GKLOMLI: a link prediction model for inferring miRNA–lncRNA interactions by using Gaussian kernel-based method on network profile and linear optimization algorithm

Abstract

Background The limited knowledge of miRNA–lncRNA interactions is considered as an obstruction of revealing the regulatory mechanism. Accumulating evidence on Human diseases indicates that the modulation of gene expression has a great relationship with the interactions between miRNAs and lncRNAs. However, such interaction validation via crosslinking-immunoprecipitation and high-throughput sequencing (CLIP-seq) experiments that inevitably costs too much money and time but with unsatisfactory results. Therefore, more and more computational prediction tools have been developed to offer many reliable candidates for a better design of further bio-experiments. Methods In this work, we proposed a novel link prediction model based on Gaussian kernel-based method and linear optimization algorithm for inferring miRNA–lncRNA interactions (GKLOMLI). Given an observed miRNA–lncRNA interaction network, the Gaussian kernel-based method was employed to output two similarity matrixes of miRNAs and lncRNAs. Based on the integrated matrix combined with similarity matrixes and the observed interaction network, a linear optimization-based link prediction model was trained for inferring miRNA–lncRNA interactions. Results To evaluate the performance of our proposed method, k-fold cross-validation (CV) and leave-one-out CV were implemented, in which each CV experiment was carried out 100 times on a training set generated randomly. The high area under the curves (AUCs) at 0.8623 ± 0.0027 (2-fold CV), 0.9053 ± 0.0017 (5-fold CV), 0.9151 ± 0.0013 (10-fold CV), and 0.9236 (LOO-CV), illustrated the precision and reliability of our proposed method. Conclusion GKLOMLI with high performance is anticipated to be used to reveal underlying interactions between miRNA and their target lncRNAs, and deciphers the potential mechanisms of the complex diseases.

Investigation on the antipyretic mechanism of Chaiqin Qingning capsule for the treatment of fever based on network pharmacology, molecular docking, and in vitro experimental validation

“…With the development of high‐throughput technology and the advent of the big data era, network prediction algorithms or procedures, visualization, and analysis software or tools have been widely used in bioinformatics research (Su et al., 2022; Wong et al., 2023; Zheng et al., 2023) including Cytoscape software (Shannon et al., 2003), which helps to present the results of the analysis directly in a variety of forms such as pictures. To reveal complex relationships between CQQNC and the fever intersection genes, the visualization and analysis of drug–ingredients–targets–disease networks were performed by Cytoscape software.…”

BCMCMI: A Fusion Model for Predicting circRNA-miRNA Interactions Combining Semantic and Meta-path

“…In heterogeneous graphs, the feature representation of nodes is based on functional similarity. Then, using the known interaction relationship between circRNAs and miRNAs, the two homogeneous graphs are connected into a heterogeneous graph . In heterogeneous graphs, the associated attribute representation of nodes is based on the adjacency matrix.…”

“…Then, using the known interaction relationship between circRNAs and miRNAs, the two homogeneous graphs are connected into a heterogeneous graph. 24 In heterogeneous graphs, the associated attribute representation of nodes is based on the adjacency matrix. This heterogeneous network is considered G = (V, E), where V represents the set of entity nodes and E represents the set of associated edges.…”

GCN-Based Heterogeneous Complex Feature Learning to Enhance Predictability for LncRNA–Disease Associations

“…According to the literature, ,− LDAs, disease-miRNA associations (DMAs), and lncRNA-miRNA interactions (LMIs) were acquired to create the corresponding networks represented as matrices, , , and , respectively. Each matrix element A ld ( l i , d j ) = 1 when lncRNA l i has a known association with disease d j , otherwise A ld ( l i , d j ) = 0.…”