Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Wang Z

PROVIDER: S-EPMC4804770 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundPost-translational modification (PTM) is a biological process that alters proteins and is therefore involved in the regulation of various cellular activities and pathogenesis. Protein phosphorylation is an essential process and one of the most-studied PTMs: it occurs when a phosphate group is added to serine (Ser, S), threonine (Thr, T), or tyrosine (Tyr, Y) residue. Dysregulation of protein phosphorylation can lead to various diseases-most commonly neurological disorders, Alzheimer's disease, and Parkinson's disease-thus necessitating the prediction of S/T/Y residues that can be phosphorylated in an uncharacterized amino acid sequence. Despite a surplus of sequencing data, current experimental methods of PTM prediction are time-consuming, costly, and error-prone, so a number of computational methods have been proposed to replace them. However, phosphorylation prediction remains limited, owing to substrate specificity, performance, and the diversity of its features.MethodsIn the present study we propose machine-learning-based predictors that use the physicochemical, sequence, structural, and functional information of proteins to classify S/T/Y phosphorylation sites. Rigorous feature selection, the minimum redundancy/maximum relevance approach, and the symmetrical uncertainty method were employed to extract the most informative features to train the models.ResultsThe RF and SVM models generated using diverse feature types in the present study were highly accurate as is evident from good values for different statistical measures. Moreover, independent test sets and benchmark validations indicated that the proposed method clearly outperformed the existing methods, demonstrating its ability to accurately predict protein phosphorylation.ConclusionsThe results obtained in the present work indicate that the proposed computational methodology can be effectively used for predicting putative phosphorylation sites further facilitating discovery of various biological processes mechanisms.

Project description:BackgroundCellular senescence can be induced by a variety of extrinsic stimuli, and sustained exposure to sunlight is a key factor in photoaging of the skin. Accordingly, irradiation of skin fibroblasts by UVB light triggers cellular senescence, which is thought to contribute to extrinsic skin aging, although molecular mechanisms are incompletely understood. Here, we addressed molecular mechanisms underlying UVB induced senescence of human diploid fibroblasts.ResultsWe observed a parallel activation of the p53/p21(WAF1) and p16(INK4a)/pRb pathways. Using genome-wide transcriptome analysis, we identified a transcriptional signature of UVB-induced senescence that was conserved in three independent strains of human diploid fibroblasts (HDF) from skin. In parallel, a comprehensive screen for microRNAs regulated during UVB-induced senescence was performed which identified five microRNAs that are significantly regulated during the process. Bioinformatic analysis of miRNA-mRNA networks was performed to identify new functional mRNA targets with high confidence for miR-15a, miR-20a, miR-20b, miR-93, and miR-101. Already known targets of these miRNAs were identified in each case, validating the approach. Several new targets were identified for all of these miRNAs, with the potential to provide new insight in the process of UVB-induced senescence at a genome-wide level. Subsequent analysis was focused on miR-101 and its putative target gene Ezh2. We confirmed that Ezh2 is regulated by miR-101 in human fibroblasts, and found that both overexpression of miR-101 and downregulation of Ezh2 independently induce senescence in the absence of UVB irradiation. However, the downregulation of miR-101 was not sufficient to block the phenotype of UVB-induced senescence, suggesting that other UVB-induced processes induce the senescence response in a pathway redundant with upregulation of miR-101.ConclusionWe performed a comprehensive screen for UVB-regulated microRNAs in human diploid fibroblasts, and identified a network of miRNA-mRNA interactions mediating UVB-induced senescence. In addition, miR-101 and Ezh2 were identified as key players in UVB-induced senescence of HDF.