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
. 2019 Jun 10;20(Suppl 8):287.
doi: 10.1186/s12859-019-2768-7.

L2,1-GRMF: an improved graph regularized matrix factorization method to predict drug-target interactions

Zhen Cui  1 , Ying-Lian Gao  2 , Jin-Xing Liu  3   4 , Ling-Yun Dai  1 , Sha-Sha Yuan  1
Affiliations

L2,1-GRMF: an improved graph regularized matrix factorization method to predict drug-target interactions

Zhen Cui et al. BMC Bioinformatics. .

Abstract

Background: Predicting drug-target interactions is time-consuming and expensive. It is important to present the accuracy of the calculation method. There are many algorithms to predict global interactions, some of which use drug-target networks for prediction (ie, a bipartite graph of bound drug pairs and targets known to interact). Although these algorithms can predict some drug-target interactions to some extent, there is little effect for some new drugs or targets that have no known interaction.

Results: Since the datasets are usually located at or near low-dimensional nonlinear manifolds, we propose an improved GRMF (graph regularized matrix factorization) method to learn these flow patterns in combination with the previous matrix-decomposition method. In addition, we use one of the pre-processing steps previously proposed to improve the accuracy of the prediction.

Conclusions: Cross-validation is used to evaluate our method, and simulation experiments are used to predict new interactions. In most cases, our method is superior to other methods. Finally, some examples of new drugs and new targets are predicted by performing simulation experiments. And the improved GRMF method can better predict the remaining drug-target interactions.

Keywords: Drug-target interaction prediction; Graph regularization; L2,1-norm; Manifold learning; Matrix factorization.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Comparison of convergence about three methods on the NR dataset
Fig. 2
Fig. 2
Comparison of convergence about three methods on the GPCR dataset
Fig. 3
Fig. 3
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVd side of each method on the NR dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 4
Fig. 4
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVd side of each method on the GPCR dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 5
Fig. 5
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVd side of each method on the IC dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 6
Fig. 6
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVd side of each method on the E dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 7
Fig. 7
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVt side of each method on the NR dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 8
Fig. 8
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVt side of each method on the GPCR dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 9
Fig. 9
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVt side of each method on the IC dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 10
Fig. 10
PR curves for different methods are plotted together, providing a visual comparison between their prediction performances. The PR curves on the CVt side of each method on the E dataset. a WKNKN is not used, the PR curves for each method. b WKNKN is used, the PR curves for each method
Fig. 11
Fig. 11
A brief flow chart of the L2,1-GRMF method. It includes the process of inputting the original datasets to the final generation of the predicted score matrix
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Novac N. Challenges and opportunities of drug repositioning. Trends Pharmacol Sci. 2013;34(5):267–272. doi: 10.1016/j.tips.2013.03.004. - DOI - PubMed
    1. Hurle MR, Yang L, Xie Q, Rajpal DK, Sanseau P, Agarwal P. Computational drug repositioning: from data to therapeutics. Clin Pharmacol Ther. 2013;93(4):335–341. doi: 10.1038/clpt.2013.1. - DOI - PubMed
    1. Kanehisa M, Furumichi M, Tanabe M, Sato Y, Morishima K. KEGG: new perspectives on genomes, pathways, diseases and drugs. Nucleic Acids Res. 2017;45(Database issue):D353–D361. doi: 10.1093/nar/gkw1092. - DOI - PMC - PubMed
    1. Knox C, Law V, Jewison T, Liu P, Ly S, Frolkis A, Pon A, Banco K, Mak C, Neveu V. DrugBank 3.0: a comprehensive resource for ‘omics’ research on drugs. Nucleic Acids Res. 2011;39:D1035. doi: 10.1093/nar/gkq1126. - DOI - PMC - PubMed
    1. Kuhn M, Szklarczyk D, Pletscherfrankild S, Blicher TH, Mering CV, Jensen LJ, Bork P. STITCH 4: integration of protein–chemical interactions with user data. Nucleic Acids Res. 2014;42(Database issue):401–407. doi: 10.1093/nar/gkt1207. - DOI - PMC - PubMed