Dawnn training set 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 code and resulting dataset from the training set generation procedure.

FILES:

autogen4_code.R R code to generate training set (250,000 independent random walks are simulated, with each random walk constituting an instance within the training set). Saves output to labels_df.csv.
labels_df.csv Training dataset generated by autogen4_code.R (Each row corresponds to a training instance, with the first column containing the simulated probability of the cell at the centre of a simulated trajectory having been drawn from Condition_1, and the remaining columns containing the labels corresponding to its 1000 neighbouring cells, with labels drawn according to the random walks simualted in autogen4_code.R).

本项研究汇聚了一系列文件，旨在允许用户复现“Dawnn：基于神经网络的单细胞差异丰度检测”模型（Hall与Castellano，待发表）中的模型开发与基准测试。Dawnn是一款专门针对单细胞RNA测序数据集进行差异丰度检测的工具，现以R语言包的形式提供，具体可在此处获取。如用户在复现论文中所述分析时遇到任何问题，请与我们联系。本集合中的文件对应着训练集生成过程中的代码与生成数据集。

文件列表：

- autogen4_code.R：用于生成训练集的R代码（模拟了250,000次独立随机游走，每次随机游走构成训练集中的一个实例）。输出结果保存至labels_df.csv文件。
- labels_df.csv：由autogen4_code.R生成的训练数据集（每一行对应一个训练实例，第一列包含模拟轨迹中心细胞在Condition_1条件下被抽样的概率，其余列包含与其相邻的1000个细胞的标签，标签根据autogen4_code.R中模拟的随机游走生成）。