ChaoHou/protein_dynamic_properties

本数据集包含用于训练SeqDance和ESMDance两个蛋白质语言模型的蛋白质序列、动态属性和特征权重。数据集包含一个CSV文件，其中包含蛋白质序列及其相关信息，以及多个HDF5文件，包含用于训练和测试的残基水平和成对动态属性。This dataset includes protein sequences, dynamic properties, and feature weights for training two protein language models, SeqDance and ESMDance. It contains a CSV file with protein sequences and their related information, as well as multiple HDF5 files with residue-level and pairwise dynamic properties for training and testing.