.png){kind=icon}
返回
Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2024.3471508.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Molecular interaction prediction plays a crucial role in forecasting unknown interactions between molecules, such as drug-target interaction (DTI) and drug-drug interaction (DDI), which are essential in the field of drug discovery and therapeutics. Although previous prediction methods have yielded promising results by leveraging the rich semantics and topological structure of biomedical knowledge graphs (KGs), they have primarily focused on enhancing predictive performance without addressing the presence of inevitable noise and inconsistent semantics. This limitation has hindered the advancement of KG-based prediction methods. To address this limitation, we propose BioKDN (Biomedical Knowledge Graph Denoising Network) for robust molecular interaction prediction. BioKDN refines the reliable structure of local subgraphs by denoising noisy links in a learnable manner, providing a general module for extracting task-relevant interactions. To enhance the reliability of the refined structure, BioKDN maintains consistent and robust semantics by smoothing relations around the target interaction. By maximizing the mutual information between reliable structure and smoothed relations, BioKDN emphasizes informative semantics to enable precise predictions. Experimental results on real-world datasets show that BioKDN surpasses state-of-the-art models in DTI and DDI prediction tasks, confirming the effectiveness and robustness of BioKDN in denoising unreliable interactions within contaminated KGs.
Keyword:
Molecular interaction prediction
knowledge graph reasoning
knowledge graph reasoning
knowledge-enhanced network
knowledge-enhanced network
knowledge-enhanced network
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
A unified drug-target interaction prediction framework based on knowledge graph and recommendation system基于知识图谱和推荐系统的统一药物-靶标相互作用预测框架.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏Biomedical Knowledge Graph Embedding With Capsule Network for Multi-Label Drug-Drug Interaction Prediction基于胶囊网络的生物医学知识图谱嵌入多标签药物相互作用预测
OAAI
OAAI分享收藏Heterogeneous relational reasoning in knowledge graphs with reinforcement learningINFORMATION FUSIONOAAI
INFORMATION FUSIONIF15.5
OAAI分享收藏
查看更多内容