Protein design using structure-based residue preferences.
Protein design using structure-based residue preferences.
复制标题
使用基于结构的残基偏好进行蛋白质设计。
DOI：
10.1038/s41467-024-45621-4
复制
发表时间：
2024
影响因子：
16.6
通讯作者：
Marks,DeboraS
中科院分区：
文献类型：
--
作者：
Ding,David;Shaw,AdaY;Sinai,Sam;Rollins,Nathan;Prywes,Noam;Savage,DavidF;Laub,MichaelT;Marks,DeboraS
蛋白质设计的最新发展依赖于具有高达数百万个参数的大型神经网络，但尚不清楚哪些残基依赖性对于确定蛋白质功能至关重要。在这里，我们表明，在单个残基上的氨基酸偏好-不考虑突变相互作用-可以解释8个数据集上的大部分，有时几乎所有的组合突变效应（R2~ 78-98%）。因此，很少有观察结果（突变残基数量的约100倍）能够准确预测保留的变体效应（Pearson r > 0.80）。我们假设残基周围的局部结构背景足以预测突变偏好，并开发了一种名为CoVES（CombinatorialVariantEffects fromStructure）的无监督方法。我们的研究结果表明，CoVES不仅优于无模型方法，而且与创建功能和多样性蛋白质变体的复杂模型相似。CoVES为识别功能性蛋白质突变的复杂模型提供了一种有效的替代方案。
Recent developments in protein design rely on large neural networks with up to 100s of millions of parameters, yet it is unclear which residue dependencies are critical for determining protein function. Here, we show that amino acid preferences at individual residues—without accounting for mutation interactions—explain much and sometimes virtually all of the combinatorial mutation effects across 8 datasets (R2~ 78-98%). Hence, few observations (~100 times the number of mutated residues) enable accurate prediction of held-out variant effects (Pearson r > 0.80). We hypothesized that the local structural contexts around a residue could be sufficient to predict mutation preferences, and develop an unsupervised approach termed CoVES (CombinatorialVariantEffects fromStructure). Our results suggest that CoVES outperforms not just model-free methods but also similarly to complex models for creating functional and diverse protein variants. CoVES offers an effective alternative to complicated models for identifying functional protein mutations.