scMapNet: marker-based cell type annotation of scRNA-seq data via vision transfer learning with tabular-to-image transformations

Identifying cell types is a key step in single-cell RNA sequencing data analysis that aids in understanding cellular heterogeneity and facilitates downstream analyses such as those concerning cell-cell interactions and data integration. Cell-type annotation methods often rely on unsupervised clustering algorithms, followed by manual or automatic annotation via marker genes, which are prone to inefficiency and inconsistency. Supervised methods, while more automated and consistent, have gained remarkable attention because of the rapid growth of large-scale, high-quality single-cell datasets. However, these methods lack the ability to effectively leverage cellular marker knowledge and a large amount of unlabelled data. Here, we introduce scMapNet, a self-supervised deep learning model based on masked autoencoders (MAE) and vision transformer (ViT), which can sufficiently learn cellular marker knowledge and information from unlabelled data. This method adopts treemap transformations to leverage cell marker information and capture information by pretraining on large amounts of unlabelled data. To demonstrate the advantages of scMapNet, we conducted scientific benchmarking, and the results showed that scMapNet achieved good performance in terms of annotation accuracy, batch immunity, and model interpretability.