TerminatorJ/relabel_output-XETG00048__0003392__VUILD115__20230313__191400

该数据集包含多个特征，包括Expression（表达量，数据类型为float64序列）、Split（划分类型，数据类型为字符串）、Cell_id（细胞ID，数据类型为字符串）、Gene（基因，数据类型为字符串序列）、Cell_Ids（细胞ID列表，数据类型为字符串）、Ranked_Gene_Names（排名基因名称，数据类型为字符串序列）、Full_Tokens（完整标记，数据类型为int64序列）和Gene_Gene_Matrix（基因-基因矩阵，数据类型为float64序列）。数据集被划分为训练集、测试集和验证集，分别包含43979、13743和10996个样本，总大小为2313124531字节。

The dataset contains multiple features, including Expression (expression levels, data type is float64 sequence), Split (split type, data type is string), Cell_id (cell ID, data type is string), Gene (gene, data type is string sequence), Cell_Ids (list of cell IDs, data type is string), Ranked_Gene_Names (ranked gene names, data type is string sequence), Full_Tokens (full tokens, data type is int64 sequence), and Gene_Gene_Matrix (gene-gene matrix, data type is float64 sequence). The dataset is divided into train, test, and validation sets, containing 43979, 13743, and 10996 samples respectively, with a total size of 2313124531 bytes.