An integrative approach to protein sequence design through multiobjective optimization.
An integrative approach to protein sequence design through multiobjective optimization.
复制标题
通过多目标优化进行蛋白质序列设计的综合方法。
DOI：
10.1101/2024.03.01.582670
复制
发表时间：
2024
期刊：
影响因子：
--
通讯作者：
Kortemme,Tanja
中科院分区：
文献类型：
--
作者：
Hong,Lu;Kortemme,Tanja
随着计算蛋白质设计领域方法学的最新进展，特别是基于深度学习的方法学进步，越来越需要能够将不同的模型和目标函数连贯地、直接地整合到生成性设计过程中的框架。在这里，我们演示了如何采用进化多目标优化技术来提供这样的方法。以已建立的非支配排序遗传算法II(NSGA-II)为优化框架，使用AlphaFold2和ProteinMPNN置信度来定义目标空间，并使用由ESM-1v和ProteinMPNN组成的变异算子对最不利位置进行排序和重新设计。以折叠开关蛋白RfaH的两态设计问题为例进行了深入研究，并以PAPD和钙调蛋白为例进行了高维设计，结果表明，与直接应用ProteinMPNN相比，进化多目标优化方法显著降低了RfaH天然序列恢复的偏差和方差。我们认为这一改进归因于三个因素：(I)信息丰富的变异算子的使用加速了序列空间的探索，(Ii)遗传算法固有的并行迭代设计过程改进了ProteinMPNN自回归序列解码方案，以及(Iii)Pareto前沿的显式近似导致了代表不同折衷条件的最佳设计候选者。我们预计这种方法很容易适应不同的模型，并与复杂规格的蛋白质设计任务广泛相关。
With recent methodological advances in the field of computational protein design, in particular those based on deep learning, there is an increasing need for frameworks that allow for coherent, direct integration of different models and objective functions into the generative design process. Here we demonstrate how evolutionary multiobjective optimization techniques can be adapted to provide such an approach. With the established Non-dominated Sorting Genetic Algorithm II (NSGA-II) as the optimization framework, we use AlphaFold2 and ProteinMPNN confidence metrics to define the objective space, and a mutation operator composed of ESM-1v and ProteinMPNN to rank and then redesign the least favorable positions. Using the two-state design problem of the foldswitching protein RfaH as an in-depth case study, and PapD and calmodulin as examples of higher-dimensional design problems, we show that the evolutionary multiobjective optimization approach leads to significant reduction in the bias and variance in RfaH native sequence recovery, compared to a direct application of ProteinMPNN. We suggest that this improvement is due to three factors: (i) the use of an informative mutation operator that accelerates the sequence space exploration, (ii) the parallel, iterative design process inherent to the genetic algorithm that improves upon the ProteinMPNN autoregressive sequence decoding scheme, and (iii) the explicit approximation of the Pareto front that leads to optimal design candidates representing diverse tradeoff conditions. We anticipate this approach to be readily adaptable to different models and broadly relevant for protein design tasks with complex specifications.