EVA: Evaluation of Metabolic Feature Fidelity Using a Deep Learning Model Trained With Over 25000 Extracted Ion Chromatograms

Extracting metabolic features from liquid chromatography-mass spectrometry (LC-MS) data relies on the recognition of extracted ion chromatogram (EIC) peak shapes using peak picking algorithms. Unfortunately, all peak picking algorithms present a significant drawback of generating a problematic number of false positives. In this work, we take advantage of deep learning technology to develop a convolutional neural network (CNN)-based program that can automatically recognize metabolic features with poor EIC shapes, which are of low feature fidelity and more likely to be false. Our CNN model was trained using 25095 EIC plots collected from 22 LC-MS-based metabolomics projects of various sample types, LC and MS conditions. Notably, we manually inspected all the EIC plots to assign good or poor EIC quality for accurate model training. The trained CNN model is embedded into a C#-based program, named EVA (short for evaluation). The EVA Windows Application is a versatile platform that can process metabolic features generated by LC-MS systems of various vendors and processed using various data processing software. Our comprehensive evaluation of EVA indicates that it achieves over 90% classification accuracy. EVA can be readily used in LC-MS-based metabolomics projects and is freely available on the Microsoft Store by searching EVA Metabolomics.

Automated summary

This study developed a program based on convolutional neural network using deep learning technology to automatically recognize metabolic features with poor EIC shapes, achieving over 90% classification accuracy in LC-MS metabolomics projects. The program, named EVA, can be freely accessed on the Microsoft Store and is compatible with various LC-MS systems and data processing software.