willdaspit/afdb_50_sequence_clustered
收藏Hugging Face2025-11-01 更新2025-11-15 收录
下载链接：
https://hf-mirror.com/datasets/willdaspit/afdb_50_sequence_clustered
下载链接
链接失效反馈官方服务：
资源简介：
AFDB50序列聚类数据集，包含序列的注释信息。数据集中的序列通过RepId和cluster_id进行聚类标识，cluster_id按从小到大排序。数据集包括单序列和所有pldddt值，并标注了簇成员数、序列的Shannon熵、二联体的Shannon熵以及Gini-Simpson指数。数据集按照1/800的比例分为验证集和测试集，采用循环方式从最小簇开始划分。
The AFDB50 sequence clustering dataset includes annotated sequences. Sequences are clustered by RepId and cluster_id, with cluster_id sorted from smallest to largest. The dataset contains single sequences and all plddts, annotated with the number of cluster members, Shannon entropy of the sequence, Shannon entropy of bigrams, and Gini-Simpson index. The dataset is divided into validation and test sets at a ratio of 1/800, using a round-robin method starting from the smallest cluster.
提供机构：
willdaspit
