stMCDI: Masked Conditional Diffusion Model with Graph Neural Network for Spatial Transcriptomics Data Imputation

TL;DR

stMCDI is a novel diffusion-based method that leverages graph neural networks to effectively impute missing values in spatial transcriptomics data while preserving spatial and gene expression distributions.

Contribution

The paper introduces stMCDI, a new conditional diffusion model combined with GNNs for improved spatial transcriptomics data imputation, addressing limitations of previous methods.

Findings

Outperforms existing imputation methods on spatial transcriptomics datasets.

Effectively preserves spatial and gene expression data distribution.

Utilizes masked data guidance and GNN encoding for enhanced performance.

Abstract

Spatially resolved transcriptomics represents a significant advancement in single-cell analysis by offering both gene expression data and their corresponding physical locations. However, this high degree of spatial resolution entails a drawback, as the resulting spatial transcriptomic data at the cellular level is notably plagued by a high incidence of missing values. Furthermore, most existing imputation methods either overlook the spatial information between spots or compromise the overall gene expression data distribution. To address these challenges, our primary focus is on effectively utilizing the spatial location information within spatial transcriptomic data to impute missing values, while preserving the overall data distribution. We introduce \textbf{stMCDI}, a novel conditional diffusion model for spatial transcriptomics data imputation, which employs a denoising network trained using randomly masked data portions as guidance, with the unmasked data serving as conditions. Additionally, it utilizes a GNN encoder to integrate the spatial position information, thereby enhancing model performance. The results obtained from spatial transcriptomics datasets elucidate the performance of our methods relative to existing approaches.