组蛋白乙酰化稳态破坏揭示多层染色质调控与转录韧性

数据集获取

源站：https://ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE282758

标准获取流程：

1. 访问源站链接，注册/登录账号；
2. 进入数据集详情页，按页面指引申请权限或直接下载；
3. 部分平台提供 SDK，例如：
   • OpenDataLab: pip install openxlab 后 openxlab.dataset.get(...)
   • ModelScope: pip install modelscope 后 modelscope download
   • 天池: 登录后页面提供直链下载
     以源站「数据下载/使用文档」页面为准。

数据说明

Dysregulation of epigenetic processes leads to a plethora of abnormalities including disease states such as cancer. Therapies focused on epigenetic modulation alter gene expression to correct dysfunction, though the mechanisms and perpetuation of these states is unknown. Here, we use integrated epigenomics and three-dimensional chromatin structure-function analyses after acute histone deacetylase inhibitor cancer drug treatment (suberoylanilide hydroxamic acid in lung cancer cells). Treatment induced substantial (13%) genomic rearrangement that rebounds despite persistent gene expression changes and spreading of acetylation. The chromatin functional landscape (accessibility, active transcription modification, and gene expression) is controlled and locus-specific, while chromatin contacts are globally altered resulting in a moderate weakening of topologically associating domains. Chromatin states are more dynamic at transcriptionally active loci while genes with reduced expression are epigenetically stable suggesting chromatin architectural turnover and nucleosome remodeling is locus-specific and underlies the bidirectional expression changes. Thus, local 3D chromatin and genome structural dynamics is integral for loci regulation in response to epigenomic perturbation. The partial persistence of these altered features may have larger implications for efficacy of epigenetic drugs in amelioration of disease states.

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。