遇见数据集

SeprotHub/Dataset-Signal-Peptides

收藏
Hugging Face2025-05-13 更新2025-11-01 收录
官方服务:

资源简介:

该数据集包含25693个氨基酸序列及其对应的标签,每个氨基酸序列分为7个类别,包括Sec/SPI信号肽、Tat/SPI或Tat/SPII信号肽、Sec/SPII信号肽、Sec/SPIII信号肽、细胞质、跨膜和细胞外。数据集分为训练集、验证集和测试集,分别包含20490、2569和2634个样本。

This dataset contains 25693 amino acid sequences with corresponding labels, each categorized into 7 classes including Sec/SPI signal peptide, Tat/SPI or Tat/SPII signal peptide, Sec/SPII signal peptide, Sec/SPIII signal peptide, cytoplasm, transmembrane, and extracellular. The dataset is split into training, validation, and test sets with 20490, 2569, and 2634 samples respectively.

提供机构:
SeprotHub
二维码
社区交流群
二维码
科研交流群
商业服务