Dawnn benchmarking dataset: Heart cells processing and label simulation

This project is a collection of files to allow users to reproduce the model development and benchmarking in "Dawnn: single-cell differential abundance with neural networks" (Hall and Castellano, under review). Dawnn is a tool for detecting differential abundance in single-cell RNAseq datasets. It is available as an R package here. Please contact us if you are unable to reproduce any of the analysis in our paper. The files in this collection correspond to the benchmarking dataset based on single-cell RNAseq of heart cells. <br> FILES: Input data Dataset from: "Integrated multi-omic characterization of congenital heart disease". Nature 608 pp. 181-191 (2022). <strong>heart_barcodes.tsv.gz</strong> Cell barcode list <strong>heart_genes.tsv.gz </strong>Gene list <strong>heart_expression_matrix.mtx.gz</strong> Cell-by-gene expression matrix Data processing code <strong>process_heart_cells.R</strong> Generates benchmarking dataset from input data. (Reads <em>heart_barcodes.tsv.gz</em>, <em>heart_genes.tsv.gz</em>, and <em>heart_expression_matrix.mtx.gz</em>; Runs the standard Seurat pipeline; Saves the resulting Seurat dataset as <em>heart_tissue_cells.RDS</em> and the resulting cell labels as <em>benchmark_dataset_heart_data_type_labels.csv</em>) Resulting datasets <strong>heart_tissue_cells.RDS</strong> Seurat dataset generated by <em>process_heart_cells.R</em>. <strong>benchmark_dataset_heart_data_type_labels.csv </strong>Cell labels generated by <em>process_heart_cells.R</em>.