Prediction of miRNA-disease associations with a vector space model

Abstract

MicroRNAs play critical roles in many physiological processes. Their dysregulations are also closely related to the development and progression of various human diseases, including cancer. Therefore, identifying new microRNAs that are associated with diseases contributes to a better understanding of pathogenicity mechanisms. MicroRNAs also represent a tremendous opportunity in biotechnology for early diagnosis. To date, several in silico methods have been developed to address the issue of microRNA-disease association prediction. However, these methods have various limitations. In this study, we investigate the hypothesis that information attached to miRNAs and diseases can be revealed by distributional semantics. Our basic approach is to represent distributional information on miRNAs and diseases in a high-dimensional vector space and to define associations between miRNAs and diseases in terms of their vector similarity. Cross validations performed on a dataset of known miRNA-disease associations demonstrate the excellent performance of our method. Moreover, the case study focused on breast cancer confirms the ability of our method to discover new disease-miRNA associations and to identify putative false associations reported in databases.

In silico prediction of potential miRNA‐disease association using an integrative bioinformatics approach based on kernel fusion

“…Predictions for different diseases were not globally comparable, as the association scores given by this method had a highly positive correlation with the number of known associated miRNAs for a dis- Figure 1). Moreover, it is worth noting that MiRAI's AUC of mere 0.6299 was much lower than 0.867 indicated by Pasquier et al, 26 because in their literature the model was evaluated on 83 diseases with at least 20 associated miRNAs, whereas in our study it was tested on 383 diseases with only 14.18 associated miRNAs per disease on average. MiRAI was based on collaborative filtering, and its performance would expectedly become worse with our sparse association data set.…”

NDAMDA: Network distance analysis for MiRNA‐disease association prediction

“…We implemented local and global LOOCV to evaluate the prediction accuracy of NDAMDA and 6 previous computational models: WBSMDA,20 RLSMDA,24 MCMDA,28 HDMP,21 RWRMDA 19 and MiRAI 22. In LOOCV, each known association was used as the validation sample and the remaining known associations were regarded as the training samples.…”

DRMDA: deep representations‐based miRNA–disease association prediction

“…Inspired by computational methods associating biomolecules with diseases , lots of computational models were established to predict miRNA–disease association, based on the assumption that miRNAs with similar functions are more likely to be associated with diseases with similar phonotypes . Jiang et al .…”

“…Inspired by computational methods associating biomolecules with diseases [13][14][15], lots of computational models were established to predict miRNA-disease association, based on the assumption that miRNAs with similar functions are more likely to be associated with diseases with similar phonotypes [16,17]. Jiang et al [18] built a hypergeometric distribution-based model on the basis of disease phenotype similarity network, miRNA functional similarity network and known human disease-miRNA association network to identify unknown miRNA-disease associations.…”