肺健康研究全基因组关联数据集
该数据集来自约翰霍普金斯大学的肺健康研究（LHS），基于4,287名欧洲裔美国人的库存DNA与表型数据，用于检验肺功能下降与慢性阻塞性肺疾病（COPD）的关联
基本信息
资源简介
肺健康研究全基因组关联数据集
该数据集来自约翰霍普金斯大学的肺健康研究（LHS），基于4,287名欧洲裔美国人的库存DNA与表型数据，用于检验肺功能下降与慢性阻塞性肺疾病（COPD）的关联。研究目标包括在LHS队列子集中发现人类基因组全部蛋白质编码区（外显子组）中与COPD等复杂肺部疾病风险相关的常见与罕见变异。LHS I是一项随机多中心临床试验，共5,887名参与者。数据可用于COPD遗传变异发现及肺功能下降的关联分析（来源 omicsdi.org）。
【数据内容】
源站描述（机器翻译，仅供参考）：约翰霍普金斯大学的“肺健康研究中的全基因组关联与环境交互作用”项目旨在利用来自纵向、多中心肺健康研究（LHS）的4,287名欧洲裔美国人的库存DNA和表型数据，检验作为慢性阻塞性肺疾病（COPD）相关主要结局的肺功能下降之间的关联。LungGO/ESP-GO的总体目标分为两大类：（i）在LHS队列的一个子集中，发现人类基因组所有蛋白质编码区（即外显子组）中赋予包括COPD在内的复杂肺部疾病风险的所有变异（即常见和罕见变异）。约翰霍普金斯大学LHS队列为阐明导致COPD的遗传变异提供了独特机会。肺健康研究I是一项随机多中心临床试验，共有5887名参与者，开展于10月
【主题与分类】
主题标签：Genomic。本站分类：呼吸系统疾病/其他。
【获取与许可】
源站页面：https://omicsdi.org/dataset/dbgap/phs000335
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取
源站：https://omicsdi.org/dataset/dbgap/phs000335
标准获取流程：
- 访问源站链接，注册/登录账号；
- 进入数据集详情页，按页面指引申请权限或直接下载；
- 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。
- OpenDataLab:
数据说明
The 'Genome-Wide Associations Environmental Interactions in the Lung Health Study' at Johns Hopkins University aims to test for association between lung function decline as a primary outcome associated with chronic obstructive pulmonary disease (COPD) using banked DNA and phenotype data on 4,287 European Americans from the longitudinal, multicenter Lung Health Study (LHS). The broad goals of the LungGO/ESP-GO falls into two general categories: (i) discovery of all variants (i.e., common and rare) in all protein-coding regions of the human genome (i.e., the exome) conferring risk to complex pulmonary diseases including COPD, in a subset of the LHS cohort. The Johns Hopkins University LHS cohort offers a unique opportunity to elucidate genetic variants that cause COPD. The Lung Health Study I was a randomized multicenter clinical trial with 5887 participants carried out from October 1986 to April 1994, designed to test the effectiveness of smoking cessation and bronchodilator administration in smokers aged 35 to 60 with mild lung function impairment. Participants were randomly assigned to one of three groups: usual care, who received no intervention smoking intervention with the inhaled bronchodilator ipratroprium bromide smoking intervention with an inhaled placebo. The effect of intervention was evaluated by the rate of decline of forced expiratory volume in one second (FEV1). For the GWAS, only the subset of European American LHS participants for whom lung function data from three time points or more are available. Thus, the GWAS represents 73% of the 5,887 volunteers who participated in the LHS study. Importantly, LHS subjects included had similar demographics (including age, gender and BMI) and rates of lung function decline (mean annual change in FEV1% predicted: -0.96 %/yr vs. -0.99 %/yr, p=0.57) compared with those not included in the GWAS, reflecting little selection bias for our primary outcome. They were, however, more likely to have quit smoking af
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。
需要用于商业化训练或医疗器械注册（NMPA/FDA）？
公开数据往往缺乏完整的病理回证与专家标注。千方医数集依托陕川双基地与超十家三甲医院直连，提供完全合规、去标识化、支持注册级质控的专病数据集交易服务。
