cskokgibbs/BEELINE-mHSC-no-label-pretokenized-NT
收藏官方服务：
资源简介：
该数据集包含了基因(gene)、转录因子(TF)、交互作用(interaction)等信息的记录。interaction字段存储交互作用的整数编码，input_ids和attention_mask字段分别存储处理后的输入标识和注意力掩码。数据集仅包含训练集(train)，共有5048316个样本，总文件大小为39622447134字节。
The dataset contains records of genes, transcription factors (TF), and interactions. The interaction field stores integer encodings of the interactions, while input_ids and attention_mask fields store the processed input identifiers and attention masks respectively. The dataset includes only a training set (train) with a total of 5048316 samples and an overall file size of 39622447134 bytes.
提供机构：
cskokgibbs
