Cross-modal Diffusion Modelling for Super-resolved Spatial Transcriptomics

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Xiaofei, Huang, Xingxu, Price, Stephen J., Li, Chao
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908627229474816
author Wang, Xiaofei
Huang, Xingxu
Price, Stephen J.
Li, Chao
author_facet Wang, Xiaofei
Huang, Xingxu
Price, Stephen J.
Li, Chao
contents The recent advancement of spatial transcriptomics (ST) allows to characterize spatial gene expression within tissue for discovery research. However, current ST platforms suffer from low resolution, hindering in-depth understanding of spatial gene expression. Super-resolution approaches promise to enhance ST maps by integrating histology images with gene expressions of profiled tissue spots. However, current super-resolution methods are limited by restoration uncertainty and mode collapse. Although diffusion models have shown promise in capturing complex interactions between multi-modal conditions, it remains a challenge to integrate histology images and gene expression for super-resolved ST maps. This paper proposes a cross-modal conditional diffusion model for super-resolving ST maps with the guidance of histology images. Specifically, we design a multi-modal disentangling network with cross-modal adaptive modulation to utilize complementary information from histology images and spatial gene expression. Moreover, we propose a dynamic cross-attention modelling strategy to extract hierarchical cell-to-tissue information from histology images. Lastly, we propose a co-expression-based gene-correlation graph network to model the co-expression relationship of multiple genes. Experiments show that our method outperforms other state-of-the-art methods in ST super-resolution on three public datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2404_12973
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cross-modal Diffusion Modelling for Super-resolved Spatial Transcriptomics
Wang, Xiaofei
Huang, Xingxu
Price, Stephen J.
Li, Chao
Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Quantitative Methods
The recent advancement of spatial transcriptomics (ST) allows to characterize spatial gene expression within tissue for discovery research. However, current ST platforms suffer from low resolution, hindering in-depth understanding of spatial gene expression. Super-resolution approaches promise to enhance ST maps by integrating histology images with gene expressions of profiled tissue spots. However, current super-resolution methods are limited by restoration uncertainty and mode collapse. Although diffusion models have shown promise in capturing complex interactions between multi-modal conditions, it remains a challenge to integrate histology images and gene expression for super-resolved ST maps. This paper proposes a cross-modal conditional diffusion model for super-resolving ST maps with the guidance of histology images. Specifically, we design a multi-modal disentangling network with cross-modal adaptive modulation to utilize complementary information from histology images and spatial gene expression. Moreover, we propose a dynamic cross-attention modelling strategy to extract hierarchical cell-to-tissue information from histology images. Lastly, we propose a co-expression-based gene-correlation graph network to model the co-expression relationship of multiple genes. Experiments show that our method outperforms other state-of-the-art methods in ST super-resolution on three public datasets.
title Cross-modal Diffusion Modelling for Super-resolved Spatial Transcriptomics
topic Image and Video Processing
Computer Vision and Pattern Recognition
Machine Learning
Quantitative Methods
url https://arxiv.org/abs/2404.12973