GleghornLab/taxonomy_kingdom

该数据集包含了从UniProt数据库中筛选和处理的生物序列信息。它主要由三个部分组成：训练集、验证集和测试集。每个条目包含序列信息、所属界（kingdom）以及对应的标签。数据集通过过滤序列长度、提取分类学ID、去除缺失值、序列聚类等方法进行了预处理。最终，数据集根据界分类生成了标签，并确保每个界至少有100个样本。数据集适用于生物序列分类任务。

This dataset consists of processed biological sequence information from the UniProt database. It is divided into three parts: training set, validation set, and test set. Each entry includes sequence information, the kingdom it belongs to, and corresponding labels. The dataset has been preprocessed through methods such as filtering sequence lengths, extracting taxonomic IDs, removing missing values, sequence clustering, etc. Finally, labels are generated based on the kingdom classification, ensuring that each kingdom has at least 100 samples. The dataset is suitable for biological sequence classification tasks.