Deep Mutational Learning Predicts ACE2 Binding and Antibody Escape to Combinatorial Mutations in the SARS-CoV-2 Receptor Binding Domain. Taft, Weber et al.

Yeast displayed RBD-library NGS sequencing data from FACS sorted binding/escape populations to ACE2 and 13 different SARS-CoV-2 binding antibodies, used to train and evaluate predictive models in "Deep Mutational Learning Predicts ACE2 Binding and Antibody Escape to Combinatorial Mutations in the SARS-CoV-2 Receptor Binding Domain" (Taft J, Weber C, et al, 2022)

Datasets are annotated by RBD sequence ('sequence_aa'), Binding Label (0 - escape, 1 - binding), distance from wild type RBD sequence ('Distance'), mAb tested ('Antibody'), and the RBM region and library each sequence is derived from ('Library')

All sequences/data combined is available as "Taft_Weber_Cell2022_FullData.csv". Alternatively, datasets for individual mAbs, and individual libraries are available in the "Full_sets" folder, separated first by library and then by mAb.

本研究所涉及的数据集源自酵母细胞表达的RBD-文库，通过流式细胞术（FACS）对ACE2结合/逃逸细胞群体进行测序，并针对13种不同的SARS-CoV-2结合抗体。该数据集被用于训练和评估预测模型，相关研究成果发表在《深度突变学习预测SARS-CoV-2受体结合域中ACE2结合与抗体逃逸的联合突变》一文中（Taft J, Weber C, 等人，2022年）。数据集的标注信息包括RBD序列（'sequence_aa'）、结合标签（0 - 逃逸，1 - 结合）、野生型RBD序列的距离（'Distance'）、测试的mAb（'Antibody'）以及每个序列所来源的RBM区域和文库（'Library'）。所有序列和数据组合均可从'Taft_Weber_Cell2022_FullData.csv'文件中获得。此外，针对单个mAb和单个文库的数据集可在'Full_sets'文件夹中找到，其中首先按文库分类，然后按mAb分类。