Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data

作     者：Yongbing Zhao Jinfeng Shao Yan W.Asmann Yongbing Zhao;Jinfeng Shao;Yan W.Asmann

作者机构：Department of Quantitative Health SciencesMayo ClinicJacksonvilleFL 32224USA The Laboratory of Malaria and Vector ResearchNational Institute of Allergy and Infectious DiseasesNational Institutes of HealthRockvilleMD 20852USA 

出 版 物：《Genomics, Proteomics & Bioinformatics》 (基因组蛋白质组与生物信息学报（英文版）)

年 卷 期：2022年第20卷第5期

页      面：899-911页

核心收录：

学科分类：0710[理学-生物学] 0831[工学-生物医学工程（可授工学、理学、医学学位）] 12[管理学] 0711[理学-系统科学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：GTEx National Institutes of Health, NIH 

主　　题：Machine learning Model interpretability Gene expression Marker gene Omics data mining 

摘      要：Explainable artificial intelligence aims to interpret how machine learning models make decisions,and many model explainers have been developed in the computer vision ***,understanding of the applicability of these model explainers to biological data is still *** this study,we comprehensively evaluated multiple explainers by interpreting pre-trained models for predicting tissue types from transcriptomic data and by identifying the top contributing genes from each sample with the greatest impacts on model *** improve the reproducibility and interpretability of results generated by model explainers,we proposed a series of optimization strategies for each explainer on two different model architectures of multilayer perceptron(MLP)and convolutional neural network(CNN).We observed three groups of explainer and model architecture combinations with high *** II,which contains three model explainers on aggregated MLP models,identified top contributing genes in different tissues that exhibited tissue-specific manifestation and were potential cancer *** summary,our work provides novel insights and guidance for exploring biological mechanisms using explainable machine learning models.