cskokgibbs/TL-mouse-noGTL-hESC

该数据集包含基因、转录因子、交互作用等信息的记录，适用于生物信息学研究领域。数据集分为训练集，包含超过二百万的示例，每个示例包含多个特征字段，如格式化输入、输入ID、注意力掩码和标签等。

This dataset contains records of genes, transcription factors, interactions, and other information, suitable for the field of bioinformatics research. The dataset is split into a training set, which includes over two million examples, each with multiple feature fields such as formatted inputs, input IDs, attention masks, and labels.