scJoint integrates atlas-scale single-cell RNA-seq and ATAC-seq data with transfer learning

Single-cell multiomics data continues to grow at an unprecedented pace. Although several methods have demonstrated promising results in integrating several data modalities from the same tissue, the complexity and scale of data compositions present in cell atlases still pose a challenge. Here, we present scJoint, a transfer learning method to integrate atlas-scale, heterogeneous collections of scRNA-seq and scATAC-seq data. scJoint leverages information from annotated scRNA-seq data in a semisupervised framework and uses a neural network to simultaneously train labeled and unlabeled data, allowing label transfer and joint visualization in an integrative framework. Using atlas data as well as multimodal datasets generated with ASAP-seq and CITE-seq, we demonstrate that scJoint is computationally efficient and consistently achieves substantially higher cell-type label accuracy than existing methods while providing meaningful joint visualizations. Thus, scJoint overcomes the heterogeneity of different data modalities to enable a more comprehensive understanding of cellular phenotypes. Integration of data from single-cell RNA-seq and ATAC-seq is achieved with transfer learning.

Automated summary

This study introduces a transfer learning method called scJoint to integrate different single-cell transcriptome and chromatin accessibility sequencing datasets. By training labeled and unlabeled data using a neural network in a semi-supervised learning framework, scJoint enables label transfer and joint visualization. The results demonstrate that scJoint outperforms existing methods in computational efficiency and cell-type label accuracy, providing a more comprehensive understanding of cellular phenotypes.