AmelieSchreiber/600K_binding_sites

该数据集是从UniProt中整理的，测试集是通过随机选择整个蛋白质家族来创建的。训练集和测试集的比例大约为80/20。所有的结合位点和活性位点注释都被合并了。所有长度超过1000个氨基酸的序列被分割成不超过1000个残基的非重叠片段。

This dataset was curated from UniProt. The test set was constructed by randomly selecting entire protein families. The ratio of the training set to the test set is approximately 80/20. All binding site and active site annotations were merged. All sequences longer than 1000 amino acids were split into non-overlapping fragments with no more than 1000 residues each.

原始信息汇总

数据集概述

数据来源

• 数据集由UniProt整理。

数据处理

• 测试集通过随机选择整个蛋白质家族创建。
• 训练集和测试集的划分比例约为80/20。
• 所有结合位点和活性位点注释已合并。
• 所有长度超过1000个氨基酸的序列被分割成不超过1000个残基的非重叠块。

许可证

• 该数据集遵循MIT许可证。