five

SeprotHub/Dataset-TrpB_fitness_landsacpe

收藏
Hugging Face2025-05-09 更新2025-11-01 收录
下载链接:
https://hf-mirror.com/datasets/SeprotHub/Dataset-TrpB_fitness_landsacpe
下载链接
链接失效反馈
官方服务:
资源简介:
这个数据集包含了160000个来自β-色氨酸合成酶亚单位(TrpB)活性位点的四位点突变序列。TrpB负责将吲哚和L-丝氨酸合成为L-色氨酸。数据集的原始酶是Tm9D8*变体,与野生型相比有十个氨基酸替代。数据集针对183/184和227/228两个位点的对进行了四位点饱和库的构建。蛋白质序列以氨基酸序列格式表示。数据集分为训练集、验证集和测试集,分别包含128000、16000和16000个样本。标签表示突变适应性,即大肠杆菌菌株的生长率,最高适应性为1,越接近1表示适应性越好。

This dataset contains 160,000 sequences of four-site mutations of an enzyme active site from the β-subunit of tryptophan synthase (TrpB), which synthesizes L-tryptophan (Trp) from indole and L-serine (Ser). The parent enzyme is the Tm9D8* variant of TrpB, which differs from the wildtype TmTrpB by ten amino acid substitutions. The dataset is constructed with a four-site saturation library targeting two pairs of positions: 183/184 and 227/228. The protein sequences are represented in the amino acid sequence format. The dataset is split into training, validation, and test sets with 128,000, 16,000, and 16,000 samples respectively. The label represents the mutation fitness, which is the growth rate of the E. coli strain, with the maximum fitness being 1, and the closer to 1, the better the fitness.
提供机构:
SeprotHub
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作