Masked adversarial neural network for cell type deconvolution in spatial transcriptomics

TL;DR

This paper introduces MACD, a neural network that uses adversarial learning and masking to improve cell type deconvolution in spatial transcriptomics, addressing data discrepancies and noise.

Contribution

The novel MACD method aligns scRNA-seq and ST data in a unified space using adversarial learning and masking, enhancing deconvolution accuracy.

Findings

MACD outperforms existing methods on simulated datasets.

MACD achieves high accuracy on real spatial transcriptomics data.

Code and datasets are publicly available for reproducibility.

Abstract

Accurately determining cell type composition in disease-relevant tissues is crucial for identifying disease targets. Most existing spatial transcriptomics (ST) technologies cannot achieve single-cell resolution, making it challenging to accurately determine cell types. To address this issue, various deconvolution methods have been developed. Most of these methods use single-cell RNA sequencing (scRNA-seq) data from the same tissue as a reference to infer cell types in ST data spots. However, they often overlook the differences between scRNA-seq and ST data. To overcome this limitation, we propose a Masked Adversarial Neural Network (MACD). MACD employs adversarial learning to align real ST data with simulated ST data generated from scRNA-seq data. By mapping them into a unified latent space, it can minimize the differences between the two types of data. Additionally, MACD uses masking techniques to effectively learn the features of real ST data and mitigate noise. We evaluated MACD on 32 simulated datasets and 2 real datasets, demonstrating its accuracy in performing cell type deconvolution. All code and public datasets used in this paper are available at https://github.com/wenwenmin/MACD and https://zenodo.org/records/12804822.