Abstract
MicroRNAs (miRNAs) performs crucial roles in various human diseases, but miRNA-related pathogenic mechanisms remain incompletely understood. Revealing the potential relationship between miRNAs and diseases is a critical problem in biomedical research. Considering limitation of existing computational approaches, we develop improved low-rank matrix recovery (ILRMR) for miRNA-disease association prediction. ILRMR is a global method that can simultaneously prioritize potential association for all diseases and does not require negative samples. ILRMR can also identify promising miRNAs for investigating diseases without any known related miRNA. By integrating miRNA-miRNA similarity information, disease-disease similarity information, and miRNA family information to matrix recovery, ILRMR performs better than other methods in cross validation and case studies.
Highlights
MicroRNAs comprise a set of 22-nucleotide long, noncoding RNAs, which are widespread in fauna and flora1. miRNAs act as crucial regulatory factors of gene expressions that result in post-transcriptional repression or degradation by complementarily binding to specific 3′ untranslated regions of their mRNA2. miRNAs participate in various important biological progresses, such as cell survival, apoptosis, differentiation, tumor growth, and metastasis[3]
In Leave-one out cross validation (LOOCV) of improved low-rank matrix recovery (ILRMR), each known miRNA-disease interaction was excluded as test sample, and remaining interactions were used as training samples to recover predictive matrix
We develop ILRMR for miRNA-disease association prediction
Summary
MicroRNAs (miRNAs) comprise a set of 22-nucleotide long, noncoding RNAs, which are widespread in fauna and flora1. miRNAs act as crucial regulatory factors of gene expressions that result in post-transcriptional repression or degradation by complementarily binding to specific 3′ untranslated regions of their mRNA2. miRNAs participate in various important biological progresses, such as cell survival, apoptosis, differentiation, tumor growth, and metastasis[3]. With accumulation of available studies and emergence of large amounts of biological data about miRNA, powerful computational approach can be used to mine underlying miRNA-disease associations from these data[10]. Numerous approaches were presented to predict miRNA-disease associations from machine-learning-based and network-similarity-based perspective. Negative samples of disease-related miRNAs are difficult even impossible to obtain[17]. These machine-learning-based approaches use unlabeled miRNA-disease associations as negative samples; inevitably, their accuracy of prediction is markedly influenced. Chen et al.[18] proposed a semi-supervised approach, named Regularized Least Squares for miRNA-Disease Association (RLSMDA), which predicted miRNA-disease association on the framework of regularized least squares
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
