SEBGLMA: Semantic Embedded Bipartite Graph Network for Predicting lncRNA-miRNA Associations

Identifying the association between long noncoding RNA (lncRNA) and micro-RNA (miRNA) is of great significance for treatment diseases by interfering with combination miRNA messenger (mRNA). Although many efforts resources have been invested to identify lncRNA-miRNA associations (LMAs), clinical trials are still expensive laborious. Nevertheless, experiments also need consult a large number side effects. Therefore, novel computer-aided models urgently needed predict LMAs. This paper proposed semantic embedded bipartite graph network predicting (SEBGLMA), which provided feature extraction method integrating K-mer segmentation, word2vec, Gaussian interaction profile (GIP), convolution (GCN). Concretely, attribute characteristics sequences extracted segmentation word2vec modules. Afterward, adjacent matrix completed GIP self-similarity. Then, fed into GCN embedding behavior features. Finally, features sent rotation forest (RoF) detecting potential The average accuracy, precision, sensitivity, specificity, Matthews correlation coefficient, F1-Score 87.09%, 87.66%, 87.03%, 87.84%, 74.18%, 86.99% on benchmark data set. For fairly validating performance our model, we conducted various comparisons different classifiers. Furthermore, case studies hsa-miR-497-5P NONHSAT022145.2 established. results further illustrated that anticipated become robust reliable tool identification