Idioma:

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

Huber, Florian ; van der Burg, Sven ; van der Hooft, Justin J. J. ; Ridder, Lars

Journal of cheminformatics, 2021-10, Vol.13 (1), p.84-84, Article 84 [Periódico revisado por pares]

Cham: Springer International Publishing

Texto completo disponível

Citações Citado por

Enviar para

Título:
MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra
Autor: Huber, Florian ; van der Burg, Sven ; van der Hooft, Justin J. J. ; Ridder, Lars
Assuntos: Chemical compounds ; Chemistry ; Chemistry and Materials Science ; Computational Biology/Bioinformatics ; Computer Applications in Chemistry ; Data processing ; Datasets ; Deep learning ; Documentation and Information in Chemistry ; Fragmentation ; Learning algorithms ; Machine learning ; Mass spectra ; Mass spectrometry ; Mass spectroscopy ; Metabolomics ; Methodology ; Neural networks ; Predictions ; Root-mean-square errors ; Similarity ; Similarity measures ; Spectral similarity measure ; Supervised machine learning ; Theoretical and Computational Chemistry ; Uncertainty
É parte de: Journal of cheminformatics, 2021-10, Vol.13 (1), p.84-84, Article 84
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: Mass spectrometry data is one of the key sources of information in many workflows in medicine and across the life sciences. Mass fragmentation spectra are generally considered to be characteristic signatures of the chemical compound they originate from, yet the chemical structure itself usually cannot be easily deduced from the spectrum. Often, spectral similarity measures are used as a proxy for structural similarity but this approach is strongly limited by a generally poor correlation between both metrics. Here, we propose MS2DeepScore: a novel Siamese neural network to predict the structural similarity between two chemical structures solely based on their MS/MS fragmentation spectra. Using a cleaned dataset of > 100,000 mass spectra of about 15,000 unique known compounds, we trained MS2DeepScore to predict structural similarity scores for spectrum pairs with high accuracy. In addition, sampling different model varieties through Monte-Carlo Dropout is used to further improve the predictions and assess the model’s prediction uncertainty. On 3600 spectra of 500 unseen compounds, MS2DeepScore is able to identify highly-reliable structural matches and to predict Tanimoto scores for pairs of molecules based on their fragment spectra with a root mean squared error of about 0.15. Furthermore, the prediction uncertainty estimate can be used to select a subset of predictions with a root mean squared error of about 0.1. Furthermore, we demonstrate that MS2DeepScore outperforms classical spectral similarity measures in retrieving chemically related compound pairs from large mass spectral datasets, thereby illustrating its potential for spectral library matching. Finally, MS2DeepScore can also be used to create chemically meaningful mass spectral embeddings that could be used to cluster large numbers of spectra. Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity measures have great potential for a range of metabolomics data processing pipelines.
Editor: Cham: Springer International Publishing
Idioma: Inglês

Links

View this record in MEDLINE/PubMed

Voltar para lista de resultados

Realização: Logos de Redes Sociais:

MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra

Huber, Florian ; van der Burg, Sven ; van der Hooft, Justin J. J. ; Ridder, Lars

Cham: Springer International Publishing

Buscando em bases de dados remotas. Favor aguardar.