HIV抗体亲和性预测方法、系统、设备及介质
By constructing benchmark machine learning and recurrent neural network models, the problems of time-consuming, labor-intensive, and inaccurate HIV antibody affinity testing in existing technologies have been solved, achieving more efficient and accurate predictions.
CN117275589BActive Publication Date: 2026-07-17DALI UNIV
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- DALI UNIV
- Filing Date
- 2023-08-28
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Existing technologies are time-consuming and laborious in determining HIV antibody affinity, and suffer from problems such as insufficient antibody coverage and low accuracy.
Method used
We constructed a benchmark machine learning model and a recurrent neural network model, trained and predicted using affinity data of HIV viral proteins and antibodies, and improved prediction performance using algorithms such as decision trees, random forests, bidirectional gated neural units, and bidirectional long short-term memory networks.
Benefits of technology
It improved the predictive performance of HIV antibody affinity, enhancing the accuracy and efficiency of prediction.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN117275589B_ABST
Abstract
本发明涉及一种HIV抗体亲和性预测方法、系统、计算机设备及存储介质。所述方法包括：检索HIV病毒蛋白与抗体的亲和性数据、抗体对应HIV病毒蛋白序列数据，将IC50作为衡量亲和性的标准生成数据集并数据预处理得到输入数据集；构建基准机器学习模型，将输入数据集分为第一训练集和第一测试集；调整基准机器学习模型参数，得到第一训练结果；构建循环神经网络模型，将输入数据集分为第二训练集、验证集、第二测试集，训练循环神经网络模型输出第二亲和性预测数据得到第二训练结果；确定亲和性预测结果。通过构建中和抗体‑HIV病毒蛋白‑IC50输入数据集，比较两个模型亲和性定量预测性能，从而提高HIV抗体亲和性的预测性能。
Need to check novelty before this filing date? Find Prior Art