Identifying drug-pathway association pairs based on L2,1-integrative penalized matrix decomposition
Jin‐Xing Liu, Dongqin Wang, Chun-Hou Zheng, Ying-Lian Gao, Shasha Wu, Junliang Shang · BMC Systems Biology · 2017
Traditional drug identification methods follow the “one drug-one target” thought. But those methods ignore the natural characters of human diseases. To overcome this limitation, many identification methods of drug-pathway association pairs have been developed, such as the integrative penalized matrix decomposition (iPaD) method. The iPaD method imposes the L 1 -norm penalty on the regularization term. However, lasso-type penalties have an obvious disadvantage, that is, the sparsity produced by them is too dispersive. Therefore, to improve the performance of the iPaD method, we propose a novel method named L 2,1 -iPaD to identify paired drug-pathway associations. In the L 2,1 -iPaD model, we use the L 2,1 -norm penalty to replace the L 1 -norm penalty since the L 2,1 -norm penalty can produce row sparsity. By applying the L 2,1 -iPaD method to the CCLE and NCI-60 datasets, we demonstrate that the performance of L 2,1 -iPaD method is superior to existing methods. And the proposed method can achieve better enrichment in terms of discovering validated drug-pathway association pairs than the iPaD method by performing permutation test. The results on the two real datasets prove that our method is effective.