肌动蛋白失调诱导小细胞肺癌神经内分泌可塑性与免疫逃逸

数据集获取

源站：https://ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE280263

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

Small cell lung cancer (SCLC) is aggressive with limited therapeutic options. Despite recent advances in targeted therapies and immunotherapies, therapy resistance is a recurring issue, which might be partly due to tumor cell plasticity, a change in cell fate. Nonetheless, the mechanisms underlying tumor cell plasticity and immune evasion in SCLC remain elusive. CRACD, a capping protein inhibitor that promotes actin polymerization, is frequently inactivated in SCLC. Cracd knockout (KO) transforms preneoplastic cells into SCLC tumor-like cells and promotes in vivo SCLC development driven by Rb1, Trp53, and Rbl2 triple KO. Cracd KO induces neuroendocrine (NE) plasticity and increases tumor cell heterogeneity of SCLC tumor cells via regulated NOTCH1 signaling by actin cytoskeleton disruption. CRACD depletion also reduces nuclear actin and induces EZH2-mediated H3K27 methylation. This nuclear event suppresses the MHC-I genes and thereby depletes intratumoral CD8+ T cells for accelerated SCLC tumorigenesis. Pharmacological blockade of EZH2 inhibits CRACD-negative SCLC tumorigenesis by restoring MHC-I expression and immune surveillance. Unsupervised single-cell transcriptomics identifies SCLC patient tumors with concomitant inactivation of CRACD and downregulated MHC-I pathway. This study defines CRACD, an actin regulator, as a tumor suppressor that limits cell plasticity and immune evasion and proposes EZH2 blockade as a viable therapeutic option for CRACD-negative SCLC.

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。