ailab-bio/PROTAC-Splitter-Dataset

PROTAC-Splitter数据集是一个用于训练和评估基于Transformer的PROTAC-Splitter模型的数据集。它包含文本和标签两种特征，并分为训练集、验证集、测试集和保留集。数据集涵盖化学、医学、目标蛋白降解和PROTAC等相关领域。

The PROTAC-Splitter dataset is a dataset for training and evaluating the Transformer-based PROTAC-Splitter model. It includes text and label features and is split into training, validation, test, and held_out sets. The dataset covers areas such as chemistry, medicine, target protein degradation, and PROTAC.