囊性纤维化肺病严重程度预测性表观遗传生物标志物识别

数据集获取

源站：https://clinicaltrials.gov/study/NCT02976714

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

Conditions: Cystic Fibrosis. Cystic Fibrosis (CF) is an autosomal recessive disease resulting from mutations in the CFTR gene. CFTR encodes a chloride channel, mainly expressed at the apical membrane of epithelial cells. CFTR dysfunction induces mucus thickening, causing multiple disorders in respiratory, digestive and reproductive tracts. In CF patients, lung disease is the main cause of morbidity and mortality, and its severity is variable among CF patients, even among those with the same genotype. This clinical variability depends on two factors: genetic (complex alleles of CFTR gene and modifier genes) and environmental factors. Genetic factors have been largely explored, and several modifier genes have been identified. By contrast, environmental factors are still poorly known. It is well established that environmental factors modify the phenotype by acting on epigenetic marks (i.e. DNA methylation, histone modification) present in the genome. Epigenetic modifications regulate and modulate gene expression. In a previous we profiled DNA methylation genome-wide in nasal epithelial cell samples from 32 CF patients and 24 healthy controls. CF patients homozygous for the p.Phe508del mutation and >18-years-old were stratified according to the lung disease severity. Through this study, we identified 187 genomic regions (CpG dinucleotides) differentially methylated between CF patients with mild lung disease and CF patients with severe lung disease. The present project aims at identifying predictive epigenetic biomarkers of lung disease severity, among these 187 regions. While the previous study was carried out on genomic DNA extracted from nasal epithelial cells, in the present project we will use a non-invasive model: spontaneous sputum. Hypothesis: some differentially methylated genomic regions between mild and severe CF patients can be used as predictive epigenetic biomarkers of lung disease severity in cystic fibrosis. Objectives: (i) to identify predictive epigenetic biomarkers of lung disease

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。