GleghornLab/plm_embedding_holder

该数据集包含多个分割，每个分割对应不同的蛋白质序列嵌入模型或方法，如prot_bert_bfd、esm2_t6_8M_UR50D等。每个分割包含蛋白质序列（seqs）和对应的向量表示（vectors）。数据集的总下载大小为45,200,194,610字节，总大小为34,260,792,408字节。每个分割的字节大小和示例数量也有所不同，例如prot_bert_bfd分割有761,184个示例，占用3,522,651,486字节。

This dataset contains multiple splits, each corresponding to different protein sequence embedding models or methods, such as prot_bert_bfd, esm2_t6_8M_UR50D, etc. Each split includes protein sequences (seqs) and their corresponding vector representations (vectors). The total download size of the dataset is 45,200,194,610 bytes, and the total size is 34,260,792,408 bytes. The byte size and number of examples for each split vary, for example, the prot_bert_bfd split has 761,184 examples and occupies 3,522,651,486 bytes.