The RESP AI model accelerates the identification of tight-binding antibodies.
The RESP AI model accelerates the identification of tight-binding antibodies.
复制标题
DOI：
10.1038/s41467-023-36028-8
复制
发表时间：
2023-01-28
影响因子：
16.6
通讯作者：
Wang W
中科院分区：
文献类型：
--
作者：
Parkinson J;Hard R;Wang W
高亲和力抗体通常通过定向进化来鉴定，这可能需要多次重复的诱变和选择以找到最佳候选物。深度学习技术有可能加速这一过程，但现有方法无法提供评估预测可靠性所需的置信区间或不确定性。在这里，我们提出了一个称为RESP的管道，用于高效识别高亲和力抗体。我们开发了一种学习表示，它在超过300万个人类B细胞受体序列上进行了训练，以编码抗体序列。然后，我们开发了一个变分贝叶斯神经网络进行有序回归的一组定向进化序列装箱的关闭率和量化的可能性是紧密结合剂对抗原。重要的是，该模型可以评估定向进化文库中不存在的序列，从而大大扩展了搜索空间，以发现用于实验评估的最佳序列。我们通过将PD-L1抗体Atezolizumab的KD提高17倍证明了这一管道的强大功能，这一成功说明了RESP在促进一般抗体开发方面的潜力。高亲和力抗体通常通过定向进化来鉴定，但深度学习方法有很大的希望。在本文中，作者报告了RESP，一种用于高效鉴定高亲和力抗体的管道，并将其应用于PD-L1抗体Atezolizumab。
High-affinity antibodies are often identified through directed evolution, which may require many iterations of mutagenesis and selection to find an optimal candidate. Deep learning techniques hold the potential to accelerate this process but the existing methods cannot provide the confidence interval or uncertainty needed to assess the reliability of the predictions. Here we present a pipeline called RESP for efficient identification of high affinity antibodies. We develop a learned representation trained on over 3 million human B-cell receptor sequences to encode antibody sequences. We then develop a variational Bayesian neural network to perform ordinal regression on a set of the directed evolution sequences binned by off-rate and quantify their likelihood to be tight binders against an antigen. Importantly, this model can assess sequences not present in the directed evolution library and thus greatly expand the search space to uncover the best sequences for experimental evaluation. We demonstrate the power of this pipeline by achieving a 17-fold improvement in the KD of the PD-L1 antibody Atezolizumab and this success illustrates the potential of RESP in facilitating general antibody development. High-affinity antibodies are often identified through directed evolution but deep leaning methods hold great promise. Here the authors report RESP, a pipeline for efficient identification of high affinity antibodies, and apply this to the PD-L1 antibody Atezolizumab.
登录
查看更多内容
影响因子：
4.6
作者：
Li Y;Chi Y;Han S;Miao Y;Chen L
通讯作者：
Chen L
影响因子：
4.3
作者：
通讯作者：
--
影响因子：
--
作者：
Ahmad ZA;Yeap SK;Ali AM;Ho WY;Alitheen NB;Hamid M
通讯作者：
Hamid M
影响因子：
5.8
作者：
Khurana, Sameer;Rawi, Reda;Mall, Raghvendra
通讯作者：
Mall, Raghvendra
影响因子：
5.8
作者：
Dunbar, James;Deane, Charlotte M.
通讯作者：
Deane, Charlotte M.