Mass Spectra Prediction with Structural Motif-based Graph Neural Networks

TL;DR

This paper introduces MoMS-Net, a graph neural network model that predicts mass spectra from molecular structural motifs, enhancing spectral library expansion and molecular identification accuracy.

Contribution

The paper presents a novel GNN-based model that leverages structural motifs for mass spectra prediction, outperforming existing models and efficiently capturing long-range dependencies.

Findings

MoMS-Net outperforms existing models in mass spectra prediction.

The model effectively captures long-range dependencies with less memory.

It demonstrates versatility across diverse mass spectra datasets.

Abstract

Mass spectra, which are agglomerations of ionized fragments from targeted molecules, play a crucial role across various fields for the identification of molecular structures. A prevalent analysis method involves spectral library searches,where unknown spectra are cross-referenced with a database. The effectiveness of such search-based approaches, however, is restricted by the scope of the existing mass spectra database, underscoring the need to expand the database via mass spectra prediction. In this research, we propose the Motif-based Mass Spectrum Prediction Network (MoMS-Net), a system that predicts mass spectra using the information derived from structural motifs and the implementation of Graph Neural Networks (GNNs). We have tested our model across diverse mass spectra and have observed its superiority over other existing models. MoMS-Net considers substructure at the graph level, which facilitates the incorporation of long-range dependencies while using less memory compared to the graph transformer model.