deeeeeeeeee/PUNCH2_data
收藏Hugging Face2024-12-13 更新2024-12-14 收录
下载链接:
https://hf-mirror.com/datasets/deeeeeeeeee/PUNCH2_data
下载链接
链接失效反馈官方服务:
资源简介:
PUNCH2数据集是一个用于训练高精度内在无序蛋白质预测工具的数据集,该工具基于CNN神经网络。数据集中包含三个版本的数据文件,分别是IDR_fullyDisordered_dataset_30.json、IDR_fullyDisordered_dataset_80.json和IDR_fullyDisordered_dataset_100.json,这些文件包含了来自Disprot数据库的完全无序蛋白质,并且分别对应30%、80%和100%的序列同一性水平。此外,还提供了用于基准测试的CAID2数据集。
The PUNCH2 dataset is used for predicting intrinsically disordered proteins, built on a CNN-based neural network. The dataset includes three versions: IDR_fullyDisordered_dataset_30.json, IDR_fullyDisordered_dataset_80.json, and IDR_fullyDisordered_dataset_100.json, which contain fully disordered proteins from Disprot with different levels of sequence identity (30%, 80%, and 100% respectively). Additionally, a benchmarking set, CAID2 (Disorder_PDB), is also provided.
提供机构:
deeeeeeeeee



