Identifying drug-pathway association pairs based on L1L2,1-integrative penalized matrix decomposition

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 L1-norm regularization, the L2,1-Integrative Penalized Matrix Decomposition (L2,1-iPaD) method imposes the L2,1-norm penalty on the regularization term. In this paper, based on the iPaD and L2,1-iPaD methods, we propose a novel method named L1L2,1-iPaD (L1L2,1-Integrative Penalized Matrix Decomposition), which takes the sum of the L1-norm and L2,1-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 L2,1-iPaD methods.

[1]  Faten Merhi,et al.  Allium compounds, dipropyl and dimethyl thiosulfinates as antiproliferative and differentiating agents of human acute myeloid leukemia cell lines , 2008, Biologics : targets & therapy.

[2]  P. Secchiero,et al.  Nutlin-3 up-regulates the expression of Notch1 in both myeloid and lymphoid leukemic cells, as part of a negative feedback antiapoptotic mechanism. , 2009, Blood.

[3]  Chris H. Q. Ding,et al.  R1-PCA: rotational invariant L1-norm principal component analysis for robust subspace factorization , 2006, ICML.

[4]  Yongdong Zhang,et al.  Drug-target interaction prediction: databases, web servers and computational models , 2016, Briefings Bioinform..

[5]  A. Griesmacher,et al.  In vitro effects of mycophenolic acid on cell cycle and activation of human lymphocytes. , 2000, Clinica chimica acta; international journal of clinical chemistry.

[6]  Nabil El Brahmi,et al.  A novel class of ethacrynic acid derivatives as promising drug-like potent generation of anticancer agents with established mechanism of action. , 2016, European journal of medicinal chemistry.

[7]  Hongyu Zhao,et al.  Drug target inference through pathway analysis of genomics data. , 2013, Advanced drug delivery reviews.

[8]  Y. Nesterov.  A method for solving the convex programming problem with convergence rate O(1/k^2) , 1983 .

[9]  David Sidransky,et al.  Selective growth inhibition in BRAF mutant thyroid cancer by the mitogen-activated protein kinase kinase 1/2 inhibitor AZD6244. , 2007, The Journal of clinical endocrinology and metabolism.

[10]  A. Odén,et al.  Arguments for Fisher's Permutation Test , 1975 .

[11]  B. Aggarwal.  Signalling pathways of the TNF superfamily: a double-edged sword , 2003, Nature Reviews Immunology.

[12]  Xingming Sun,et al.  Effective and Efficient Global Context Verification for Image Copy Detection , 2017, IEEE Transactions on Information Forensics and Security.

[13]  Hongyu Zhao,et al.  iFad: an integrative factor analysis model for drug-pathway association inference , 2012, Bioinform..

[14]  Hongyu Zhao,et al.  Efficient Drug-Pathway Association Analysis via Integrative Penalized Matrix Decomposition , 2016, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[15]  Zhipeng Cai,et al.  The Pathway Analysis of Micrornas Regulated Drug-Resistant Responses in HeLa Cells , 2016, IEEE Transactions on NanoBioscience.

[16]  Pablo Tamayo,et al.  Gene set enrichment analysis: A knowledge-based approach for interpreting genome-wide expression profiles , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[17]  Feng Liu,et al.  A joint-L2, 1-norm-constraint-based semi-supervised feature extraction for RNA-Seq data analysis , 2017, Neurocomputing.

[18]  Paul Greengard,et al.  Gleevec inhibits β-amyloid production but not Notch cleavage , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[19]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[20]  David Garcia-Dorado,et al.  Loss of ischemic preconditioning's cardioprotection in aged mouse hearts is associated with reduced gap junctional and mitochondrial levels of connexin 43. , 2007, American journal of physiology. Heart and circulatory physiology.

[21]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[22]  Feiping Nie,et al.  Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization , 2010, NIPS.

[23]  Feiping Nie,et al.  Robust Manifold Nonnegative Matrix Factorization , 2014, ACM Trans. Knowl. Discov. Data.

[24]  Chun-Hou Zheng,et al.  L21-iPaD: An efficient method for drug-pathway association pairs inference , 2016, 2016 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[25]  Susumu Goto,et al.  KEGG for integration and interpretation of large-scale molecular data sets , 2011, Nucleic Acids Res..

[26]  Zhizhuang Joe Zhao,et al.  Erlotinib Effectively Inhibits JAK2V617F Activity and Polycythemia Vera Cell Growth* , 2006, Journal of Biological Chemistry.

[27]  Arghya Ray,et al.  Potentiation of antileukemic therapies by Smac mimetic, LBW242: effects on mutant FLT3-expressing cells , 2007, Molecular Cancer Therapeutics.

[28]  Daniela Renga,et al.  Congenital and acquired neutropenia consensus guidelines on diagnosis from the Neutropenia Committee of the Marrow Failure Syndrome Group of the AIEOP (Associazione Italiana Emato‐Oncologia Pediatrica) , 2011, Pediatric blood & cancer.

[29]  Feiping Nie,et al.  Multi-View Clustering and Feature Learning via Structured Sparsity , 2013, ICML.

[30]  Jun Kishi,et al.  Antifibrotic effects of focal adhesion kinase inhibitor in bleomycin-induced pulmonary fibrosis in mice. , 2013, American journal of respiratory cell and molecular biology.

[31]  Gayatry Mohapatra,et al.  Amplification of MET may identify a subset of cancers with extreme sensitivity to the selective tyrosine kinase inhibitor PHA-665752 , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[32]  Feng Xu,et al.  Therapeutic target database update 2016: enriched resource for bench to clinical drug target and targeted pathway information , 2015, Nucleic Acids Res..

[33]  Hongyu Zhao,et al.  FacPad: Bayesian sparse factor modeling for the inference of pathways responsive to drug treatment , 2012, Bioinform..

[34]  Somenath Roy,et al.  Redox sensing and signaling by malaria parasite in vertebrate host , 2015, Journal of basic microbiology.

[35]  F Peter Guengerich,et al.  Cytochrome P450-dependent catabolism of vitamin K: ω-hydroxylation catalyzed by human CYP4F2 and CYP4F11. , 2013, Biochemistry.

[36]  C. Kang,et al.  The inhibition of ERK/MAPK not the activation of JNK/SAPK is primarily required to induce apoptosis in chronic myelogenous leukemic K562 cells. , 2000, Leukemia research.

[37]  Srinivas Annavarapu,et al.  Combination of the histone deacetylase inhibitor LBH589 and the hsp90 inhibitor 17-AAG is highly active against human CML-BC cells and AML cells with activating mutation of FLT-3. , 2005, Blood.

[38]  Emilie Flaberg,et al.  Effect of frequently used chemotherapeutic drugs on the cytotoxic activity of human natural killer cells , 2007, Molecular Cancer Therapeutics.

[39]  B. Turcq,et al.  ABT-737 increases tyrosine kinase inhibitor-induced apoptosis in chronic myeloid leukemia cells through XIAP downregulation and sensitizes CD34(+) CD38(-) population to imatinib. , 2012, Experimental hematology.