癌症纳米疫苗疗效最大化及免疫治疗应答与非应答者的免疫细胞图谱

数据集获取

源站：https://ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE273375

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

The therapeutic efficacy of cancer vaccines can be optimized from 3 aspects: adjuvants, vaccine formulation, and processing of tumor antigens. Herein, various different adjuvants, such as toll like receptors and STING agonists etc., and their combinations were compared in cancer nanovaccines loaded with whole tumor antigens were illustrated. By comparing different sized nanovaccines and micronvaccines, 200nm-400nm and 2.5μm were discovered to be optimal sizes of nanovaccines and micronvaccines. Rapid freezing, fixation, heating, salting-out, ethanol precipitate can affect the immunogenicity of tumor antigens and efficacy of cancer vaccines. The optimal cancer vaccine can cure all or most tumor-bearing body in melanoma mouse model, lung cancer mouse model, subcutaneous pancreatic cancer model, orthotopic pancreatic cancer model, melanoma lung metastasis model. In addition, the immune cell profiles were systematically investigated using single-cell sequencing, in blood, splenocytes and draining lymph nodes of healthy mice, PBS treated tumor-bearing mice, vaccine-treated non-cured mice and cured mice after different time. By comparing 21 samples, some featured clusters and markers, such as S100A4, KLRG1, SIPR5, CXCR3, IL2Ra, IKZF2, CX3CR1, S100A8, and S100A9 etc., were identified to distinguish responders and non-responders to immunotherapy. These biomarkers were verified and confirmed the feasibility of predicting therapeutic efficacy in mouse cancer model and cancer patients. In summary, this study presented a method to optimize cancer nanovacines from different aspects, systematically investigated immune cell profiles in non-responders and responders to immunotherapy, and discovered some featured biomarkers for predicting or distinguishing responders and non-responders to immunotherapy.

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。