Cargando…
In Search of Disentanglement in Tandem Mass Spectrometry Datasets
Generative modeling and representation learning of tandem mass spectrometry data aim to learn an interpretable and instrument-agnostic digital representation of metabolites directly from MS/MS spectra. Interpretable and instrument-agnostic digital representations would facilitate comparisons of MS/M...
Autores principales: | , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10526774/ https://www.ncbi.nlm.nih.gov/pubmed/37759743 http://dx.doi.org/10.3390/biom13091343 |
_version_ | 1785111062892249088 |
---|---|
author | Abram, Krzysztof Jan McCloskey, Douglas |
author_facet | Abram, Krzysztof Jan McCloskey, Douglas |
author_sort | Abram, Krzysztof Jan |
collection | PubMed |
description | Generative modeling and representation learning of tandem mass spectrometry data aim to learn an interpretable and instrument-agnostic digital representation of metabolites directly from MS/MS spectra. Interpretable and instrument-agnostic digital representations would facilitate comparisons of MS/MS spectra between instrument vendors and enable better and more accurate queries of large MS/MS spectra databases for metabolite identification. In this study, we apply generative modeling and representation learning using variational autoencoders to understand the extent to which tandem mass spectra can be disentangled into their factors of generation (e.g., collision energy, ionization mode, instrument type, etc.) with minimal prior knowledge of the factors. We find that variational autoencoders can disentangle tandem mass spectra data with the proper choice of hyperparameters into meaningful latent representations aligned with known factors of variation. We develop a two-step approach to facilitate the selection of models that are disentangled, which could be applied to other complex and high-dimensional data sets. |
format | Online Article Text |
id | pubmed-10526774 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-105267742023-09-28 In Search of Disentanglement in Tandem Mass Spectrometry Datasets Abram, Krzysztof Jan McCloskey, Douglas Biomolecules Article Generative modeling and representation learning of tandem mass spectrometry data aim to learn an interpretable and instrument-agnostic digital representation of metabolites directly from MS/MS spectra. Interpretable and instrument-agnostic digital representations would facilitate comparisons of MS/MS spectra between instrument vendors and enable better and more accurate queries of large MS/MS spectra databases for metabolite identification. In this study, we apply generative modeling and representation learning using variational autoencoders to understand the extent to which tandem mass spectra can be disentangled into their factors of generation (e.g., collision energy, ionization mode, instrument type, etc.) with minimal prior knowledge of the factors. We find that variational autoencoders can disentangle tandem mass spectra data with the proper choice of hyperparameters into meaningful latent representations aligned with known factors of variation. We develop a two-step approach to facilitate the selection of models that are disentangled, which could be applied to other complex and high-dimensional data sets. MDPI 2023-09-04 /pmc/articles/PMC10526774/ /pubmed/37759743 http://dx.doi.org/10.3390/biom13091343 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Abram, Krzysztof Jan McCloskey, Douglas In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title | In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title_full | In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title_fullStr | In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title_full_unstemmed | In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title_short | In Search of Disentanglement in Tandem Mass Spectrometry Datasets |
title_sort | in search of disentanglement in tandem mass spectrometry datasets |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10526774/ https://www.ncbi.nlm.nih.gov/pubmed/37759743 http://dx.doi.org/10.3390/biom13091343 |
work_keys_str_mv | AT abramkrzysztofjan insearchofdisentanglementintandemmassspectrometrydatasets AT mccloskeydouglas insearchofdisentanglementintandemmassspectrometrydatasets |