E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction.
E(3) equivariant graph neural networks for robust and accurate protein-protein interaction site prediction.
复制标题
E(3)等变图神经网络，用于稳健和准确的蛋白质相互作用位点预测。
DOI：
10.1371/journal.pcbi.1011435
复制
发表时间：
2023-08
影响因子：
4.3
通讯作者：
中科院分区：
文献类型：
--
作者：
人工智能驱动的蛋白质结构预测方法已经导致了计算结构生物学的范式转变，但预测蛋白质-蛋白质相互作用（PPI）的界面残基（即位点）的当代方法仍然依赖于实验结构。最近的研究已经证明了使用图卷积进行PPI位置预测的好处，但忽略了在三维空间中自然发生的对称性，并且仅在实验坐标上起作用。在这里，我们提出了EquiPPIS，一种用于PPI站点预测的E(3)等变图神经网络方法。EquiPPIS采用对称感知的图形卷积，可以在3D空间中进行平移、旋转和反射等变换，与不变卷积相比，可以为分子数据提供更丰富的表示。EquiPPIS在相同实验输入的基础上大大优于最先进的方法，并且通过使用来自AlphaFold2的预测结构模型获得比现有方法更好的准确性，从而表现出显著的鲁棒性，即使使用实验结构也无法实现。EquiPPIS可在https://github.com/Bhattacharya-Lab/EquiPPIS免费获得，可大规模准确预测PPI站点。预测蛋白质如何相互作用并表征蛋白质-蛋白质相互作用界面（即位点）上的相互作用残基对于理解由蛋白质-蛋白质相互作用（PPI）驱动的各种生物过程至关重要。尽管最近在人工智能驱动的蛋白质结构预测方面取得了显著进展，但现有的PPI位点预测方法仍然依赖于实验输入。本文提出了一种用于PPI站点预测的E(3)等变图神经网络方法，该方法考虑了三维空间中自然存在的对称性，并通过平移、旋转和反射进行了等变变换。严格的实验验证表明，与现有方法相比，我们的方法获得了显着提高的准确性和鲁棒性。我们的方法超越了目前仅通过实验输入的可能性，可以使用AlphaFold2的预测结构模型进行大规模PPI位点预测，而不会影响准确性。EquiPPIS的一个开源软件实现，在GNU通用公共许可证v3下获得许可，可以在https://github.com/Bhattacharya-Lab/EquiPPIS上免费获得。
Artificial intelligence-powered protein structure prediction methods have led to a paradigm-shift in computational structural biology, yet contemporary approaches for predicting the interfacial residues (i.e., sites) of protein-protein interaction (PPI) still rely on experimental structures. Recent studies have demonstrated benefits of employing graph convolution for PPI site prediction, but ignore symmetries naturally occurring in 3-dimensional space and act only on experimental coordinates. Here we present EquiPPIS, an E(3) equivariant graph neural network approach for PPI site prediction. EquiPPIS employs symmetry-aware graph convolutions that transform equivariantly with translation, rotation, and reflection in 3D space, providing richer representations for molecular data compared to invariant convolutions. EquiPPIS substantially outperforms state-of-the-art approaches based on the same experimental input, and exhibits remarkable robustness by attaining better accuracy with predicted structural models from AlphaFold2 than what existing methods can achieve even with experimental structures. Freely available at https://github.com/Bhattacharya-Lab/EquiPPIS, EquiPPIS enables accurate PPI site prediction at scale. Predicting how proteins interact and characterizing the interacting residues at the protein-protein interaction interface (i.e., sites) is of central importance to understanding various biological processes actuated by protein-protein interactions (PPI). Despite the remarkable recent progress in protein structure prediction driven by artificial intelligence, existing approaches for PPI site prediction still rely on experimental input. This paper presents an E(3) equivariant graph neural network approach for PPI site prediction that takes into account symmetries naturally occurring in 3-dimensional space and transforms equivariantly with translation, rotation, and reflection. Rigorous experimental validation shows that our method attains substantially improved accuracy and robustness over the existing approaches. Moving beyond what is currently possible with only experimental input, our method enables large-scale PPI site prediction using predicted structural models from AlphaFold2 without compromising on accuracy. An open-source software implementation of EquiPPIS, licensed under the GNU General Public License v3, is freely available at https://github.com/Bhattacharya-Lab/EquiPPIS.