Graph embedding-based novel protein interaction prediction via higher-order graph convolutional network

Abstract

Protein-protein interactions (PPIs) are essential for most biological processes. However, current PPI networks present high levels of noise, sparseness and incompleteness, which limits our ability to understand the cell at the system level from the PPI network. Predicting novel (missing) links in noisy PPI networks is an essential computational method for automatically expanding the human interactome and for identifying biologically legitimate but undetected interactions for experimental determination of PPIs, which is both expensive and time-consuming. Recently, graph convolutional networks (GCN) have shown their effectiveness in modeling graph-structured data, which employ a 1-hop neighborhood aggregation procedure and have emerged as a powerful architecture for node or graph representations. In this paper, we propose a novel node (protein) embedding method by combining GCN and PageRank as the latter can significantly improve the GCN's aggregation scheme, which has difficulty in extending and exploring topological information of networks across higher-order neighborhoods of each node. Building on this novel node embedding model, we develop a higher-order GCN variational auto-encoder (HO-VGAE) architecture, which can learn a joint node representation of higher-order local and global PPI network topology for novel protein interaction prediction. It is worth noting that our method is based exclusively on network topology, with no protein attributes or extra biological features used. Extensive computational validations on PPI prediction task demonstrate our method without leveraging any additional biological information shows competitive performance-outperforms all existing graph embedding-based link prediction methods in both accuracy and robustness.

Topological network measures for drug repositioning

“…The same embedding method has also been used to infer disease-related miRNAs [ 56 ]. Graph convolutional neural networks (GCNs) have also shown interesting results for the problems of prediction of the side-effects of drug combinations [ 57 , 58 ] but also novel PPIs [ 59 ], drug-target interactions [ 60 ] or gene function [ 61 ]. Given the pace of development of deep learning and graph embedding techniques in the fields of artificial intelligence, it is likely that GCNs will be instrumental to drug discovery and repositioning in the future.…”

DWPPI: A Deep Learning Approach for Predicting Protein–Protein Interactions in Plants Based on Multi-Source Information With a Large-Scale Biological Network

“… Xu et al (2020) developed a method called PPI-GE, which predicts PPIs by combining the contact graph energy and physicochemical graph energy. Xiao and Deng (2020) proposed a new node embedding approach to predict PPIs that captures the topological information from higher-order neighborhoods of PPI network nodes. Li et al (2021) built a novel model called GAEMDA that used a graph neural network-based encoder to detect the miRNA-disease associations.…”

BScNets: Block Simplicial Complex Neural Networks

“…Graph Convolutional Networks (GCNs) is a powerful machinery for graph learning, allowing for efficient exploration of various pairwise interactions among graph nodes. However, most GCN-based approaches tend to be limited in their ability to efficiently exploit and propagate information across higher-order structures (Morris et al 2019;Xiao and Deng 2020). In turn, many recent studies on cyber-physical, social, and financial networks suggest that relations among multi-node graph structures, as opposed to pairwise interaction among nodes, may be the key toward understanding hidden mechanisms behind structural organization of complex network systems.…”