XAI-enabled neural network analysis of metabolite spatial distributions

doi:10.1007/s00216-023-04694-8

	XAI-enabled neural network analysis of metabolite spatial distributions
	Ma, Wenwu 1,2,3,4,5; Luo, Lanfang 2,3,4,5; Liang, Kun 2,3,4,5; Liu, Taoyan 2,3,4,5; Su, Jiali 2,3,4,5; Wang, Yuefan 2,3,4,5; Li, Jun 6,7,8; Zhou, S. Kevin 6,7,8; Shyh-Chang, Ng 2,3,4,5
	2023-04-21
发表期刊	ANALYTICAL AND BIOANALYTICAL CHEMISTRY
ISSN	1618-2642
页码	12
摘要	We used deep neural networks to process the mass spectrometry imaging (MSI) data of mouse muscle (young vs aged) and human cancer (tumor vs normal adjacent) tissues, with the aim of using explainable artificial intelligence (XAI) methods to rapidly identify biomarkers that can distinguish different classes of tissues, from several thousands of metabolite features. We also modified classic neural network architectures to construct a deep convolutional neural network that is more suitable for processing high-dimensional MSI data directly, instead of using dimension reduction techniques, and compared it to seven other machine learning analysis methods' performance in classification accuracy. After ascertaining the superiority of Channel-ResNet10, we used a novel channel selection-based XAI method to identify the key metabolite features that were responsible for its learning accuracy. These key metabolite biomarkers were then processed using MetaboAnalyst for pathway enrichment mapping. We found that Channel-ResNet10 was superior to seven other machine learning methods for MSI analysis, reaching > 98% accuracy in muscle aging and colorectal cancer datasets. We also used a novel channel selection-based XAI method to find that in young and aged muscle tissues, the differentially distributed metabolite biomarkers were especially enriched in the propanoate metabolism pathway, suggesting it as a novel target pathway for anti-aging therapy.
关键词	Mass spectrometry imaging Deep neural networks Feature extraction Pathway analysis Aging
DOI	10.1007/s00216-023-04694-8
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2019YFA0801701] ; National Natural Science Foundation of China[91957202] ; CAS Project for Young Scientists in Basic Research[YSBR-012] ; State Key Laboratory of Stem Cell and Reproductive Biology
WOS研究方向	Biochemistry & Molecular Biology ; Chemistry
WOS类目	Biochemical Research Methods ; Chemistry, Analytical
WOS记录号	WOS:000976256000003
出版者	SPRINGER HEIDELBERG
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/21410
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Shyh-Chang, Ng
作者单位	1.Univ Sci & Technol China, Dept Life Sci & Med, Hefei, Peoples R China 2.Chinese Acad Sci, State Key Lab Stem Cell & Reprod Biol, Beijing, Peoples R China 3.Chinese Acad Sci, Inst Stem Cell & Regenerat, Beijing, Peoples R China 4.Univ Chinese Acad Sci, Beijing, Peoples R China 5.Beijing Inst Stem Cell & Regenerat Med, Beijing, Peoples R China 6.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc Chinese Acad Sci, Beijing, Peoples R China 7.Univ Sci & Technol China, Ctr Med Imaging Robot Analyt Comp & Learning MIRAC, Sch Biomed Engn, Suzhou, Peoples R China 8.Univ Sci & Technol China, Suzhou Inst Adv Res, Suzhou, Peoples R China
推荐引用方式 GB/T 7714	Ma, Wenwu,Luo, Lanfang,Liang, Kun,et al. XAI-enabled neural network analysis of metabolite spatial distributions[J]. ANALYTICAL AND BIOANALYTICAL CHEMISTRY,2023:12.
APA	Ma, Wenwu.,Luo, Lanfang.,Liang, Kun.,Liu, Taoyan.,Su, Jiali.,...&Shyh-Chang, Ng.(2023).XAI-enabled neural network analysis of metabolite spatial distributions.ANALYTICAL AND BIOANALYTICAL CHEMISTRY,12.
MLA	Ma, Wenwu,et al."XAI-enabled neural network analysis of metabolite spatial distributions".ANALYTICAL AND BIOANALYTICAL CHEMISTRY (2023):12.