Protein Docking Model Evaluation by Graph Neural Networks.
Protein Docking Model Evaluation by Graph Neural Networks.
复制标题
DOI：
10.3389/fmolb.2021.647915
复制
发表时间：
2021
影响因子：
5
通讯作者：
Kihara D
中科院分区：
文献类型：
--
作者：
Wang X;Flannery ST;Kihara D
蛋白质的物理相互作用在许多重要的细胞过程中发挥着关键的功能作用。为了了解此类功能的分子机制，确定蛋白质复合物的结构至关重要。为了补充通常需要大量时间和资源的实验方法，已经开发了各种计算方法来预测蛋白质复合物的结构。在计算建模中，挑战之一是从大量生成的模型中识别接近原生的结构。在这里，我们开发了一种基于深度学习的方法，名为基于图神经网络的 DOcking decoy eValuation scorE (GNN-DOVE)。为了评估蛋白质对接模型，GNN-DOVE 提取界面区域并将其表示为图表。原子的化学性质和原子间距离分别用作图中节点和边的特征。 GNN-DOVE 在 Dockground 数据库中的对接模型上进行了训练、验证和测试，并在 Dockground 和 ZDOCK 基准的组合数据集以及 CAPRI 评分数据集上进行了进一步测试。 GNN-DOVE 的性能优于现有方法，包括 DOVE，这是我们之前在体素化结构模型上使用卷积神经网络的开发成果。
Physical interactions of proteins play key functional roles in many important cellular processes. To understand molecular mechanisms of such functions, it is crucial to determine the structure of protein complexes. To complement experimental approaches, which usually take a considerable amount of time and resources, various computational methods have been developed for predicting the structures of protein complexes. In computational modeling, one of the challenges is to identify near-native structures from a large pool of generated models. Here, we developed a deep learning–based approach named Graph Neural Network–based DOcking decoy eValuation scorE (GNN-DOVE). To evaluate a protein docking model, GNN-DOVE extracts the interface area and represents it as a graph. The chemical properties of atoms and the inter-atom distances are used as features of nodes and edges in the graph, respectively. GNN-DOVE was trained, validated, and tested on docking models in the Dockground database and further tested on a combined dataset of Dockground and ZDOCK benchmark as well as a CAPRI scoring dataset. GNN-DOVE performed better than existing methods, including DOVE, which is our previous development that uses a convolutional neural network on voxelized structure models.
登录
查看更多内容
影响因子：
3
作者：
Kingsley, Laura J.;Esquivel-Rodriguez, Juan;Lill, Markus A.
通讯作者：
Lill, Markus A.
影响因子：
2.9
作者：
Janin, Joel
通讯作者：
Janin, Joel
影响因子：
3
作者：
Fink, Florian;Hochrein, Jochen;Gronwald, Wolfram
通讯作者：
Gronwald, Wolfram
影响因子：
3.3
作者：
Esquivel-Rodriguez, Juan;Kihara, Daisuke
通讯作者：
Kihara, Daisuke
影响因子：
4.3
作者：
Alam, Nawsad;Goldstein, Oriel;Schueler-Furman, Ora
通讯作者：
Schueler-Furman, Ora