DiffusionST: A deep generative diffusion model-based framework for enhancing spatial transcriptomics data quality and identifying spatial domains

Abstract

Recent advancements in spatial transcriptomics technology have generated substantial volumes of spatial transcriptome data. However, the quality of this data is often compromised due to the limitations of current sequencing technologies. To address this issue, DiffusionST proposes a method for imputing spatial transcriptomics data and clustering the imputed data. The method employs a graph convolutional network (GCN) model combined with a newly designed loss function, denoising data using the zero-inflated negative binomial (ZINB) distribution, and data enhancement through a diffusion model to improve clustering accuracy. DiffusionST demonstrates superior clustering accuracy compared to six of the most popular spatial transcriptomics clustering algorithms. DiffusionST also excels in data imputation when compared to five single-cell RNA sequencing (scRNA-seq) imputation algorithms. Additionally, DiffusionSTs robustness against noise is quantitatively validated by manually introducing random dropout noise into the dataset, where our model significantly enhances the quality of spatial transcriptomic data. Moreover, DiffusionST is well-suited for high-resolution spatial transcriptomics data and has been demonstrated, through survival analysis and cell-cell communication studies, to dissect spatial domains within breast cancer tissues. These findings provide strong evidence of DiffusionSTs efficacy in handling spatial transcriptomic data especially with strong noise, making it a valuable tool in this field.