Predicting microRNA-disease associations from knowledge graph using tensor decomposition with relational constraints

MicroRNAs (miRNAs) play crucial roles in multifarious biological processes associated with human diseases. Identifying potential miRNA-disease associations contributes to understanding the molecular mechanisms of miRNA-related diseases. Most of the existing computational methods mainly focus on predicting whether a miRNA-disease association exists or not. However, the roles of miRNAs in diseases are prominently diverged, for instance, Genetic variants of miRNA (mir-15) may affect the expression level of miRNAs leading to B cell chronic lymphocytic leukemia, while circulating miRNAs (including mir-1246, mir-1307-3p, etc.) have potentials to detecting breast cancer in the early stage. In this paper, we aim to predict multi-type miRNA-disease associations instead of taking them as binary. To this end, we innovatively represent miRNA-disease-type triples as a tensor and introduce tensor decomposition methods to solve the prediction task. Experimental results on two widely-adopted miRNA-disease datasets: HMDD v2.0 and HMDD v3.2 show that tensor decomposition methods improve a recent baseline in a large scale (up to $38\%$ in Top-1F1). We then propose a novel method, Tensor Decomposition with Relational Constraints (TDRC), which incorporates biological features as relational constraints to further the existing tensor decomposition methods. Compared with two existing tensor decomposition methods, TDRC can produce better performance while being more efficient.

[1]  E. Miska,et al.  How microRNAs control cell division, differentiation and death. , 2005, Current opinion in genetics & development.

[2]  Xing Chen,et al.  Ensemble of decision tree reveals potential miRNA-disease associations , 2019, PLoS Comput. Biol..

[3]  É. Várallyay,et al.  MicroRNA detection by northern blotting using locked nucleic acid probes , 2008, Nature Protocols.

[4]  Srinivasan Parthasarathy,et al.  Graph embedding on biomedical networks: methods, applications and evaluations , 2019, Bioinform..

[5]  Xia Li,et al.  Prediction of potential disease-associated microRNAs based on random walk , 2015, Bioinform..

[6]  Hisashi Kashima,et al.  Tensor factorization using auxiliary information , 2011, Data Mining and Knowledge Discovery.

[7]  Yadong Wang,et al.  miR2Disease: a manually curated database for microRNA deregulation in human disease , 2008, Nucleic Acids Res..

[8]  Xing Chen,et al.  MicroRNAs and complex diseases: from experimental results to computational models , 2019, Briefings Bioinform..

[9]  Miao Zheng,et al.  MiR-199a-3p enhances breast cancer cell sensitivity to cisplatin by downregulating TFAM (TFAM). , 2017, Biomedicine & pharmacotherapy = Biomedecine & pharmacotherapie.

[10]  Jianye Hao,et al.  A learning-based framework for miRNA-disease association identification using neural networks , 2018, bioRxiv.

[11]  Yang Li,et al.  HMDD v2.0: a database for experimentally supported human microRNA and disease associations , 2013, Nucleic Acids Res..

[12]  Bo Yu,et al.  miR-1-3p suppresses proliferation of hepatocellular carcinoma through targeting SOX9 , 2019, OncoTargets and therapy.

[13]  Feng Liu,et al.  Predicting drug-disease associations by using similarity constrained matrix factorization , 2018, BMC Bioinformatics.

[14]  Hans-Peter Kriegel,et al.  A Three-Way Model for Collective Learning on Multi-Relational Data , 2011, ICML.

[15]  Zhigang Zhong,et al.  MiR-16 attenuates &bgr;-amyloid-induced neurotoxicity through targeting &bgr;-site amyloid precursor protein-cleaving enzyme 1 in an Alzheimer’s disease cell model , 2018, Neuroreport.

[16]  Jia Wu,et al.  Link Prediction with Signed Latent Factors in Signed Social Networks , 2019, KDD.

[17]  Cheng Liang,et al.  A graph regularized non-negative matrix factorization method for identifying microRNA-disease associations , 2018, Bioinform..

[18]  Lei Wang,et al.  BNPMDA: Bipartite Network Projection for MiRNA–Disease Association prediction , 2018, Bioinform..

[19]  Lars Schmidt-Thieme,et al.  Learning optimal ranking with tensor factorization for tag recommendation , 2009, KDD.

[20]  Inderjit S. Dhillon,et al.  Large-scale Multi-label Learning with Missing Labels , 2013, ICML.

[21]  T. Ochiya,et al.  Novel combination of serum microRNA for detecting breast cancer in the early stage , 2016, Cancer science.

[22]  Xu Zhang,et al.  A Semi-Supervised Learning Algorithm for Predicting Four Types MiRNA-Disease Associations by Mutual Information in a Heterogeneous Network , 2018, Genes.

[23]  Xantha Karp,et al.  Encountering MicroRNAs in Cell Fate Signaling , 2005, Science.

[24]  Atul Bhatnagar,et al.  Plasma MicroRNA Are Disease Response Biomarkers in Classical Hodgkin Lymphoma , 2013, Clinical Cancer Research.

[25]  Peizhang Xu,et al.  MicroRNAs and the regulation of cell death. , 2004, Trends in genetics : TIG.

[26]  C. Croce,et al.  Frequent deletions and down-regulation of micro- RNA genes miR15 and miR16 at 13q14 in chronic lymphocytic leukemia , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[27]  Xing Chen,et al.  Adaptive boosting-based computational model for predicting potential miRNA-disease associations , 2019, Bioinform..

[28]  Feng Liu,et al.  Prediction of Drug-Disease Associations and Their Effects by Signed Network-Based Nonnegative Matrix Factorization , 2018, 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

[29]  Tamara G. Kolda,et al.  Tensor Decompositions and Applications , 2009, SIAM Rev..

[30]  Guillaume Bouchard,et al.  Knowledge Graph Completion via Complex Tensor Factorization , 2017, J. Mach. Learn. Res..

[31]  M. Hestenes,et al.  Methods of conjugate gradients for solving linear systems , 1952 .

[32]  Xiangxiang Zeng,et al.  Inferring MicroRNA-Disease Associations by Random Walk on a Heterogeneous Network with Multiple Data Sources , 2017, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[33]  Q. Cui,et al.  An Analysis of Human MicroRNA and Disease Associations , 2008, PloS one.

[34]  Xing Chen,et al.  MDHGI: Matrix Decomposition and Heterogeneous Graph Inference for miRNA-disease association prediction , 2018, PLoS Comput. Biol..

[35]  D. Bartel.  MicroRNAs Genomics, Biogenesis, Mechanism, and Function , 2004, Cell.

[36]  Jing Li,et al.  Modeling Relational Drug-Target-Disease Interactions via Tensor Factorization with Multiple Web Sources , 2019, WWW.

[37]  Zenglin Xu,et al.  Similarity Learning via Kernel Preserving Embedding , 2019, AAAI.

[38]  Changning Liu,et al.  dbDEMC: a database of differentially expressed miRNAs in human cancers , 2010, BMC Genomics.

[39]  Dong Wang,et al.  Inferring the human microRNA functional similarity and functional network based on microRNA-associated diseases , 2010, Bioinform..

[40]  P. Manzine,et al.  microRNA 221 Targets ADAM10 mRNA and is Downregulated in Alzheimer's Disease. , 2017, Journal of Alzheimer's disease : JAD.

[41]  Q. Cui,et al.  Benchmark of computational methods for predicting microRNA-disease associations , 2019, Genome Biology.

[42]  Yan Zhao,et al.  NCMCMDA: miRNA-disease association prediction through neighborhood constraint matrix completion , 2020, Briefings Bioinform..

[43]  George Coukos,et al.  Therapeutic MicroRNA Strategies in Human Cancer , 2009, The AAPS Journal.

[44]  L. Tucker,et al.  Some mathematical notes on three-mode factor analysis , 1966, Psychometrika.

[45]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..

[46]  Feng Huang,et al.  A Fast Linear Neighborhood Similarity-Based Network Link Inference Method to Predict MicroRNA-Disease Associations , 2019, IEEE/ACM Transactions on Computational Biology and Bioinformatics.

[47]  Xing Chen,et al.  LRSSLMDA: Laplacian Regularized Sparse Subspace Learning for MiRNA-Disease Association prediction , 2017, PLoS Comput. Biol..

[48]  M. Byrom,et al.  Antisense inhibition of human miRNAs and indications for an involvement of miRNA in cell growth and apoptosis , 2005, Nucleic acids research.

[49]  Qinghua Cui,et al.  MISIM v2.0: a web server for inferring microRNA functional similarity based on microRNA-disease associations , 2019, Nucleic Acids Res..

[50]  Juan Fortea,et al.  Plasma miR-34a-5p and miR-545-3p as Early Biomarkers of Alzheimer’s Disease: Potential and Limitations , 2017, Molecular Neurobiology.

[51]  Qionghai Dai,et al.  RBMMMDA: predicting multiple types of disease-microRNA associations , 2015, Scientific Reports.

[52]  M. Swellam,et al.  Serum MiRNA-27a as potential diagnostic nucleic marker for breast cancer , 2019, Archives of physiology and biochemistry.

[53]  Qinghua Cui,et al.  The relationship of human tissue microRNAs with those from body fluids , 2020, Scientific Reports.

[54]  H. Qian,et al.  Role of microRNA-150-5p/SRCIN1 axis in the progression of breast cancer , 2019, Experimental and therapeutic medicine.

[55]  Ping Zhang,et al.  Multitask Dyadic Prediction and Its Application in Prediction of Adverse Drug-Drug Interaction , 2017, AAAI.

[56]  Chiang-Ching Huang,et al.  MicroRNA expression profiling for Molecular Classification of pediatric brain tumors , 2011, Pediatric blood & cancer.

[57]  Na-Na Guan,et al.  Predicting miRNA‐disease association based on inductive matrix completion , 2018, Bioinform..

[58]  Xiangxiang Zeng,et al.  Prediction of potential disease-associated microRNAs using structural perturbation method , 2017, bioRxiv.