HNF-DDA:子图对比驱动的变压器式异质网络嵌入用于药物疾病关联预测
Yifan Shang1, Zixu Wang2, Yangyang Chen1
1College of Computer Science and Electronic Engineering, Hunan University, Changsha, 410082, China.
本研究介绍了HNF-DDA,这是一种用于药物疾病关联 (DDA) 预测的新型模型,通过整合全球和本地网络信息来增强药物发现. HNF-DDA提高了预测准确度,并确定了现有药物的潜在新用途.
科学领域:
- 计算生物学是一种计算生物学.
- 生物信息学是一种生物信息学.
- 药物发现 药物发现
背景情况:
- 药物疾病关联 (DDA) 预测对于识别新的治疗潜力至关重要.
- 现有的方法往往无法捕捉复杂的关系和全球网络信息.
研究的目的:
- 提出HNF-DDA,一种变压器式异质网络嵌入模型,用于增强DDA预测.
- 整合多omics数据并捕捉全球和本地网络结构.
主要方法:
- 使用全对消息传递策略来捕获全球网络结构.
- 实现了子图对比学习,从局部药物疾病子图中学习高级语义信息.
- 在异质网络嵌入框架内集成的多学科信息.
主要成果:
- 在两个基准数据集上,HNF-DDA的表现优于几种最先进的方法.
- 在不同的数据集分割方案中表现出卓越的概括能力.
- 案例研究显示,预测乳腺癌和前列腺癌治疗药物的准确性很高.
结论:
- 通过使用异质信息,HNF-DDA有效地学习药物和疾病表征.
- 该模型显示了药物重新定位应用的巨大潜力.
- 信息传递和子图对比学习的集成增强了DDA预测.
更多相关视频
03:37Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
Published on: March 1, 2024
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
相关概念视频
Protein Networks
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,...
Genome-wide Association Studies-GWAS
GWAS does not require the identification of the target gene involved in...
Drug Discovery: Overview
Drug Biotransformation: Overview
Combined Effects of Drugs: Synergism
Such synergistic combinations...
Factors Influencing Drug Absorption: Disease States and Pharmacology
Substances such as alcohol and specific drugs, including antineoplastics, can also negatively impact drug absorption. For instance,...
