Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Feb 26:12:635451.
doi: 10.3389/fgene.2021.635451. eCollection 2021.

An Efficient Computational Model for Large-Scale Prediction of Protein-Protein Interactions Based on Accurate and Scalable Graph Embedding

Xiao-Rui Su  1   2   3 , Zhu-Hong You  1   2   3 , Lun Hu  1   2   3 , Yu-An Huang  1 , Yi Wang  1   2   3 , Hai-Cheng Yi  1   2   3
Affiliations

An Efficient Computational Model for Large-Scale Prediction of Protein-Protein Interactions Based on Accurate and Scalable Graph Embedding

Xiao-Rui Su et al. Front Genet. .

Abstract

Protein-protein interaction (PPI) is the basis of the whole molecular mechanisms of living cells. Although traditional experiments are able to detect PPIs accurately, they often encounter high cost and require more time. As a result, computational methods have been used to predict PPIs to avoid these problems. Graph structure, as the important and pervasive data carriers, is considered as the most suitable structure to present biomedical entities and relationships. Although graph embedding is the most popular approach for graph representation learning, it usually suffers from high computational and space cost, especially in large-scale graphs. Therefore, developing a framework, which can accelerate graph embedding and improve the accuracy of embedding results, is important to large-scale PPIs prediction. In this paper, we propose a multi-level model LPPI to improve both the quality and speed of large-scale PPIs prediction. Firstly, protein basic information is collected as its attribute, including positional gene sets, motif gene sets, and immunological signatures. Secondly, we construct a weighted graph by using protein attributes to calculate node similarity. Then GraphZoom is used to accelerate the embedding process by reducing the size of the weighted graph. Next, graph embedding methods are used to learn graph topology features from the reconstructed graph. Finally, the linear Logistic Regression (LR) model is used to predict the probability of interactions of two proteins. LPPI achieved a high accuracy of 0.99997 and 0.9979 on the PPI network dataset and GraphSAGE-PPI dataset, respectively. Our further results show that the LPPI is promising for large-scale PPI prediction in both accuracy and efficiency, which is beneficial to other large-scale biomedical molecules interactions detection.

Keywords: GraphZoom; graph embedding; large-scale; protein-protein interaction; weighted graph.

PubMed Disclaimer

Conflict of interest statement

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Figures

Figure 1
Figure 1
The overview of the proposed model.
Figure 2
Figure 2
Timing experiments of four parts on PPI network dataset and GraphSAGE-PPI dataset.
Figure 3
Figure 3
Timing experiments of different embedding methods on PPI network dataset and GraphSAGE-PPI dataset.
Figure 4
Figure 4
Accuracy and timing experiments on two benchmark datasets. (A) Model performance with respect to the coarsening level on PPI network dataset. (B) Model performance with respect to the coarsening level on the GraphSAGE-PPI dataset. (C) Model performance about fusion parameter on PPI network dataset. (D) Model performance about fusion parameter on the GraphSAGE-PPI dataset.
Figure 5
Figure 5
(A) The change of link number and node number with the coarsening level increasing on the PPI network dataset. (B) The change of link number and node number with the coarsening level increasing on the GraphSAGE-PPI dataset.
See this image and copyright information in PMC

References

    1. Belkin M., Niyogi P. (2003). Laplacian eigenmaps for dimensionality reduction and data. Neural Comput. 15, 1373–1396. 10.1162/089976603321780317 - DOI
    1. Chen K. -H., Wang T. -F., Hu Y. -J. (2019). Protein-protein interaction prediction using a hybrid feature representation and a stacked generalization scheme. BMC Bioinformatics 20:308. 10.1186/s12859-019-2907-1, PMID: - DOI - PMC - PubMed
    1. Deng C., Zhao Z., Wang Y., Zhang Z., Feng Z. (2019). ‘GraphZoom: a multi-level spectral approach for accurate and scalable graph embedding.’ Comput. Sci. [Preprint].
    1. Gavin A. -C., Bösche M., Krause R., Grandi P., Marzioch M., Bauer A., et al. (2002). Functional organization of the yeast proteome by systematic analysis of protein complexes. Nature 415, 141–147. 10.1038/415141a, PMID: - DOI - PubMed
    1. Grover A., Leskovec J. (2016). “node2vec: Scalable feature learning for networks” in Proceedings of the 22nd ACM SIGKDD international conference on knowledge 1117 discovery and data mining (ACM); August 13–17, 2016; 855–864. - PMC - PubMed