Refining EI-MS library search results through atomic-level insights
Open Access
- 6 November 2025
- journal article
- research article
- Published by Springer Nature in Communications Chemistry
- Vol. 8 (1) , 1-13
Abstract
The inherent complexity of mass spectra and the lack of direct correlation between spectral and structural similarities retards structure elucidation and accurate peak annotation. Our methodology employs modified atomic environments from topological radii zero to represent collections of annotated spectral peaks. Rather than aiming for de novo structure prediction from spectra, our objective is to refine and re-rank candidate structures retrieved by existing library search methods using predicted atom environments. We conducted a multi-step complexity reduction to mass-to-fragment mappings and trained the Transformer model to predict the atomic environments of compounds directly from mass and intensity data, achieving a peak precision of 86.1% and a recall rate of 78.4% on the test set. This novel framework not only aids in interpreting EI-MS data by providing insights into structural contents but also refines cosine similarity rankings by suggesting the inclusion or exclusion of certain atomic environments. Our findings over the NIST database suggest that our approach complements conventional methods by improving spectra matching through an in-depth atomic-level analysis.Keywords
Funding Information
- National Research Foundation of Korea (NRF-2022M3E5F3081268, NRF-2022R1C1C1005080, RS-2023-00256320, 5120200513755)
- MOE | Korea Environmental Industry and Technology Institute (RS-2023-00219144)
- Seoul National University (370C-20220109, 0413-20230053)
- Institute of Information and Commnucations Technology Planning & Evaluation
This publication has 62 references indexed in Scilit:
- Deep learning under mass‐to‐charge ratio pre‐retrieval to realize electron ionization mass spectrometry library retrievalRapid Communications in Mass Spectrometry, 2022
- Development and application of an in-house library and workflow for gas chromatography–electron ionization–accurate-mass/high-resolution mass spectrometry screening of environmental samplesAnalytical and Bioanalytical Chemistry, 2021
- Pattern Similarity Measures Applied to Mass Spectra2020
- MetFID: artificial neural network-based compound fingerprint prediction for metabolite annotationMetabolomics, 2020
- Identification of small molecules using accurate mass MS/MS searchMass Spectrometry Reviews, 2017
- Towards First Principles Calculation of Electron Impact Mass Spectra of MoleculesAngewandte Chemie International Edition, 2013
- Advances in structure elucidation of small molecules using mass spectrometryBioanalytical Reviews, 2010
- MassBank: a public repository for sharing mass spectral data for life sciencesJournal of Mass Spectrometry, 2010
- Estimating probabilities of correct identification from results of mass spectral library searchesJournal of the American Society for Mass Spectrometry, 1994
- Probability based matching of mass spectra. Rapid identification of specific compounds in mixturesJournal of Mass Spectrometry, 1974