proteinglm/cloning_clf

Cloning CLF数据集用于蛋白质结构确定过程中的稳定性分类任务。数据集包含蛋白质序列和对应的标签，标签表示蛋白质在特定实验阶段是否稳定。数据集分为训练集和测试集，分别包含23,375和4,791个实例。数据集的来源是PredPPCrys，该数据集手动注释了数千个蛋白质的实验过程。数据集的特征包括蛋白质序列（seq）和标签（label），标签为浮点数，表示蛋白质序列的$k_cat$分数。数据集发布在Apache-2.0许可证下，并提供了相关的引用信息。

In the process of protein structure determination, each experimental stage corresponds to a stage tag to denote whether the protein is stable under that stage. The dataset contains protein sequence strings and integer labels, representing the sequence and stability, respectively. The dataset is divided into train and test sets, containing 23,375 and 4,791 instances, respectively. The dataset is sourced from PredPPCrys and is released under the Apache-2.0 license.