fredzzp/backboneref
收藏Hugging Face2025-08-02 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/fredzzp/backboneref
下载链接
链接失效反馈官方服务：
资源简介：
BackboneRef数据集是一个合成的蛋白质序列资源，包含240,811个蛋白质骨架和约240万个设计序列，分为三个子集：未过滤的BRu、注重结构设计性的BRq和注重结构新颖性的BRn。数据集用于蛋白质语言模型的训练，提供结构多样性和新颖性。
The BackboneRef dataset is a synthetic protein sequence resource containing 240,811 protein backbones and approximately 2.4 million designed sequences, divided into three subsets: unfiltered BRu, structurally designable BRq, and structurally novel BRn. The dataset is used for training protein language models, providing structural diversity and novelty.
提供机构：
fredzzp
