Identifying drug-pathway association pairs based on L1L2,1-integrative penalized matrix decomposition
Dongqin Wang, Ying-Lian Gao, Jin‐Xing Liu, Chun-Hou Zheng, Xiang-Zhen Kong · Oncotarget · 2017
// Dong-Qin Wang 1 , Ying-Lian Gao 2 , Jin-Xing Liu 1 , Chun-Hou Zheng 1 and Xiang-Zhen Kong 1 1 School of Information Science and Engineering, Qufu Normal University, Rizhao, China 2 Library of Qufu Normal University, Qufu Normal University, Rizhao, China Correspondence to: Jin-Xing Liu, email: [email protected] Chun-Hou Zheng, email: [email protected] Keywords: L 2,1 -norm, L 1 -norm, integrative penalized matrix decomposition, paired drug-pathway associations, drug discovery Received: January 23, 2017 Accepted: May 01, 2017 Published: May 29, 2017 ABSTRACT The traditional methods of drug discovery follow the “one drug-one target” approach, which ignores the cellular and physiological environment of the action mechanism of drugs. However, pathway-based drug discovery methods can overcome this limitation. This kind of method, such as the Integrative Penalized Matrix Decomposition (iPaD) method, identifies the drug-pathway associations by taking the lasso-type penalty on the regularization term. Moreover, instead of imposing the L 1 -norm regularization, the L 2,1 -Integrative Penalized Matrix Decomposition (L 2,1 -iPaD) method imposes the L 2,1 -norm penalty on the regularization term. In this paper, based on the iPaD and L 2,1 -iPaD methods, we propose a novel method named L 1 L 2,1 -iPaD (L 1 L 2,1 -Integrative Penalized Matrix Decomposition), which takes the sum of the L 1 -norm and L 2,1 -norm penalties on the regularization term. Besides, we perform permutation test to assess the significance of the identified drug-pathway association pairs and compute the P-values. Compared with the existing methods, our method can identify more drug-pathway association pairs which have been validated in the CancerResource database. In order to identify drug-pathway associations which are not validated in the CancerResource database, we retrieve published papers to prove these associations. The results on two real datasets prove that our method can achieve better enrichment for identified association pairs than the iPaD and L 2,1 -iPaD methods.