CAFA3 based dataset

Dataset based on CAFA3 database challenge. Functions presented in at least 50 and the duplicated proteins were removed from different sets. Each file contains the ontology (bp for Biological Process, cc for Cellular Component, and mf for Molecular Function) and the set (training, validation and test). For generated for augmentation, it has the identification of augmented_training.

本数据集依托CAFA3数据库挑战赛构建。筛选出现频次不少于50次的功能，并在各数据集划分中移除重复蛋白质。每个文件均包含本体类别（bp即生物过程（Biological Process）、cc即细胞组分（Cellular Component）以及mf即分子功能（Molecular Function））与数据集子集（训练集、验证集与测试集）。用于数据增强的生成数据集带有augmented_training标识。