PMAMCA: Prediction of microRNA-disease association utilizing a matrix completion approach

Background: Numerous experimental results have indicated that microRNAs (miRNAs) play a vital role in biological processes, as well as outbreaks of diseases at the molecular level. Despite their important role in biological processes, knowledge regarding specific functions of miRNAs in the development of human diseases is very limited. While attempting to solve this problem, many computational approaches have been proposed and attracted significant attention. However, most previous approaches suffer from the common problem of being inapplicable to new diseases without any known miRNA-disease associations. Results: This paper proposes a novel method for inferring disease-miRNA associations utilizing a machine learning technique called matrix factorization, which is widely used in recommendation systems. In recommendation systems, the goal is to predict rating scores that a user might assign to specific items. By replacing users with miRNAs and items with diseases, we can efficiently predict miRNA-disease associations without seed miRNAs. As a result, our proposed model, called prediction of microRNA-disease association utilizing a matrix completion approach, achieves excellent performance compared to previous approaches with a reliable AUC value of 0.882 by implementing five-fold cross validation. Conclusions: To the best of our knowledge, the proposed method applies the matrix completion technique to infer miRNA-disease associations and overcome the seed-miRNA problem negatively affects existing computational models.