Calculation method for predicting interaction between circular RNA and micro RNA

By employing gated multi-head attention and graph structure learning, the accuracy and stability of circRNA–miRNA interaction prediction are improved, addressing the issues of insufficient semantic feature expression and robustness in existing models, and achieving efficient circRNA–miRNA interaction prediction.

CN121768480APending Publication Date: 2026-03-31GUILIN UNIV OF ELECTRONIC TECH
0 Cites 0 Cited by

Patent Information

Application Number
CN202511960057.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-12-24
Publication Date
2026-03-31

AI Technical Summary

Technical Problem

Existing circRNA–miRNA interaction prediction models suffer from insufficient semantic feature expression, inadequate utilization of structural information, and limited robustness and generalization ability, making it difficult to meet the needs of large-scale, systematic CMI mining.

Method used

We employ a gated multi-head attention and graph structure learning approach, combining graph attention convolution and a nonlinear classifier. By using the multi-head attention mechanism, we extract key semantic information, enhance feature representation capabilities, adapt to topological relationship modeling under conditions of feature noise and missing features, and improve model stability through an adaptive optimization algorithm.

Benefits of technology

This approach enables more reliable prediction of circRNA–miRNA interactions, improving prediction accuracy and model generalization ability while reducing experimental costs and time.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a method and a system TGrKCMI for predicting interaction between circRNA (Ribonucleic Acid) and miRNA (Micro Ribonucleic Acid). According to the method, a pre-training model is used for extracting sequence features of circRNA and miRNA, and redundant information is reduced through PCA dimension reduction; then, a multi-head attention module with a gating mechanism is introduced to encode sequence features, and the expression ability of key information is enhanced; on the basis, a circRNA-miRNA interaction diagram is constructed, and robust diagram feature learning is realized in combination with diagram attention convolution of random feature masks. And finally, a kernel-based adaptive nonlinear classifier is adopted to carry out modeling on the fusion features, and high-precision and high-robustness interaction prediction is realized.
Need to check novelty before this filing date? Find Prior Art