Dawnn benchmarking dataset: Mouse embryo 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 mouse emrbyo cells.

FILES:
Input data
Dataset from: "A single-cell molecular map of mouse gastrulation and early organogenesis". Nature 566, pp490–495 (2019).
The input data is loaded from the MouseGastrulationData R package. We upload here the RDS file generated by loading the dataset in process_mouse_cells.R in case the R package becomes unavailable

MouseGastrulationData_loaded_dataset.RDS Dataset loaded from MouseGastrulationData R package in process_mouse_cells.R (in call to EmbryoAtlasData function).

Data processing code

process_mouse_cells.R Generates benchmarking dataset from input data. (Loads input data; Runs the standard single-cell RNAseq pipeline). Follows Dann et al. Resulting dataset saved as mouse_gastrulation_data_regen.RDS.
simulate_mouse_pc1_Rscript.R R code to simulate P(Condition_1)s for benchmarking.
simulate_mouse_pc1_bash.sh Bash script to execute simulate_mouse_pc1_Rscript.R. Outputs stored in benchmark_dataset_mouse_pc1s_regen.csv.
simulate_mouse_labels_Rscript.R R code to simulate labels for benchmarking.
simulate_mouse_labels_bash.sh Bash script to execute simulate_mouse_labels_Rscript.R. Outputs stored in benchmark_dataset_mouse.csv.

Resulting datasets

mouse_gastrulation_data_regen.RDS Seurat dataset generated by process_mouse_cells.R.
benchmark_dataset_mouse.csv Cell labels generated by simulate_mouse_labels_bash.sh.
benchmark_dataset_mouse_pc1s_regen.csv P(Condition_1)s generated by simulate_mouse_pc1_bash.sh.

本项目汇集了一系列文件，旨在使用户能够复现论文《Dawnn：基于神经网络的单细胞RNA测序数据中的差异富集》中模型开发与基准测试的过程（Hall和Castellano，待发表）。Dawnn是一款用于检测单细胞RNA测序数据集中差异富集的工具，现以R包的形式提供。若用户在复现论文中的任何分析时遇到困难，请与我方联系。本集合中的文件对应基于小鼠胚胎干细胞单细胞RNA测序的基准测试数据集。

文件列表：

输入数据
数据来源：'《小鼠 gastrulation 和早期器官形成过程的单细胞分子图谱》'，Nature 566，第490-495页（2019年）。输入数据由MouseGastrulationData R包加载。在此，我们上传了在process_mouse_cells.R中加载数据集生成的RDS文件，以备R包不可用的情况。 MouseGastrulationData_loaded_dataset.RDS：在process_mouse_cells.R中调用EmbryoAtlasData函数时，从MouseGastrulationData R包加载的数据集。

数据处理代码
process_mouse_cells.R：从输入数据生成基准测试数据集。该代码（加载输入数据；运行标准单细胞RNA测序流程）遵循Dann等人的方法。结果数据集以mouse_gastrulation_data_regen.RDS保存。
simulate_mouse_pc1_Rscript.R：用于模拟基准测试中Condition_1概率的R代码。
simulate_mouse_pc1_bash.sh：执行simulate_mouse_pc1_Rscript.R的Bash脚本。输出存储在benchmark_dataset_mouse_pc1s_regen.csv中。
simulate_mouse_labels_Rscript.R：用于模拟基准测试标签的R代码。
simulate_mouse_labels_bash.sh：执行simulate_mouse_labels_Rscript.R的Bash脚本。输出存储在benchmark_dataset_mouse.csv中。

结果数据集
mouse_gastrulation_data_regen.RDS：由process_mouse_cells.R生成的Seurat数据集。
benchmark_dataset_mouse.csv：由simulate_mouse_labels_bash.sh生成的细胞标签。
benchmark_dataset_mouse_pc1s_regen.csv：由simulate_mouse_pc1_bash.sh生成的Condition_1概率。