IRWRLDA: improved random walk with restart for lncRNA-disease association prediction

Abstract

In recent years, accumulating evidences have shown that the dysregulations of lncRNAs are associated with a wide range of human diseases. It is necessary and feasible to analyze known lncRNA-disease associations, predict potential lncRNA-disease associations, and provide the most possible lncRNA-disease pairs for experimental validation. Considering the limitations of traditional Random Walk with Restart (RWR), the model of Improved Random Walk with Restart for LncRNA-Disease Association prediction (IRWRLDA) was developed to predict novel lncRNA-disease associations by integrating known lncRNA-disease associations, disease semantic similarity, and various lncRNA similarity measures. The novelty of IRWRLDA lies in the incorporation of lncRNA expression similarity and disease semantic similarity to set the initial probability vector of the RWR. Therefore, IRWRLDA could be applied to diseases without any known related lncRNAs. IRWRLDA significantly improved previous classical models with reliable AUCs of 0.7242 and 0.7872 in two known lncRNA-disease association datasets downloaded from the lncRNADisease database, respectively. Further case studies of colon cancer and leukemia were implemented for IRWRLDA and 60% of lncRNAs in the top 10 prediction lists have been confirmed by recent experimental reports.

Long Noncoding RNA Identification: Comparing Machine Learning Based Tools for Long Noncoding Transcripts Discrimination

“…RWRlncD can only be applied to the case that lncRNAs have known related diseases and RWRHLD cannot deal with the circumstance that lncRNAs have unknown lncRNA-miRNA interactions. Another method, Improved Random Walk with Restart for LncRNA-Disease Association (IRWRLDA) [19], is also based on RWR, but IRWRLDA can predict the associations even when diseases show no known related lncRNAs.…”

ProphTools: general prioritization tools for heterogeneous biological networks

“…These results show that predictions made by ProphTools with the proposed heterogeneous network configuration are consistent with current knowledge about lncRNAs and diseases and therefore likely to provide new predictions of interest. These AUC values are competitive with state-of-the art ad hoc approaches, such as IRWRLDA (0.7242 and 0.7872 AUC values) [29], LRLSLDA (0.7760 AUC value) [37] , and RWRlncD (0.822 AUC value) [30], and the recent LncPriCNet (0.93 AUC value) [31]. Furthermore, single prioritization queries on the dataset ran on average between 8.14 (±0.04) seconds for lncRNA-disease prioritization and 11.86 (±0.52) seconds for disease-lncRNA on our server (Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz (×48), 256GiB RAM).…”

“…LRLSLDA [28] defines a classification function based on the assumption that similarity between diseases can be an indicator of the similarity between the lncRNAs they are associated to. Later, their authors released IRWRLDA [29], a network-based lncRNA-disease prioritization algorithm that uses disease semantic similarity and lncRNA expression data to relate lncRNAs, and a modification of a Random Walk with Restarts (RWR) algorithm to perform prioritization. RWRlncD [30] also implements RWR on an lncRNA similarity network.…”

DisSetSim: An online system for calculating similarity between disease sets

“…The similarity of pair-wise disease sets (SDS) has drawn more and more attention in identifying functional similarity of the disease-caused molecules [1], predicting potential relationships between diseases and molecules [2][3][4][5][6][7][8], and so on. In previous studies, Wang et al utilized the SDS to construct a human miRNA functional similarity network (MFSN) [1].…”