Feature Selection Pipelines with Classification for Non-targeted Metabolomics Combining the Neural Network and Genetic Algorithm

• Published in: Analytical chemistry (Washington) 2022-04, Vol.94 (14), p.5474-5482
• Main Authors: Lisitsyna, Anna, Moritz, Franco, Liu, Youzhong, Al Sadat, Loubna, Hauner, Hans, Claussnitzer, Melina, Schmitt-Kopplin, Philippe, Forcisi, Sara
• Format: Article
• Language: English
• Subjects: Algorithms; Artificial neural networks; Chemistry; Classification; Cyclotron resonance; Datasets; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2; Feature selection; Fourier analysis; Fourier transforms; Genetic algorithms; Glucose tolerance; Health risks; High resolution; Humans; Ions; Mass spectrometry; Mass Spectrometry - methods; Mass spectroscopy; Metabolomics; Metabolomics - methods; Neural networks; Neural Networks, Computer; Scientific imaging; Spectroscopy; Statistical analysis; Statistical methods
• ISSN: 0003-2700; 1520-6882
• DOI: 10.1021/acs.analchem.1c03237

Non-targeted metabolomics via high-resolution mass spectrometry methods, such as direct infusion Fourier transform-ion cyclotron resonance mass spectrometry (DI-FT-ICR MS), produces data sets with thousands of features. By contrast, the number of samples is in general substantially lower. This disparity presents challenges when analyzing non-targeted metabolomics data sets and often requires custom methods to uncover information not always accessible via classical statistical techniques. In this work, we present a pipeline that combines a convolutional neural network with traditional statistical approaches and an adaptation of a genetic algorithm. The developed method was applied to a lifestyle intervention cohort data set, where subjects at risk of type 2 diabetes underwent an oral glucose tolerance test. Feature selection is the final result of the pipeline, achieved through classification of the data set via a neural network, with a precision-recall score of over 0.9 on the test set. The features most relevant for the described classification were then chosen via a genetic algorithm. The output of the developed pipeline encompasses approximately 200 features with high predictive scores, providing a fingerprint of the metabolic changes in the prediabetic class on the data set. Our framework presents a new approach which allows to apply complex modeling based on convolutional neural networks for the analysis of high-resolution mass spectrometric data.