基于双分割图形变压器预测circRNA-药物关联
IEEE journal of biomedical and health informatics
|December 30, 2025
概括
这项研究引入了CircRNA-Drug Bipartite Graph Transformer (CDBGT),用于预测循环RNA (circRNA) 和药物关联. 通过整合多omics数据和网络拓来获得新的治疗见解,CDBGT提高了预测准确性.
科学领域:
- 生物信息学是一种生物信息学.
- 计算生物学 计算生物学
- 基因组学就是基因组学.
背景情况:
- 循环RNAs (circRNAs) 是调节药物反应的非编码RNA.
- 现有的circRNA药物关联计算方法缺乏多omics数据和网络拓集成.
研究的目的:
- 开发一个先进的计算框架,CDBGT,用于预测circRNA药物协会.
- 利用多主题数据和异质网络拓来提高预测准确度.
主要方法:
- 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer (CDBGT) 框架. 提出了CircRNA-Drug Bipartite Graph Transformer的框架.
- 集成circRNA序列/指纹特征 (RNA-FM,ChemBERTa),多omics数据和异质网络拓.
- 在双分图形变压器中使用拓位置编码 (度,度排名,光谱).
主要成果:
- 在5倍交叉验证中,CDBGT表现稳定.
- 在响应数据集中实现了高ROC-AUC (0.9674) 和PR-AUC (0.9540).
- 在ROC-AUC中表现比现有方法高3.20-26.87个百分点,在目标数据集 (ROC-AUC0.8621) 中取得了显著的结果.
结论:
- 通过整合各种数据类型和网络信息,CDBGT有效地预测circRNA药物相关性.
- 该框架为推进基于circRNA的治疗研究提供了一个有前途的工具.
- 废弃性研究证实了每个模块对CDBGT性能的贡献.
更多相关视频
10:27In Silico Identification and Characterization of circRNAs During Host-Pathogen Interactions
Published on: October 21, 2022
1.9K
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
1.2K
相关概念视频
02:26Protein Networks
4.4K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.4K
01:30Combined Effects of Drugs: Antagonism
11.5K
The combined effects of drugs can result in various interactions, of which an important type is antagonism. Antagonism is a mechanism where one drug inhibits or counteracts the effects of another drug. Antagonism can occur through various means, including receptor binding, allosteric modulation, functional interaction, chemical reactions, and pharmacokinetic processes.
The most common type is receptor antagonism, where one drug acts as an antagonist to block the effects of another drug by...
The most common type is receptor antagonism, where one drug acts as an antagonist to block the effects of another drug by...
11.5K