Integrating full spectrum of sequence features into predicting functional microRNA-mRNA interactions

MOTIVATION MicroRNAs (miRNAs) play important roles in general biological processes and diseases pathogenesis. Identifying miRNA target genes is an essential step to fully understand the regulatory effects of miRNAs. Many computational methods based on the sequence complementary rules and the miRNA and mRNA expression profiles have been developed for this purpose. It is noted that there have been many sequence features of miRNA targets available, including the context features of the target sites, the thermodynamic stability and the accessibility energy for miRNA-mRNA interaction. However, most of current computational methods that combine sequence and expression information do not effectively integrate full spectrum of these features; instead, they perceive putative miRNA-mRNA interactions from sequence-based prediction as equally meaningful. Therefore, these sequence features have not been fully utilized for improving miRNA target prediction. RESULTS We propose a novel regularized regression approach that is based on the adaptive Lasso procedure for detecting functional miRNA-mRNA interactions. Our method fully takes into account the gene sequence features and the miRNA and mRNA expression profiles. Given a set of sequence features for each putative miRNA-mRNA interaction and their expression values, our model quantifies the down-regulation effect of each miRNA on its targets while simultaneously estimating the contribution of each sequence feature to predicting functional miRNA-mRNA interactions. By applying our model to the expression datasets from two cancer studies, we have demonstrated our prediction results have achieved better sensitivity and specificity and are more biologically meaningful compared with those based on other methods. AVAILABILITY AND IMPLEMENTATION The source code is available at: http://nba.uth.tmc.edu/homepage/liu/miRNALasso. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online. CONTACT Yin.Liu@uth.tmc.edu.

[1]  C. Burge,et al.  Conserved Seed Pairing, Often Flanked by Adenosines, Indicates that Thousands of Human Genes are MicroRNA Targets , 2005, Cell.

[2]  R. Giegerich,et al.  Fast and effective prediction of microRNA/target duplexes. , 2004, RNA.

[3]  Zhaolei Zhang,et al.  A probabilistic approach to explore human miRNA targetome by integrating miRNA-overexpression data and sequence information , 2014, Bioinform..

[4]  Chi-Meng Tzeng,et al.  Integrated miRNA and mRNA expression profiling to identify mRNA targets of dysregulated miRNAs in non-obstructive azoospermia , 2015, Scientific Reports.

[5]  Tom Michoel,et al.  kruX: matrix-based non-parametric eQTL discovery , 2013, BMC Bioinformatics.

[6]  Thomas Lengauer,et al.  ROCR: visualizing classifier performance in R , 2005, Bioinform..

[7]  Minghua Deng,et al.  A Lasso regression model for the construction of microRNA-target regulatory networks , 2011, Bioinform..

[8]  Nectarios Koziris,et al.  Accurate microRNA target prediction correlates with protein repression levels , 2009, BMC Bioinformatics.

[9]  N. Rajewsky,et al.  Widespread changes in protein synthesis induced by microRNAs , 2008, Nature.

[10]  E. Izaurralde,et al.  Gene silencing by microRNAs: contributions of translational repression and mRNA decay , 2011, Nature Reviews Genetics.

[11]  Jan Krüger,et al.  RNAhybrid: microRNA target prediction easy, fast and flexible , 2006, Nucleic Acids Res..

[12]  A. Luttun,et al.  Quantification of miRNA-mRNA Interactions , 2012, PloS one.

[13]  Yin Liu,et al.  Identifying microRNA targets in different gene regions , 2014, BMC Bioinformatics.

[14]  Hsien-Da Huang,et al.  miRTarBase update 2014: an information resource for experimentally validated miRNA-target interactions , 2013, Nucleic Acids Res..

[15]  Yu-ping Wang,et al.  A Unified Sparse Representation for Sequence Variant Identification for Complex Traits , 2014, Genetic epidemiology.

[16]  Jae H. Park,et al.  Drosophila caspases involved in developmentally regulated programmed cell death of peptidergic neurons during early metamorphosis , 2011, The Journal of comparative neurology.

[17]  D. Bartel,et al.  Weak Seed-Pairing Stability and High Target-Site Abundance Decrease the Proficiency of lsy-6 and Other miRNAs , 2011, Nature Structural &Molecular Biology.

[18]  K. Gunsalus,et al.  Combinatorial microRNA target predictions , 2005, Nature Genetics.

[19]  H. Horvitz,et al.  MicroRNA expression profiles classify human cancers , 2005, Nature.

[20]  Seunghak Lee,et al.  Adaptive Multi-Task Lasso: with Application to eQTL Detection , 2010, NIPS.

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

[22]  Brendan J. Frey,et al.  Bayesian Inference of MicroRNA Targets from Sequence and Expression Data , 2007, J. Comput. Biol..

[23]  Zixing Wang,et al.  A Bayesian Framework to Improve MicroRNA Target Prediction by Incorporating External Information , 2014, Cancer informatics.

[24]  Wenlong Xu,et al.  The Characterization of microRNA-Mediated Gene Regulation as Impacted by Both Target Site Location and Seed Match Type , 2014, PloS one.

[25]  C. Croce,et al.  MicroRNA dysregulation in cancer: diagnostics, monitoring and therapeutics. A comprehensive review , 2012, EMBO molecular medicine.

[26]  T. Poggio,et al.  Multiclass cancer diagnosis using tumor gene expression signatures , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[27]  C. Bracken,et al.  IsomiRs--the overlooked repertoire in the dynamic microRNAome. , 2012, Trends in genetics : TIG.

[28]  C. Langford,et al.  5′ isomiR variation is of functional and evolutionary importance , 2014, Nucleic acids research.

[29]  C. Croce,et al.  Human microRNA genes are frequently located at fragile sites and genomic regions involved in cancers. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[30]  C. Burge,et al.  Most mammalian mRNAs are conserved targets of microRNAs. , 2008, Genome research.

[31]  D. Qian,et al.  A Review of Cancer Risk Prediction Models with Genetic Variants , 2014, Cancer informatics.

[32]  E. Lai,et al.  Vive la différence: biogenesis and evolution of microRNAs in plants and animals , 2011, Genome Biology.

[33]  Michael Kertesz,et al.  The role of site accessibility in microRNA target recognition , 2007, Nature Genetics.

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

[35]  Ana Kozomara,et al.  miRBase: integrating microRNA annotation and deep-sequencing data , 2010, Nucleic Acids Res..

[36]  W. Filipowicz,et al.  Regulation of mRNA translation and stability by microRNAs. , 2010, Annual review of biochemistry.

[37]  Doron Betel,et al.  The microRNA.org resource: targets and expression , 2007, Nucleic Acids Res..

[38]  Peijing Zhang,et al.  miR-100 Induces Epithelial-Mesenchymal Transition but Suppresses Tumorigenesis, Migration and Invasion , 2014, PLoS genetics.

[39]  Yin Liu,et al.  Incorporating prior knowledge into Gene Network Study , 2013, Bioinform..

[40]  L. Lim,et al.  MicroRNA targeting specificity in mammals: determinants beyond seed pairing. , 2007, Molecular cell.

[41]  Stephen P. Boyd,et al.  An Interior-Point Method for Large-Scale $\ell_1$-Regularized Least Squares , 2007, IEEE Journal of Selected Topics in Signal Processing.