Generative design of de novo proteins based on secondary structure constraints using an attention-based diffusion model.
Generative design of de novo proteins based on secondary structure constraints using an attention-based diffusion model.
复制标题
DOI：
10.1016/j.chempr.2023.03.020
复制
发表时间：
2023-04
期刊：
影响因子：
23.5
通讯作者：
Bo Ni;D. L. Kaplan;M. Buehler
中科院分区：
文献类型：
--
作者：
Bo Ni;D. L. Kaplan;M. Buehler
我们报告了两个生成式深度学习模型，它们基于二级结构设计目标，通过整体内容或每个残基结构来预测氨基酸序列和3D蛋白质结构。这两个模型对于不完美的输入都是稳健的，并且提供了novodesign能力，因为它们可以发现尚未从自然机制或系统中发现的新蛋白质序列。残基水平的二级结构设计模型通常产生更高的精度和更多样化的序列。这些发现表明，在已知蛋白质之外的大量氨基酸序列中，蛋白质设计和功能结果存在未开发的机会。我们的模型基于基于注意力扩散模型，并在从实验已知的3D蛋白质结构中提取的数据集上进行训练，在各种生物或工程系统的条件生成设计中提供了许多下游应用。未来的工作可能包括额外的调节和探索所产生的蛋白质的其他功能特性，以获得结构目标以外的各种特性。
We report two generative deep-learning models that predict amino acid sequences and 3D protein structures on the basis of secondary-structure design objectives via either the overall content or the per-residue structure. Both models are robust regarding imperfect inputs and offerde novodesign capacity because they can discover new protein sequences not yet discovered from natural mechanisms or systems. The residue-level secondary-structure design model generally yields higher accuracy and more diverse sequences. These findings suggest unexplored opportunities for protein designs and functional outcomes within the vast amino acid sequences beyond known proteins. Our models, based on an attention-based diffusion model and trained on a dataset extracted from experimentally known 3D protein structures, offer numerous downstream applications in the conditional generative design of various biological or engineering systems. Future work could include additional conditioning and an exploration of other functional properties of the generated proteins for various properties beyond structural objectives.