已取代 - 错义变异在人类ARID DNA结合蛋白家族功能注释中的应用

数据集获取

源站：https://datashare.ed.ac.uk/handle/10283/4015

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

SUPERSEDED - This dataset has been replaced by the one which can be found at https://doi.org/10.7488/ds/3190 . ## Missense variants are alterations to protein coding sequences that alter the identity of an amino acid at a specific site. They can be deleterious if the site is required for function but are likely to be tolerated at other sites. Consequently, missense variation within a healthy population mirrors the effects of negative selection on protein structure and function. Advances in high-throughput sequencing have dramatically increased the sample size of human variation data, allowing for population-wide interpretations of selective pressures. In this study, we developed a convenient framework for mapping missense variants onto solved or modelled protein structures and applied it to characterize the ARID family of gene regulators. ARID family members are implicated in multiple cancer types, developmental disorders, and immunological diseases but current understanding of their mechanistic roles is incomplete. Combined with phylogenetic and structural analyses, our approach allowed us to identify important sites for protein-protein interactions, histone code recognition, and DNA binding by the ARID proteins. We propose that missense variants can serve as a valuable tool for complementing experimental findings and formulating mechanistic hypotheses.

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。