SaProtHub/TrpB_fitness_landsacpe_dataset
收藏资源简介：
该数据集包含160000个酶活性位点的四位置突变序列，这些序列来自色氨酸合成酶（TrpB）的β亚基，该酶催化从吲哚和L-丝氨酸合成L-色氨酸的过程。数据集中的父酶是TrpB变体Tm9D8*，它与野生型TmTrpB有十个氨基酸替换。四位置饱和库针对两对位置：183/184和227/228。数据集分为训练集、验证集和测试集，分别为128000、16000和16000个序列。标签表示突变适应性，这里代表大肠杆菌菌株的生长率。
This dataset contains 160000 sequences of four site mutation of an enzyme active site, involving the β-subunit of tryptophan synthase (TrpB). The parent enzyme is TrpB variant Tm9D8*, differing from wildtype TmTrpB by ten amino acid substitutions. The 4-site saturation library targeted two pairs of positions: 183/184 and 227/228. The dataset is split into training, validation, and test sets, containing 128000, 16000, and 16000 sequences respectively. The label represents mutation fitness, indicating the growth rate of E. coli strain.
