非小细胞肺癌肿瘤浸润T细胞TCR库分析[tet_sorted_PBLT_cells]

数据集获取

源站：https://ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE151531

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

We analyzed 778,938 T cell receptor (TCR) CDR3b sequences from 178 non-small cell lung cancer (NSCLC) patients using GLIPH2 (Grouping of Lymphocyte Interactions with Paratope Hotspots 2). We identified over 66,000 TCR shared specificity groups, of which over 400 were enriched in tumor vs. adjacent lung. We focused on one tumor-enriched specificity group and used a yeast display library to identify the peptide epitopes. These include peptides from TMEM161A, which is an overexpressed antigen in NSCLC, and homologous peptides from Epstein-Barr virus (EBV) and E. coli, aligning with recent reports of virus-specific T cells in tumor infiltrates. Overall, we analyzed a very large dataset of TCR sequences from NSCLC patients and found thousands of specificities shared by three or more patients. This creates a database of TCR shared specificity groups in NSCLC, and also a template for mining and understanding the specificity of infiltrating T cells for any cancer.

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。