Method and system for recognizing type iv secretion effect protein based on multi-modal information

By employing a multimodal information fusion learning framework, this method utilizes protein language models and structure prediction models to obtain amino acid residue features and spatial adjacency graphs. By combining contrastive learning and cross-attention modules, it addresses the lack of three-dimensional structural modeling in existing methods and achieves high-precision identification of type IV secretory effector proteins.

CN121483389BActive Publication Date: 2026-06-02EAST CHINA JIAOTONG UNIVERSITY
2 Cites 0 Cited by

Patent Information

Application Number
CN202610025680.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-01-09
Publication Date
2026-06-02
Estimated Expiration
2046-01-09

AI Technical Summary

Technical Problem

Existing methods for identifying type IV secretory effector proteins mainly rely on amino acid sequences or shallow features, lacking effective modeling of the three-dimensional spatial structure of proteins. This results in insufficient generalization ability and biological interpretability in low homology scenarios.

Method used

A multimodal information fusion learning framework is adopted. Amino acid residue features and spatial adjacency graphs are obtained through protein language models and structure prediction models. The contrastive learning module aligns sequences and structural representations, and the cross-attention module is used to achieve feature fusion. Finally, classification is performed through gated linear units.

Benefits of technology

It significantly improved the recognition accuracy and generalization ability of type IV secretory effector proteins, and enhanced the model's recognition accuracy and stability under cross-modal information.

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

Abstract

The application discloses a type IV secretory effector protein recognition method and system based on multi-modal information, and belongs to the technical field of bioinformatics and secretory protein recognition. The amino acid residue features of the protein are extracted by using a protein language model, and a spatial adjacency graph of the protein is constructed by using a three-dimensional structure predicted by a protein structure prediction model; then, sequence features and structure features of the protein are extracted by a deep sequence module and a hierarchical graph module respectively; meanwhile, a contrast learning module is introduced to realize cross-modal alignment of the same protein in a latent space; the sequence features and the structure features are bidirectionally interacted by using a cross attention module to obtain joint features, and finally, a classification result is output after a nonlinear transformation of a gate linear unit, and is used for prediction of the type IV secretory effector protein. The application realizes efficient cooperation of sequence and structure double modal information, and significantly improves the accuracy of type IV secretory effector protein recognition.
Need to check novelty before this filing date? Find Prior Art