典型文献
Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data
文献摘要：
Explainable artificial intelligence aims to interpret how machine learning models make decisions,and many model explainers have been developed in the computer vision field.However,understanding of the applicability of these model explainers to biological data is still lacking.In this study,we comprehensively evaluated multiple explainers by interpreting pre-trained models for pre-dicting tissue types from transcriptomic data and by identifying the top contributing genes from each sample with the greatest impacts on model prediction.To 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 reproducibility.Group 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 biomarkers.In summary,our work provides novel insights and guidance for exploring biological mechanisms using explainable machine learning models.
文献关键词：
中图分类号：
作者姓名：
Yongbing Zhao;Jinfeng Shao;Yan W.Asmann
作者机构：
Department of Quantitative Health Sciences,Mayo Clinic,Jacksonville,FL 32224,USA;The Laboratory of Malaria and Vector Research,National Institute of Allergy and Infectious Diseases,National Institutes of Health,Rockville,MD 20852,USA
文献出处：
引用格式：
[1]Yongbing Zhao;Jinfeng Shao;Yan W.Asmann-.Assessment and Optimization of Explainable Machine Learning Models Applied to Transcriptomic Data)[J].基因组蛋白质组与生物信息学报（英文版）,2022(05):899-911
A类：
explainers,explainer
B类：
Assessment,Optimization,Explainable,Machine,Learning,Models,Applied,Transcriptomic,Data,artificial,intelligence,aims,how,machine,learning,models,make,decisions,many,have,been,developed,computer,vision,field,However,understanding,applicability,these,biological,data,still,lacking,In,this,study,comprehensively,evaluated,multiple,by,interpreting,trained,dicting,types,from,transcriptomic,identifying,top,contributing,genes,each,sample,greatest,impacts,prediction,To,improve,reproducibility,interpretability,results,generated,proposed,series,optimization,strategies,different,architectures,multilayer,perceptron,MLP,convolutional,neural,network,We,observed,three,groups,combinations,high,Group,which,contains,aggregated,identified,tissues,that,exhibited,specific,manifestation,were,potential,cancer,biomarkers,summary,our,provides,novel,insights,guidance,exploring,mechanisms,using,explainable
AB值：
0.618021
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
