BCE prediction method based on hybrid deep learning strategy
By constructing a BCE prediction model with a hybrid deep learning strategy, using the protein language big model and structural characteristics, the time-consuming and expensive BCE prediction in the existing technology is solved, and efficient and economical BCE prediction is achieved, supporting the rapid development of immune drugs and vaccines.
CN119993274AActive Publication Date: 2025-05-13ANQING NORMAL UNIV
7 Cites 0 Cited by
Patent Information
- Application Number
- CN202510055199.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-14
- Publication Date
- 2025-05-13
- Estimated Expiration
- 2045-01-14
AI Technical Summary
Technical Problem
The prior art is time-consuming and expensive to predict B-cell antigen epitope (BCE), making it difficult to efficiently support the development of immune drugs and vaccines.
Method used
Using a BCE prediction method based on a hybrid deep learning strategy, a prediction model including a database, feature extraction module, feature processing module and forward neural network module is constructed, and protein sequence features are extracted using a protein language model and predicted in combination with structural features.
Benefits of technology
It achieves rapid and economical prediction of BCE, reduces experimental costs and manpower investment, and improves the efficiency of vaccine and drug design.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention relates to the technical field of immune drug research and development, and discloses a BCE prediction method based on a hybrid deep learning strategy, and the method comprises the following steps: 1, constructing a BCE prediction model; 2, inputting a protein sequence into the BCE prediction model; and step 3, outputting a result whether the protein sequence is BCE or not by utilizing the prediction model. The BCE prediction model in the step 1 comprises a database, a feature extraction module, a feature processing module and a forward neural network module; wherein the database is used for acquiring a training data set; the feature extraction module is used for performing feature extraction on the data and obtaining four groups of features; and the feature processing module is used for processing the extracted features. According to the deep learning prediction method provided by the invention, a protein is represented by sequence features and structural features, sequence information and structural information are respectively extracted by using a four-channel deep neural network, and linear epitopes can be predicted by using the same model.
Need to check novelty before this filing date? Find Prior Art