4.4 Article

Feature impact assessment: a new score to identify relevant metabolomics features in artificial neural networks using validated labels

Journal

METABOLOMICS
Volume 19, Issue 4, Pages -

Publisher

SPRINGER
DOI: 10.1007/s11306-023-01996-x

Keywords

Artificial neural networks; Deep learning; Artificial intelligence; Feature selection; Metabolomics; Machine learning

Ask authors/readers for more resources

This study aims to develop a model-agnostic, simple, and interpretable feature impact score. Feature Impact Assessment (FIA) is calculated by varying feature combinations and observing changes in prediction outcomes. FIA outperforms LIME and SHAP in selecting biologically meaningful features and is applicable to different ANN architectures.
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.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.4
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available