SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction

doi:10.1109/TVCG.2024.3456325

	SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction
	Haoran Jiang; Shaohan Shi; Shuhao Zhang; Jie Zheng; Quan Li
	2024
发表期刊	IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (IF:4.7[JCR-2023],5.1[5-Year])
ISSN	2160-9306
EISSN	1941-0506
卷号	PP 期号:99 页码:919-929
发表状态	已发表
DOI	10.1109/TVCG.2024.3456325
摘要	Synthetic Lethal (SL) relationships, though rare among the vast array of gene combinations, hold substantial promise for targeted cancer therapy. Despite advancements in AI model accuracy, there is still a significant need among domain experts for interpretive paths and mechanism explorations that align better with domain-specific knowledge, particularly due to the high costs of experimentation. To address this gap, we propose an iterative Human-AI collaborative framework with two key components: 1) HumanEngaged Knowledge Graph Refinement based on Metapath Strategies, which leverages insights from interpretive paths and domain expertise to refine the knowledge graph through metapath strategies with appropriate granularity. 2) Cross-Granularity SL Interpretation Enhancement and Mechanism Analysis, which aids experts in organizing and comparing predictions and interpretive paths across different granularities, uncovering new SL relationships, enhancing result interpretation, and elucidating potential mechanisms inferred by Graph Neural Network (GNN) models. These components cyclically optimize model predictions and mechanism explorations, enhancing expert involvement and intervention to build trust. Facilitated by SLInterpreter, this framework ensures that newly generated interpretive paths increasingly align with domain knowledge and adhere more closely to real-world biological principles through iterative Human-AI collaboration. We evaluate the framework's efficacy through a case study and expert interviews
关键词	Economic and social effects Collaborative systems Graph neural networks Interpretability Iterative human-AI collaboration Knowledge graphs Model interpretability Network-based Synthetic lethal Synthetic lethality Visual analytics
URL	查看原文
收录类别	EI
语种	英语
出版者	IEEE Computer Society
EI入藏号	20244017128542
EI主题词	Graph neural networks
EI分类号	1101 ; 971 Social Sciences
原始文献类型	Article in Press
来源库	IEEE
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/427480
专题	信息科学与技术学院信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_郑杰组信息科学与技术学院_PI研究组_李权组
作者单位	School of Information Science and Technology, and Shanghai Engineering Research Center of Intelligent Vision and Imaging, ShanghaiTech University, China
第一作者单位	信息科学与技术学院
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Haoran Jiang,Shaohan Shi,Shuhao Zhang,et al. SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction[J]. IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,2024,PP(99):919-929.
APA	Haoran Jiang,Shaohan Shi,Shuhao Zhang,Jie Zheng,&Quan Li.(2024).SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction.IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS,PP(99),919-929.
MLA	Haoran Jiang,et al."SLInterpreter: An Exploratory and Iterative Human-AI Collaborative System for GNN-based Synthetic Lethal Prediction".IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS PP.99(2024):919-929.