scDART: integrating unmatched scRNA-seq and scATAC-seq data and learning cross-modality relationship simultaneously

Genome Biol. 2022 Jun 27;23(1):139. doi: 10.1186/s13059-022-02706-x.

Abstract

It is a challenging task to integrate scRNA-seq and scATAC-seq data obtained from different batches. Existing methods tend to use a pre-defined gene activity matrix to convert the scATAC-seq data into scRNA-seq data. The pre-defined gene activity matrix is often of low quality and does not reflect the dataset-specific relationship between the two data modalities. We propose scDART, a deep learning framework that integrates scRNA-seq and scATAC-seq data and learns cross-modalities relationships simultaneously. Specifically, the design of scDART allows it to preserve cell trajectories in continuous cell populations and can be applied to trajectory inference on integrated data.

Keywords: Integrative analysis; Single-cell multiomics; Trajectory inference; scATAC-seq; scRNA-seq.

Publication types

  • Research Support, U.S. Gov't, Non-P.H.S.
  • Research Support, N.I.H., Extramural

MeSH terms

  • Gene Expression Profiling*
  • Sequence Analysis, RNA
  • Single-Cell Analysis*
  • Whole Exome Sequencing