Filters








7 Hits in 2.1 sec

Spec2Vec: Improved mass spectral similarity scoring through learning of structural relationships [article]

Florian Huber, Lars Ridder, Simon Rogers, Justin JJ van der Hooft
2020 biorxiv/medrxiv   pre-print
Where Word2Vec learns relationships between words in sentences, Spec2Vec does so for mass fragments and neutral losses in MS/MS spectra.  ...  Although weaknesses in the relationship between common spectral similarity scores and the true structural similarities have been pointed out, little development of alternative scores has been undertaken  ...  We thank Mingxun Wang for creating the first GNPS-Spec2Vec implementation. Author Contributions  ... 
doi:10.1101/2020.08.11.245928 fatcat:4kyhntm7fnhcdjcx7fecyqjwvm

Spec2Vec: Improved mass spectral similarity scoring through learning of structural relationships

Florian Huber, Lars Ridder, Stefan Verhoeven, Jurriaan H Spaaks, Faruk Diblen, Simon Rogers, Justin J J van der Hooft
2021 PLoS Computational Biology  
Spec2Vec learns fragmental relationships within a large set of spectral data to derive abstract spectral embeddings that can be used to assess spectral similarities.  ...  Although weaknesses in the relationship between spectral similarity scores and the true structural similarities have been described, little development of alternative scores has been undertaken.  ...  We thank Mingxun Wang for creating the first GNPS-Spec2Vec implementation. Author Contributions  ... 
doi:10.1371/journal.pcbi.1008724 pmid:33591968 pmcid:PMC7909622 fatcat:4iugdivf3vgi3o6vcjpz5tatca

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

Florian Huber, Sven van der Burg, Justin J. J. van der Hooft, Lars Ridder
2021 Journal of Cheminformatics  
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  ...  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.  ...  The authors thank the GNPS community for contributing annotated spectra to the public GNPS spectral library.  ... 
doi:10.1186/s13321-021-00558-4 pmid:34715914 fatcat:n2vvvvmmirhydgmcplrd36w6lu

MS2DeepScore - a novel deep learning similarity measure for mass fragmentation spectrum comparisons [article]

Florian Huber, Sven van der Burg, Justin J.J. van der Hooft, Lars Ridder
2021 bioRxiv   pre-print
Using a cleaned dataset of >100,000 mass spectra of about 15,000 unique known compounds, MS2DeepScore learns to predict structural similarity scores for spectrum pairs with high accuracy.  ...  Added to the recently introduced unsupervised Spec2Vec metric, we believe that machine learning-supported mass spectral similarity metrics have great potential for a range of metabolomics data processing  ...  Acknowledgements This work was carried out on the Dutch national e-infrastructure with the support of SURF Cooperative.  ... 
doi:10.1101/2021.04.18.440324 fatcat:ig4rj63lvrefbhbs4267m55z4e

Advances in decomposing complex metabolite mixtures using substructure- and network-based computational metabolomics approaches

Mehdi A. Beniddir, Kyo Bin Kang, Grégory Genta-Jouve, Florian Huber, Simon Rogers, Justin J. J. van der Hooft
2021 Natural product reports (Print)  
Word2Vec, 44 called Spec2Vec. 45 Spec2Vec learns fragmental relationships within a large set of spectral data to derive abstract spectral embeddings that can be used to assess spectral similarities.  ...  library of >75 000 spectra with a cyclopeptide and lipid example. 45 We expect that Spec2Vec will trigger the emergence of more novel machine learning-based mass spectral similarity scores, both unsupervised  ... 
doi:10.1039/d1np00023c pmid:34821250 pmcid:PMC8597898 fatcat:hvbwacvx4fgmjnbop5jmy6nvee

Metabolomics-Guided Elucidation of Plant Abiotic Stress Responses in the 4IR Era: An Overview

Morena M. Tinte, Kekeletso H. Chele, Justin J. J. van der Hooft, Fidele Tugizimana
2021 Metabolites  
Specifically, we highlight technological advancements in (plant) metabolomics workflows and the use of machine learning and computational tools to decipher the dynamics in the chemical space that define  ...  The dawn of a new era characterized by the emergence of fourth industrial revolution (4IR) technologies has redefined the ideological boundaries of research and applications in plant sciences.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/metabo11070445 fatcat:grizhdxgnzcaxlcwr2octo2wdy

MEMO: Mass Spectrometry-based Sample Vectorization to Explore Chemodiverse Datasets [article]

Arnaud Gaudry, Florian Huber, Louis-Felix Nothias, Sylvian Cretton, Marcel Kaiser, Jean-Luc Wolfender, Pierre-Marie Allard
2021 bioRxiv   pre-print
Samples are usually analyzed by liquid chromatography coupled with fragmentation mass spectrometry to acquire informative mass spectral ensembles.  ...  MEMO demonstrated similar clustering performance as state-of-the-art metrics taking into account fragmentation spectra.  ...  JLW, LFN and PMA are thankful to the Swiss National Science Foundation for the funding of the project (SNF N°C RSII5_189921 / 1).  ... 
doi:10.1101/2021.12.24.474089 fatcat:nmo7rvnxorgatcrtvagyssshhy