特征影响评估：一种使用经过验证的标签在人工神经网络中识别相关代谢组学特征的新评分方法。
Feature impact assessment: a new score to identify relevant metabolomics features in artificial neural networks using validated labels.
作者信息
Wang Danhui, Greenwood Peyton, Klein Matthias S
机构信息
Department of Food Science and Technology, The Ohio State University, Columbus, OH, 43210, USA.
Department of Nutrition and Food Sciences, Texas Woman's University, Denton, TX, 76204, USA.
出版信息
Metabolomics. 2023 Mar 25;19(4):22. doi: 10.1007/s11306-023-01996-x.
INTRODUCTION
Artificial Neural Networks (ANN) are increasingly used in metabolomics but are hard to interpret.
OBJECTIVES
We aimed at developing a feature impact score that is model-agnostic, simple, and interpretable.
METHODS
Feature Impact Assessment (FIA) is calculated by varying combinations of features within their observed value range and checking for changes in prediction outcomes. FIA was implemented in R and tested on metabolomics datasets.
RESULTS
FIA exceeded LIME and SHAP in selecting biologically meaningful features. Values were comparable across different ANN architectures.
CONCLUSION
FIA is a novel score ranking feature impact, helping interpreting ANN in the metabolomics field.
引言
人工神经网络（ANN）在代谢组学中的应用日益广泛，但难以解释。
目的
我们旨在开发一种与模型无关、简单且可解释的特征影响评分。
方法
通过在其观测值范围内改变特征的组合并检查预测结果的变化来计算特征影响评估（FIA）。FIA在R语言中实现并在代谢组学数据集上进行测试。
结果
在选择具有生物学意义的特征方面，FIA超过了局部可解释模型无关解释（LIME）和SHapley值解释（SHAP）。不同ANN架构的结果具有可比性。
结论
FIA是一种用于对特征影响进行排名的新评分，有助于解释代谢组学领域中的人工神经网络。
Zotero 插件