Mass Spectra Prediction with Structural Motif-based Graph Neural Networks
This work addresses the limitation of spectral library searches in fields like chemistry by expanding mass spectra databases, though it appears incremental as it builds on existing GNN methods.
The paper tackled the problem of mass spectra prediction for molecular structure identification by proposing MoMS-Net, a system using structural motifs and Graph Neural Networks, which outperformed existing models in tests across diverse mass spectra.
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.