Genentech/binary-atac-tutorial-data
收藏Hugging Face2026-02-23 更新2026-02-07 收录
下载链接：
https://hf-mirror.com/datasets/Genentech/binary-atac-tutorial-data
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含222种细胞类型中1154611个CREs（顺式调控元件）的二进制可访问性值。数据来源于CATlas（https://decoder-genetics.wustl.edu/catlasv1/humanenhancer/data/cCRE_by_cell_type/）。此版本的数据集用于gReLU教程2（https://github.com/Genentech/gReLU/blob/main/docs/tutorials/2_finetune.ipynb）。数据集结构包括.cell type（细胞类型名称）、.var（包含染色体、基因组起始位置、基因组结束位置和CRE类别）以及.X（一个222 × 1154611形状的二进制可访问性矩阵，采用压缩稀疏行格式）。
This dataset contains binary accessibility values for 1154611 CREs in 222 cell types. The original source of this data is CATlas (https://decoder-genetics.wustl.edu/catlasv1/humanenhancer/data/cCRE_by_cell_type/). For more details, see https://decoder-genetics.wustl.edu/catlasv1/catlas_humanenhancer/#!/. This version of the dataset is used in gReLU tutorial 2 (https://github.com/Genentech/gReLU/blob/main/docs/tutorials/2_finetune.ipynb). The dataset structure includes .cell type (name of the cell type), .var (containing chromosome, genomic start position, genomic end position, and CRE class), and .X (a binary accessibility matrix of shape 222 × 1154611 in Compressed Sparse Row format).
提供机构：
Genentech
