GleghornLab/temperature_stability

该数据集旨在预测蛋白质在65摄氏度下的结构稳定性。它包含两个字段：蛋白质序列（seq）和表示结构稳定性的标签（label）。数据集分为训练集、验证集和测试集，分别包含283,057、62,973和73,205个样本。数据集根据TemStaPro数据集策略进行改编，并遵循Apache-2.0许可发布。

This dataset aims to predict the structural stability of proteins at 65 degrees Celsius. It includes two fields: a protein sequence (seq) and a label indicating structural stability (label). The dataset is split into training, validation, and test sets, containing 283,057, 62,973, and 73,205 samples respectively. The dataset is adapted from the TemStaPro dataset strategy and is released under the Apache-2.0 License.