RNA G-quadruplex prediction method and system based on pre-training model and RNA secondary structure

By combining pre-trained models and RNA secondary structural features, using technologies such as convolutional neural networks and self-attention mechanisms, the problem of insufficient recognition ability of non-normal or variant rG4 in the existing technology is solved, and the performance and comprehensiveness of RNA G-quadruple body prediction is significantly improved.

CN119724349AActive Publication Date: 2025-03-28YANGTZE DELTA REGION INST (QUZHOU) UNIV OF ELECTRONIC SCI & TECH OF CHINA
6 Cites 1 Cited by

Patent Information

Application Number
CN202510228817.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-28
Publication Date
2025-03-28
Estimated Expiration
2045-02-28

AI Technical Summary

Technical Problem

The existing RNA G-quadruple (rG4) prediction methods lack flexibility, difficult to identify non-canonical or variant forms of rG4, and do not fully consider the secondary structural characteristics of RNA, resulting in insufficient comprehensive prediction.

Method used

Using a method based on pre-trained models and RNA secondary structure, we use positive and negative samples to build positive and negative samples and generate RNA secondary structure features, combine pre-trained BERT models to extract sequence features, and use convolutional neural networks and self-attention mechanisms to perform model training to predict RNA G-quadrilateral bodies.

Benefits of technology

It significantly improves the performance of RNA G-quadruple prediction, can better capture complex rG4 sequence characteristics and secondary structural characteristics of RNA, and improves the accuracy and comprehensiveness of prediction.

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

Abstract

The invention discloses an RNA G-quadruplex prediction method and system based on a pre-training model and an RNA secondary structure, and the method comprises the steps: obtaining the position information of human rG4 on a human transcript; for each sequence, filling the same length to two sides according to the position coordinates of the sequence, so that the total length reaches a set length value; obtaining human cDNA sequence data as a reference sequence, and extracting rG4 data containing flanking sequence information from the cDNA sequence according to the filled sequence coordinates as a positive sample sequence; disorganizing each positive sample sequence to obtain a negative sample sequence; rNA secondary structure features of each sample sequence are generated; extracting sequence features of the sample sequence by using a pre-training model; and inputting the sequence features and the RNA secondary structure features into a prediction model for model training. According to the scheme, the secondary structural features of the RNA sequence are utilized, the secondary structural features are introduced as auxiliary information, and the prediction performance of the model can be remarkably improved.
Need to check novelty before this filing date? Find Prior Art