arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2306.13699q-bio.QMcs.AIcs.LGq-bio.BM
收藏

用于生物分子相互作用预测的曲率增强图卷积网络

Curvature-enhanced Graph Convolutional Network for Biomolecular Interaction Prediction

Hunan University(湖南大学);Case Western Reserve University(凯斯西储大学);Nanyang Technological University(南洋理工大学);Shandong University(山东大学)

Cong Shen, Pingjian Ding, Junjie Wee, Jialin Bi, Jiawei Luo, Kelin Xia

AI总结:

首次提出曲率增强图卷积网络(CGCN),采用Ollivier-Ricci曲率刻画网络局部结构并作为特征聚合权重,在十四个真实生物分子相互作用网络中的十三个上优于现有模型,并在模拟数据中表现出对传统GCN的全面优势。

摘要:

几何深度学习在非欧几里得数据分析中展现了巨大潜力。将几何见解融入学习架构对其成功至关重要。在此,我们首次提出了一种用于生物分子相互作用预测的曲率增强图卷积网络(CGCN)。我们的CGCN采用Ollivier-Ricci曲率(ORC)来刻画网络局部结构,并增强GCN的学习能力。具体而言,ORC基于来自节点邻域的局部拓扑进行评估,并进一步在消息传递过程中作为特征聚合的权重使用。我们的CGCN模型在十四个真实世界的生物分子相互作用网络和一系列模拟数据上进行了广泛验证。结果发现,我们的CGCN能够取得最先进的结果。据我们所知,它在十四个真实世界数据集中的十三个上优于所有现有模型,并在剩余的一个数据集中排名第二。模拟数据的结果表明,无论正负曲率比率、网络密度和网络大小(当大于500时)如何,我们的CGCN模型都优于传统的GCN模型。

英文摘要:

Geometric deep learning has demonstrated a great potential in non-Euclidean data analysis. The incorporation of geometric insights into learning architecture is vital to its success. Here we propose a curvature-enhanced graph convolutional network (CGCN) for biomolecular interaction prediction, for the first time. Our CGCN employs Ollivier-Ricci curvature (ORC) to characterize network local structures and to enhance the learning capability of GCNs. More specifically, ORCs are evaluated based on the local topology from node neighborhoods, and further used as weights for the feature aggregation in message-passing procedure. Our CGCN model is extensively validated on fourteen real-world bimolecular interaction networks and a series of simulated data. It has been found that our CGCN can achieve the state-of-the-art results. It outperforms all existing models, as far as we know, in thirteen out of the fourteen real-world datasets and ranks as the second in the rest one. The results from the simulated data show that our CGCN model is superior to the traditional GCN models regardless of the positive-to-negativecurvature ratios, network densities, and network sizes (when larger than 500).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑