Inference of cell type-specific gene regulatory networks on cell lineages from single cell omic datasets

The uploaded files are source datasets for the scMTNI algorithm. scMTNI is a multi-task learning framework that integrates the cell lineage structure, scRNA-seq and scATAC-seq measurements to enable joint inference of cell type-specific GRNs. See more details at Zhang, S., Pyne, S., Pietrzak, S. et al. Inference of cell type-specific gene regulatory networks on cell lineages from single cell omic datasets. Nat Commun 14, 3064 (2023). https://doi.org/10.1038/s41467-023-38637-9

The source data scMTNI_sourcedata.tar.gz contains the following 3 parts:

1) The cluster-specific scRNA-seq matrices and the prior networks for all three datasets and scMTNI inferred consensus networks.

2) Gold standard human and mouse datasets for evaluation.

3) Source data for scMTNI figures 2-8 and supplementary figures. The key for each figure and its corresponding file path is in SourceData_Key_v2.xlsx.

The source data Buenrostro_Hematopoiesis.tar.gz contains the scRNA-seq data for human hematopoietic differentiation downloaded from Data S2 of Buenrostro et al.

The source data RawMotifFiles.tar.gz contains the motif instance files and promoter files for human and mouse for generating prior networks using scATAC-seq data for scMTNI. Check https://github.com/Roy-lab/scMTNI/blob/master/Scripts/genPriorNetwork/readme.md for examples and scripts.

The Buenrostro_priorNetwork_bamfiles.tar.gz contains the raw bam files of scATAC-seq data for human hematopoietic differentiation downloaded from Buenrostro et al.