数据集获取

git clone https://github.com/dfimerel/Breast-Cancer-datasets-to-mine.git

curl -L -o repo.zip https://github.com/dfimerel/Breast-Cancer-datasets-to-mine/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

Breast-Cancer-datasets-to-mine

Collection of datasets with breast cancer samples to mine and explore.

cBioPortal & ICGC

Contains gene expression, DNA mutations, CNA, DNA methylation, protein expression, histopathology images

• cBioPortal
• ICGC

PCAWG

Contains whole-genome sequencing

• PCAWG

GENIE

Contains exome mutations focused on common cancer related genes

• GENIE

Cell lines

Contains gene expression, DNA mutations, CNA and other from cancer cell lines

• Cancer Cell Line Encyclopedia

Early-stage BC

Here you can find datasets with different molecular data in early-stage BC

• RNA sequencing-based single sample predictors of molecular subtype and risk of recurrence for clinical assessment of early-stage breast cancer

Metastatic BC

Here you can find datasets with different molecular data in metastatic BC

• Genomic profiling and pre-clinical modelling of breast cancer leptomeningeal metastasis reveals acquisition of a lobular-like phenotype
• Phylogenetic reconstruction of breast cancer reveals two routes of metastatic dissemination associated with distinct clinical outcome
• Characterization of Stromal Tumor-infiltrating Lymphocytes and Genomic Alterations in Metastatic Lobular Breast Cancer
• Genomic and Transcriptomic Analyses of Breast Cancer Primaries and Matched Metastases in AURORA, the Breast International Group (BIG) Molecular Screening Initiative
• Multiomics in primary and metastatic breast tumors from the AURORA US network finds microenvironment and epigenetic drivers of metastasis
• Genomic characterization of metastatic breast cancers
• [Genomic characterization of metastatic patterns from prospective clinical sequencing of 25,000 patients](https://doi.org/10.1016/j.cell.2022.

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。

完整仓库：github.com/dfimerel/Breast-Cancer-datasets-to-mine