genbio-ai/contact_prediction_binary_rag

这是一个蛋白质接触图预测数据集，用于预测蛋白质序列中两个残基是否在小于8埃的阈值内接触。数据集包括蛋白质序列和对应的接触标签，分为训练集、验证集和测试集。数据来源于trRosetta数据集，并采用Apache-2.0许可证发布。

This is a contact map prediction dataset for proteins, which is used to predict whether two residues in a protein sequence are in contact within a threshold of less than 8 Angstroms. The dataset includes protein sequences and their corresponding contact labels, and is split into training, validation, and test sets. The data is sourced from the trRosetta dataset and is released under the Apache-2.0 License.