Synthyra/BIOGRID-MV

BIOGRID数据集是一个生物医学领域的蛋白质、遗传和化学相互作用关系的综合数据库。该数据集是Multi-Validated (MV)版本，通过特定的选择标准筛选而出。它包含了蛋白质之间的相互作用对，并且确保每个相互作用对中的A和B实体都有映射的序列。在数据集的构建中，优先使用SwissProt IDs。数据集共有训练集部分，包含了497083个示例。The BIOGRID dataset is a comprehensive biomedical resource of curated protein, genetic, and chemical interactions. This dataset is the Multi-Validated (MV) version, selected through specific criteria. It contains protein interaction pairs, ensuring that both A and B entities in each interaction pair have mapped sequences. SwissProt IDs are used preferentially in the construction of the dataset. The dataset includes a training set with 497083 examples.