A Research On Prediction Method Of Disease Related-lncRNA Based On Probability Model

The discovery of human disease-related lncRNAs has certain research value in recent years and an increasing number of studies have indicated that long-non-coding RNAs(lncRNAs)play crucial roles in biological processes,complex disease diagnoses,prognoses,and treatments.Considering the lncRNA-disease associations verified by biology experiments are still limited,therefore,in order to solve the problem of scarce known lncRNA-disease associations,it is important to develop efficient computational models to discover potential lncRNA-disease associations.Using bioinformatics methods to predict disease-associated lncRNA has become a hot topic in recent years,which attracts researchers’ attention.In this paper,we first introduces the background knowledge of disease-related lncRNA,and then focuses on two methods of predicting the potential association between lncRNA and disease.The detailed methods are as follows:(1)Recently,computational models have been developed to discover potential associations between lncRNAs and diseases by integrating multiple heterogeneous biological data;this has become a hot topic in biological research.In the section three,we constructed a global tripartite network by integrating a variety of biological information including miRNA–disease,miRNA–lncRNA,and lncRNA–disease associations and interactions.Then,we constructed a global quadruple network by appending gene–lncRNA interaction,gene–disease association,and gene–miRNA interaction networks to the global tripartite network.Subsequently,based on these two global networks,a novel approach was proposed based on the na?ve Bayesian classifier to predict potential lncRNA–disease associations.our new method does not entirely rely on known lncRNA–disease associations,and can achieve a reliable performance.(2)A novel collaborative filtering algorithm for lncRNA-disease associations prediction is proposed on the basis of Na?ve Bayesian Classifier(CFNBC),in which,an original lncRNA-miRNA-disease tripartite network will be constructed first through integrating miRNA-lncRNA,miRNA-disease,and lncRNA-disease associations and interactions,and then,an updated lncRNA-miRNA-disease tripartite network can be obtained by applying the item-based collaborative filtering algorithm to original tripartite network.Next,based on the updated tripartite network,a novel approach called CFNBC for abbreviation will be proposed based on the Na?ve Bayesian Classifier to predict potential associations between lncRNAs and diseases.The method can achieve excellent performance with sparse known associations between lncRNA and disease.In the last chapter of this paper,we summarizes the two prediction models and discusses the next research plan.