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 ...
We have testedscDARTon three real datasets: two unmatched datasets where the scRNA-seq and scATAC-seq data are not jointly profiled, and a matched dataset where both chromatin accessibility and gene-expression are measured simultaneously in the same cells. We also proposed a simulation procedure to...
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...
We also provide a set of datasets for real-world style demos, including scRNAseq, scATACseq, spatial transcriptomics and DNA methylation data. They are described in detail in the articles that make use of them. Please check them out from the links above....
it becomes possible to capture longer dynamical processes or transient cellular states (Manno et al.2018). While the focus of this review centers on scRNAseq, complementary techniques such as scATAC-seq could provide valuable insight into biophysical properties and phenotypes with slower fluctuations....