MicroRNAs, small non-coding elements implied in gene regulation, are very interesting biomarkers for various diseases such as cancers.
They represent potential prodigious biotechnologies for early diagnosis and gene therapies. However, experimental verification of microRNA-disease
associations are time-consuming and costly, so that computational modeling is a proper solution. Previously, we designed MiRAI, a predictive
method based on distributional semantics, to identify new associations between microRNA molecules and human diseases. Our preliminary results
showed very good prediction scores compared to other available methods. However, MiRAI performances depend on numerous parameters that cannot
be tuned manually. In this study, a parallel evolutionary algorithm is proposed for finding an optimal configuration of our predictive method.
The automatically parametrized version of MiRAI achieved excellent performance. It highlighted new miRNA-disease associations, especially the
potential implication of mir-188 and mir-795 in various diseases. In addition, our method allowed to detect several putative false associations
contained in the reference database.
By Pallez Denis, Claude Pasquier and Julien Gardès.
Scientific Reports 7, Article number: 10548 (2017) doi:10.1038/s41598-017-10065-y