Work

Determination of Flavonoid Glycoside Isomers Using Vision Transformer and Tandem Mass Spectrometry

Year: 2024

Type: article

Abstract: A vision transformer (ViT)-based deep neural network was applied to classify the flavonoid glycoside isomers by analyzing electrospray ionization tandem mass spectrometry (ESI-MS/MS) spectra. Our model successfully classified the flavonoid isomers with various substitution patterns (3-O, 6-C, 7-O, 8-C, 4'-O) and multiple glycosides, achieving over 80% accuracy during training. In addition, the experimental spectra from flavonoid glycoside standards were acquired with different adducts, and our model showed robust performance regardless of the experimental conditions. As a result, the vision transformer-based computer vision model is promising for analyzing mass spectrometry data.

Source: Plants

DOI: 10.3390/plants13233401

Authors: Ji In Park, Myeong Ji Kim, Kyu Hyeong Lee, Seung Hyun Oh, Young Hoon Kang, Hyunwoo Kim

Institution: Dongguk University

Language: English

Topic: Mass Spectrometry Techniques and Applications

Subfield: Spectroscopy

Field: Chemistry

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $3,069

Funder: National Research Foundation of Korea