A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning

Computational methods are playing an increasingly important role as a complement to conventional data evaluation methods in analytical chemistry, and particularly mass spectrometry. Computational mass spectrometry (CompMS) is the application of computational methods on mass spectrometry data. Herein...

Full description

Saved in:
Bibliographic Details
Main Author: Michael A. Stravs
Format: Article
Language:deu
Published: Swiss Chemical Society 2024-08-01
Series:CHIMIA
Subjects:
Online Access:https://www.chimia.ch/chimia/article/view/7344
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849310918673956864
author Michael A. Stravs
author_facet Michael A. Stravs
author_sort Michael A. Stravs
collection DOAJ
description Computational methods are playing an increasingly important role as a complement to conventional data evaluation methods in analytical chemistry, and particularly mass spectrometry. Computational mass spectrometry (CompMS) is the application of computational methods on mass spectrometry data. Herein, advances in CompMS for small molecule chemistry are discussed in the areas of spectral libraries, spectrum prediction, and tentative structure identification (annotation): Automatic spectrum curation is facilitating the expansion of openly available spectral libraries, a crucial resource both for compound annotation directly and as a resource for machine learning algorithms. Spectrum prediction and molecular fingerprint prediction have emerged as two key approaches to compound annotation. For both, multiple methods based on classical machine learning and deep learning have been developed. Driven by advances in deep learning-based generative chemistry, de novo structure generation from fragment spectra is emerging as a new field of research. This review highlights key publications in these fields, including our approaches RMassBank (automatic spectrum curation) and MSNovelist (de novo structure generation).
format Article
id doaj-art-e59a2b91bb9746ad90c3283c2a78a5c9
institution Kabale University
issn 0009-4293
2673-2424
language deu
publishDate 2024-08-01
publisher Swiss Chemical Society
record_format Article
series CHIMIA
spelling doaj-art-e59a2b91bb9746ad90c3283c2a78a5c92025-08-20T03:53:33ZdeuSwiss Chemical SocietyCHIMIA0009-42932673-24242024-08-01787-810.2533/chimia.2024.525A Decade of Computational Mass Spectrometry from Reference Spectra to Deep LearningMichael A. Stravs0Eawag, Ueberlandstrasse 133, CH-8600 DübendorfComputational methods are playing an increasingly important role as a complement to conventional data evaluation methods in analytical chemistry, and particularly mass spectrometry. Computational mass spectrometry (CompMS) is the application of computational methods on mass spectrometry data. Herein, advances in CompMS for small molecule chemistry are discussed in the areas of spectral libraries, spectrum prediction, and tentative structure identification (annotation): Automatic spectrum curation is facilitating the expansion of openly available spectral libraries, a crucial resource both for compound annotation directly and as a resource for machine learning algorithms. Spectrum prediction and molecular fingerprint prediction have emerged as two key approaches to compound annotation. For both, multiple methods based on classical machine learning and deep learning have been developed. Driven by advances in deep learning-based generative chemistry, de novo structure generation from fragment spectra is emerging as a new field of research. This review highlights key publications in these fields, including our approaches RMassBank (automatic spectrum curation) and MSNovelist (de novo structure generation). https://www.chimia.ch/chimia/article/view/7344Machine LearningMass spectrometrySmall molecules
spellingShingle Michael A. Stravs
A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
CHIMIA
Machine Learning
Mass spectrometry
Small molecules
title A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
title_full A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
title_fullStr A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
title_full_unstemmed A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
title_short A Decade of Computational Mass Spectrometry from Reference Spectra to Deep Learning
title_sort decade of computational mass spectrometry from reference spectra to deep learning
topic Machine Learning
Mass spectrometry
Small molecules
url https://www.chimia.ch/chimia/article/view/7344
work_keys_str_mv AT michaelastravs adecadeofcomputationalmassspectrometryfromreferencespectratodeeplearning
AT michaelastravs decadeofcomputationalmassspectrometryfromreferencespectratodeeplearning