miRNAs (microRNAs) regulate gene expression by binding to mRNAs, inhibiting translation, or promoting mRNA degradation. miRNAs are of great importance in the development of diseases. Currently, a variety of miRNA target prediction tools are available, which analyze sequence complementarity, thermodynamic stability, and evolutionary conservation to predict miRNA-target interactions (MTIs) within the 3’ untranslated region (3’UTR). We propose a concept for further screening sequence-based predicted MTIs by considering the disease similarity between miRNA and gene to establish a prediction database of disease-specific MTIs. We fine-tuned a Sentence-BERT model to calculate disease semantic similarity. The method achieved an F1 score of 0.88 in accurately distinguishing protein-level experimentally (Western Blot, Reporter Assay, etc.) validated MTIs and predicted MTIs. Moreover, the method exhibits exceptional generalizability across different databases. The proposed method was utilized to calculate the similarity of disease in 1,220,904 MTIs from miRTarbase, miRDB, and miRWalk, involving 6,085 genes and 1,261 pre-miRNAs. The study holds the potential to offer valuable insights into comprehending miRNA-gene regulatory networks and advancing progress in disease diagnosis, treatment, and drug development.
