DSCMF: prediction of LncRNA-disease associations based on dual sparse collaborative matrix factorization

Abstract

Background: In the development of science and technology, there are increasing evidences that there are some associations between lncRNAs and human diseases. Therefore, finding these associations between them will have a huge impact on our treatment and prevention of some diseases. However, the process of finding the associations between them is very difficult and requires a lot of time and effort. Therefore, it is particularly important to find some good methods for predicting lncRNA-disease associations (LDAs).

Results: In this paper, we propose a method based on dual sparse collaborative matrix factorization (DSCMF) to predict LDAs. The DSCMF method is improved on the traditional collaborative matrix factorization method. To increase the sparsity, the L_2,1-norm is added in our method. At the same time, Gaussian interaction profile kernel is added to our method, which increase the network similarity between lncRNA and disease. Finally, the AUC value obtained by the experiment is used to evaluate the quality of our method, and the AUC value is obtained by the ten-fold cross-validation method.

Conclusions: The AUC value obtained by the DSCMF method is 0.8523. At the end of the paper, simulation experiment is carried out, and the experimental results of prostate cancer, breast cancer, ovarian cancer and colorectal cancer are analyzed in detail. The DSCMF method is expected to bring some help to lncRNA-disease associations research. The code can access the https://github.com/Ming-0113/DSCMF website.

Keywords: Collaborative matrix factorization; Gaussian interaction profile kernel; LncRNA-disease associations.

Fig. 1

The LRLSLDA, ncPred, TPGLDA, NTSHMDA and DSCMF methods compare the performance of the AUC and ROC curves based on the ten-fold cross-validation method. It can be seen that the DSCMF method has the best performance

Fig. 2

The sensitivity analysis for $K$ under CV-p

Fig. 3

The sensitivity analysis for $P$ under CV-p

Fig. 4

The comparison of the robustness of the CMF and DSCMF methods when the noise point is 1

Fig. 5

The comparison of the robustness of the CMF and DSCMF methods when the noise point is 30

Fig. 6

The comparison of the robustness of the CMF and DSCMF methods when the noise point is 60

Fig. 7

The comparison of the robustness of the CMF and DSCMF methods when the noise point is 90

Fig. 8

Method flow chart. The DSCMF method consists of two parts. First, the matrix $\mathbf{Y}$ is decomposed into $\mathbf{A}$ and $\mathbf{B}$, and L_2,1-norm is added to $\mathbf{A}$ and $\mathbf{B}$, respectively. Second is to join the GIP kernel in the CMF method

Fig. 9

Convergence curve of the DSCMF method. When the number of iterations is about ten, our method tends to converge