SaProtHub/Dataset-GB1-fitness

本数据集包含突变GB1蛋白质的健身分数。蛋白质格式为氨基酸序列。数据集分为训练集、验证集和测试集，分别包含119644、14917和14800条数据。标签为相对于野生型的蛋白质健身分数，所有分数均大于0，分数大于1表示健身水平高于野生型。

This dataset contains the fitness scores of mutant GB1 proteins. The protein format is in amino acid sequences. The dataset is split into training, validation, and test sets with 119,644, 14,917, and 14,800 entries respectively. The labels represent the fitness scores relative to the wildtype, with all scores being greater than 0, and scores greater than 1 indicating higher fitness than the wildtype.