biolm/human-proteome-esmc-embeddings
收藏Hugging Face2025-10-29 更新2025-11-01 收录
下载链接:
https://hf-mirror.com/datasets/biolm/human-proteome-esmc-embeddings
下载链接
链接失效反馈官方服务:
资源简介:
该数据集提供了236,252个人类蛋白质的预计算嵌入,使用EvolutionaryScale的ESMC蛋白质语言模型。这些嵌入捕获了进化和结构信息,适用于蛋白质功能预测、相似性搜索和迁移学习任务。数据集提供了两种模型大小:ESMC 300M和ESMC 600M,并且包含了层级的嵌入。数据集以分片的Parquet文件格式提供,方便快速下载和并行加载。
This dataset provides pre-computed embeddings for 236,252 human proteins using EvolutionaryScales ESMC protein language models. These embeddings capture evolutionary and structural information useful for protein function prediction, similarity search, and transfer learning tasks. The dataset offers two model sizes: ESMC 300M and ESMC 600M, and includes layer-wise embeddings. The data is provided in sharded Parquet files for efficient downloading and parallel loading.
提供机构:
biolm



