the model learns the hierarchical relationships within the tissue. The network is trained on a combined dataset of The Cancer Genome Atlas Program (TCGA), Visium, and Xenium samples across lung, kidney, and breast tissues. A hybrid training strategy is employed, leveraging direct supervision alongside weakly supervised consistency losses to ensure predictions align across biological scales. Results show the model accurately predicts gene expression at the slide level and moderately at the patch level (strongest on Xenium), and achieves moderate correlation at the challenging single-cell level. Furthermore, downstream tasks explore the clinical relevance of these predictions, demonstrating their utility in survival analysis, spatial hazard mapping, and tumor classification via molecular signatures.
Abstract:Understanding the spatial distribution of gene expression is key to studying complex diseases like cancer. While Spatial Transcriptomics (ST) and Single-Cell Transcriptomics (scT) provide high-resolution insights, they remain expensive and scarce. In contrast, standard histopathology Whole-Slide Images (WSIs) paired with bulk RNA sequencing are widely available. This work introduces a Multi-Scale Graph Neural Network (GNN) capable of simultaneously predicting bulk, spatial, and single-cell transcriptomics directly from WSIs. By extracting morphological features using a Pathology Foundation Model (PFM) (UNI2-h) and constructing spatial graphs at both patch and cell levels, the model learns the hierarchical relationships within the tissue. The network is trained on a combined dataset of The Cancer Genome Atlas Program (TCGA), Visium, and Xenium samples across lung, kidney, and breast tissues. A hybrid training strategy is employed, leveraging direct supervision alongside weakly supervised consistency losses to ensure predictions align across biological scales. Results show the model accurately predicts gene expression at the slide level and moderately at the patch level (strongest on Xenium), and achieves moderate correlation at the challenging single-cell level. Furthermore, downstream tasks explore the clinical relevance of these predictions, demonstrating their utility in survival analysis, spatial hazard mapping, and tumor classification via molecular signatures.
Machine Learning (cs.LG)
arXiv:2610.41692 [cs.LG]
(or arXiv:2610.41692v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.41692 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 292 cuvinte