Rapid Prediction of Electron-Ionization Mass Spectrometry Using Neural Networks

Overview

Journal ACS Cent Sci

Specialty Chemistry

Date 2019 May 2

PMID 31041390

Citations 41

Authors

Jennifer N Wei

David Belanger

Ryan P Adams

D Sculley

Affiliations

Soon will be listed here.

Abstract

When confronted with a substance of unknown identity, researchers often perform mass spectrometry on the sample and compare the observed spectrum to a library of previously collected spectra to identify the molecule. While popular, this approach will fail to identify molecules that are not in the existing library. In response, we propose to improve the library's coverage by augmenting it with synthetic spectra that are predicted from candidate molecules using machine learning. We contribute a lightweight neural network model that quickly predicts mass spectra for small molecules, averaging 5 ms per molecule with a recall-at-10 accuracy of 91.8%. Achieving high-accuracy predictions requires a novel neural network architecture that is designed to capture typical fragmentation patterns from electron ionization. We analyze the effects of our modeling innovations on library matching performance and compare our models to prior machine-learning-based work on spectrum prediction.

Citing Articles

A guide to reverse metabolomics-a framework for big data discovery strategy.

Charron-Lamoureux V, Mannochio-Russo H, Lamichhane S, Xing S, Patan A, Portal Gomes P Nat Protoc. 2025; .

PMID: 40021805 DOI: 10.1038/s41596-024-01136-2.

From multi-omics to predictive biomarker: AI in tumor microenvironment.

Hai L, Jiang Z, Zhang H, Sun Y Front Immunol. 2025; 15:1514977.

PMID: 39763649 PMC: 11701166. DOI: 10.3389/fimmu.2024.1514977.

JESTR: Joint Embedding Space Technique for Ranking Candidate Molecules for the Annotation of Untargeted Metabolomics Data.

Kalia A, Krishnan D, Hassoun S ArXiv. 2024; .

PMID: 39606728 PMC: 11601792.

Insights into predicting small molecule retention times in liquid chromatography using deep learning.

Liu Y, Yoshizawa A, Ling Y, Okuda S J Cheminform. 2024; 16(1):113.

PMID: 39375739 PMC: 11460055. DOI: 10.1186/s13321-024-00905-1.

Deep learning prediction of electrospray ionization tandem mass spectra of chemically derived molecules.

Chen B, Li H, Huang R, Tang Y, Li F Nat Commun. 2024; 15(1):8396.

PMID: 39333165 PMC: 11436754. DOI: 10.1038/s41467-024-52805-5.

References

Rosenstock H, Wallenstein M, Wahrhaftig A, EYRING H . Absolute Rate Theory for Isolated Systems and the Mass Spectra of Polyatomic Molecules. Proc Natl Acad Sci U S A. 1952; 38(8):667-78. PMC: 1063633. DOI: 10.1073/pnas.38.8.667. View

Hsieh Y, Korfmacher W . Increasing speed and throughput when using HPLC-MS/MS systems for drug metabolism and pharmacokinetic screening. Curr Drug Metab. 2006; 7(5):479-89. DOI: 10.2174/138920006777697963. View

Petrie S, Bohme D . Ions in space. Mass Spectrom Rev. 2006; 26(2):258-80. DOI: 10.1002/mas.20114. View

Rogers D, Hahn M . Extended-connectivity fingerprints. J Chem Inf Model. 2010; 50(5):742-54. DOI: 10.1021/ci100050t. View

Horai H, Arita M, Kanaya S, Nihei Y, Ikeda T, Suwa K . MassBank: a public repository for sharing mass spectral data for life sciences. J Mass Spectrom. 2010; 45(7):703-14. DOI: 10.1002/jms.1777. View

Stein S . Mass spectral reference libraries: an ever-expanding resource for chemical identification. Anal Chem. 2012; 84(17):7274-82. DOI: 10.1021/ac301205z. View

Grimme S . Towards first principles calculation of electron impact mass spectra of molecules. Angew Chem Int Ed Engl. 2013; 52(24):6306-12. DOI: 10.1002/anie.201300158. View

Stein S . Chemical substructure identification by mass spectral library searching. J Am Soc Mass Spectrom. 2013; 6(8):644-55. DOI: 10.1016/1044-0305(95)00291-K. View

Stein S, Scott D . Optimization and testing of mass spectral library search algorithms for compound identification. J Am Soc Mass Spectrom. 2013; 5(9):859-66. DOI: 10.1016/1044-0305(94)87009-8. View

10.

Eng J, McCormack A, Yates J . An approach to correlate tandem mass spectral data of peptides with amino acid sequences in a protein database. J Am Soc Mass Spectrom. 2013; 5(11):976-89. DOI: 10.1016/1044-0305(94)80016-2. View

11.

Duhrkop K, Shen H, Meusel M, Rousu J, Bocker S . Searching molecular structure databases with tandem mass spectra using CSI:FingerID. Proc Natl Acad Sci U S A. 2015; 112(41):12580-5. PMC: 4611636. DOI: 10.1073/pnas.1509788112. View

12.

Bauer C, Grimme S . How to Compute Electron Ionization Mass Spectra from First Principles. J Phys Chem A. 2016; 120(21):3755-66. DOI: 10.1021/acs.jpca.6b02907. View

13.

Allen F, Pon A, Greiner R, Wishart D . Computational Prediction of Electron Ionization Mass Spectra to Assist in GC/MS Compound Identification. Anal Chem. 2016; 88(15):7689-97. DOI: 10.1021/acs.analchem.6b01622. View

14.

Kearnes S, McCloskey K, Berndl M, Pande V, Riley P . Molecular graph convolutions: moving beyond fingerprints. J Comput Aided Mol Des. 2016; 30(8):595-608. PMC: 5028207. DOI: 10.1007/s10822-016-9938-8. View

15.

Viant M, Kurland I, Jones M, Dunn W . How close are we to complete annotation of metabolomes?. Curr Opin Chem Biol. 2017; 36:64-69. PMC: 5337156. DOI: 10.1016/j.cbpa.2017.01.001. View

16.

Zhou Z, Zare R . Personal Information from Latent Fingerprints Using Desorption Electrospray Ionization Mass Spectrometry and Machine Learning. Anal Chem. 2017; 89(2):1369-1372. DOI: 10.1021/acs.analchem.6b04498. View

17.

Tran N, Zhang X, Xin L, Shan B, Li M . De novo peptide sequencing by deep learning. Proc Natl Acad Sci U S A. 2017; 114(31):8247-8252. PMC: 5547637. DOI: 10.1073/pnas.1705691114. View

18.

Irikura K . Ab Initio Computation of Energy Deposition During Electron Ionization of Molecules. J Phys Chem A. 2017; 121(40):7751-7760. DOI: 10.1021/acs.jpca.7b07993. View

19.

Asgeirsson V, Bauer C, Grimme S . Quantum chemical calculation of electron ionization mass spectra for general organic and inorganic molecules. Chem Sci. 2017; 8(7):4879-4895. PMC: 5603848. DOI: 10.1039/c7sc00601b. View

20.

Moorthy A, Wallace W, Kearsley A, Tchekhovskoi D, Stein S . Combining Fragment-Ion and Neutral-Loss Matching during Mass Spectral Library Searching: A New General Purpose Algorithm Applicable to Illicit Drug Identification. Anal Chem. 2017; 89(24):13261-13268. PMC: 5841953. DOI: 10.1021/acs.analchem.7b03320. View