DCPR_V1.0

<b>DCPR</b>This is a repository to deposit the code and data for DCPR model. DCPR is a deep learning framework for circadian phase reconstruction.<b>Main f</b><b>iles</b><b>AD Datasets</b>: Three Alzheimer's Disease(AD) datasets from different brain regions: Entorhinal Cortex (EC), Hippocampus (HIP), and Frontal Cortex (FC).<b>Synthetic datasets</b>: Eighteen synthetic datasets differ in sampling frequency, circadian gene content, and noise conditions.<b>GEO datasets</b>: Six GEO datasets with diffrent species, tissues and sequencing platforms.<b>DCPR_codes</b>: Source code for DCPR model.<b>Visualization</b>: Scripts for data visualization, including circadian curves (cosine model fitting), sample plots (predicted and real time), model performance (CDF curves, and accuracy plots).<b>Supplementary File 1</b>: Seed gene sets derived from mouse peritoneal macrophages/hypothalamus and Papio anubis ileum.<b>Supplementary File 2</b>: Prior knowledge obtained from the Circadian Gene Database (CGDB) and related analysis of core clock genes from mouse liver.<b>Supplementary File 3</b>: Comparative analysis of differential rhythmic patterns in core clock genes between normal and Alzheimer's disease conditions across three brain region datasets (Entorhinal Cortex (EC), Hippocampus (HIP), and Frontal Cortex (FC)).<b>Configuration</b>It is recommended to use the conda environment (python 3.8). See environment.yaml for details.<b>How to use</b>refer to<b> </b>https://github.com/NJAU-CDSIC/DCPR_V1.0<br>

<b>DCPR</b> 本仓库用于存储DCPR模型的代码与配套数据集。DCPR是一款用于昼夜节律相位重构的深度学习框架。
<b>主要文件</b>
<b>AD数据集</b>：包含3份源自不同脑区的阿尔茨海默病（Alzheimer's Disease, AD）数据集，分别为内嗅皮层（Entorhinal Cortex, EC）、海马体（Hippocampus, HIP）以及额叶皮层（Frontal Cortex, FC）。
<b>合成数据集</b>：共18份合成数据集，在采样频率、节律基因组成与噪声条件上存在差异。
<b>GEO数据集（Gene Expression Omnibus）</b>：共6份GEO数据集，涵盖不同物种、组织类型与测序平台。
<b>DCPR模型代码</b>：DCPR模型的源代码文件。
<b>可视化脚本</b>：用于数据可视化的脚本，涵盖节律曲线（余弦模型拟合）、样本绘图（预测时间与真实时间对比）以及模型性能评估（累积分布函数（Cumulative Distribution Function, CDF）曲线与准确率绘图）。
<b>补充文件1</b>：源自小鼠腹腔巨噬细胞/下丘脑以及阿拉伯狒狒（Papio anubis）回肠的种子基因集。
<b>补充文件2</b>：从节律基因数据库（Circadian Gene Database, CGDB）中获取的先验知识，以及针对小鼠肝脏核心时钟基因的相关分析结果。
<b>补充文件3</b>：针对三份脑区数据集（内嗅皮层EC、海马体HIP与额叶皮层FC），对比分析正常状态与阿尔茨海默病状态下核心时钟基因的节律模式差异。
<b>环境配置</b>：推荐使用conda环境（Python 3.8），具体配置请参考environment.yaml文件。
<b>使用方法</b>：请参考链接 https://github.com/NJAU-CDSIC/DCPR_V1.0