GleghornLab/SL_13

该数据集是从UniProt数据库中搜索并筛选出的蛋白质序列，根据特定的子细胞位置进行分类。数据集经过严格的质量控制，包括序列长度限制、相似度过滤、去除重复序列等步骤。最终包含的序列和对应的子细胞位置标签被用于机器学习模型的训练和评估。

This dataset consists of protein sequences searched and filtered from the UniProt database, categorized according to specific subcellular locations. The dataset has undergone rigorous quality control, including sequence length constraints, similarity filtering, and removal of duplicate sequences. The sequences and their corresponding subcellular location labels are used for training and evaluation of machine learning models.