Saved in:
Bibliographic Details
Main Authors: Ma, Tengfei, Chen, Yujie, Tao, Wen, Zheng, Dashun, Lin, Xuan, Pang, Patrick Cheong-lao, Liu, Yiping, Wang, Yijun, Wang, Longyue, Song, Bosheng, Zeng, Xiangxiang, Yu, Philip S.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.06682
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929552655122432
author Ma, Tengfei
Chen, Yujie
Tao, Wen
Zheng, Dashun
Lin, Xuan
Pang, Patrick Cheong-lao
Liu, Yiping
Wang, Yijun
Wang, Longyue
Song, Bosheng
Zeng, Xiangxiang
Yu, Philip S.
author_facet Ma, Tengfei
Chen, Yujie
Tao, Wen
Zheng, Dashun
Lin, Xuan
Pang, Patrick Cheong-lao
Liu, Yiping
Wang, Yijun
Wang, Longyue
Song, Bosheng
Zeng, Xiangxiang
Yu, Philip S.
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2312_06682
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
Ma, Tengfei
Chen, Yujie
Tao, Wen
Zheng, Dashun
Lin, Xuan
Pang, Patrick Cheong-lao
Liu, Yiping
Wang, Yijun
Wang, Longyue
Song, Bosheng
Zeng, Xiangxiang
Yu, Philip S.
Artificial Intelligence
Machine Learning
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
title Learning to Denoise Biomedical Knowledge Graph for Robust Molecular Interaction Prediction
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2312.06682