DNRLCNN: A CNN Framework for Identifying MiRNA –Disease Associations Using Latent Feature Matrix Extraction with Positive Samples

AbstractEmerging evidence indicates that miRNAs have strong relationships with many human diseases. Investigating the associations will contribute to elucidating the activities of miRNAs and pathogenesis mechanisms, and providing new opportunities for disease diagnosis and drug discovery. Therefore, it is of significance to identify potential associations between miRNAs and diseases. The existing databases about the miRNA –disease associations (MDAs) only provide the known MDAs, which can be regarded as positive samples. However, the unknown MDAs are not sufficient to regard as reliable negative samples. To deal with this uncertainty, we proposed a convolutional neural network (CNN) framework, named DNRLCNN, based on a latent feature matrix extracted by only positive samples to predict MDAs. First, by only considering the positive samples into the calculation process, we captured the latent feature matrix for complex interactions between miRNAs and diseases in low-dimensional space. Then, we constructed a fea ture vector for each miRNA and disease pair based on the feature representation. Finally, we adopted a modified CNN for the feature vector to predict MDAs. As a result, our model achieves better performance than other state-of-the-art methods which based CNN in fivefold cross-validation on both miRN A–disease association prediction task (average AUC of 0.9030) and miRNA–phenotype association prediction task (average AUC of 0. 9442). In addition, we carried out case...
Source: Interdisciplinary Sciences, Computational Life Sciences - Category: Bioinformatics Source Type: research