We are analyzing https://link.springer.com/article/10.1186/s13321-021-00558-4.

Title:
MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra | Journal of Cheminformatics
Description:
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.
Website Age:
28 years and 1 months (reg. 1997-05-29).

Matching Content Categories {📚}

Science
Education
Virtual Reality

Content Management System {📝}

What CMS is link.springer.com built with?

Custom-built

No common CMS systems were detected on Link.springer.com, and no known web development framework was identified.

Traffic Estimate {📈}

What is the average monthly size of link.springer.com audience?

🌠 Phenomenal Traffic: 5M - 10M visitors per month

Based on our best estimate, this website will receive around 5,000,019 visitors per month in the current month.
However, some sources were not loaded, we suggest to reload the page to get complete results.

check SE Ranking
check Ahrefs
check Similarweb
check Ubersuggest
check Semrush

How Does Link.springer.com Make Money? {💸}

We don’t know how the website earns money.

Websites don't always need to be profitable; some serve as platforms for education or personal expression. Websites can serve multiple purposes. And this might be one of them. Link.springer.com has a secret sauce for making money, but we can't detect it yet.

Keywords {🔍}

spectra, scores, similarity, mass, tanimoto, structural, msdeepscore, data, spectral, pairs, article, score, fig, fingerprints, set, google, scholar, predictions, training, learning, spectrum, model, molecular, network, prediction, chemical, neural, high, deep, dropout, test, trained, large, peaks, predict, embeddings, based, msms, uncertainty, compound, measures, information, compounds, dataset, range, similarities, additional, bins, cas, library,

Topics {✒️}

van der hooft machine learning-based approaches full size image van der burg intel i7-8550u cpu dutch national e-infrastructure articles/preprint/npclassifier_a_deep_neural_network-based_structural_classification_tool_for_natural_products/12885494/1 /matchms/ms2deepscore/tree/main/notebooks fingerprint-based similarity score automated biology-driven metabolomics ligand-based virtual screening fingerprint-based similarity calculations chemically meaningful clustering tandem mass spectrometry article download pdf mass spectrometry cheminformatics cosine-based similarity scores monte-carlo dropout modus lc-ms/ms data analogue search t-sne plots based presented supervised approach related subjects machine learning approaches ms/ms fragmentation spectra open-source cheminformatics annotated ms/ms spectra resulting t-sne plot unlike alternative approaches applying monte-carlo dropout pair-wise tanimoto predictions mass spectrometry data monte-carlo dropout ensembles figure s11 t-sne ms/ms spectrum pairs link ms/ms spectra ms2deepscore-generated spectral embeddings deep learning network unlike modified cosine privacy choices/manage cookies alternative spectral libraries mass spectral similarities spectral similarity measures structurally related micropollutants spectral similarity score explore chemical relationships training-data spectrum representations tandem mass spectra additional spectral clustering low-intensity peak removal

Questions {❓}

Bajusz D, Rácz A, Héberger K (2015) Why is Tanimoto index an appropriate choice for fingerprint-based similarity calculations?
Bender A, Jenkins JL, Scheiber J, Sukuru SCK, Glick M, Davies JW (2009) How similar are similarity searching methods?

Schema {🗺️}

WebPage:
      mainEntity:
         headline:MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra
         description: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.
         datePublished:2021-10-29T00:00:00Z
         dateModified:2021-10-29T00:00:00Z
         pageStart:1
         pageEnd:14
         license:http://creativecommons.org/publicdomain/zero/1.0/
         sameAs:https://doi.org/10.1186/s13321-021-00558-4
         keywords:
            Mass spectrometry
            Metabolomics
            Spectral similarity measure
            Supervised machine learning
            Deep learning
            Computer Applications in Chemistry
            Documentation and Information in Chemistry
            Theoretical and Computational Chemistry
            Computational Biology/Bioinformatics
         image:
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig1_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig2_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig3_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig4_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig5_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig6_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig7_HTML.png
            https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig8_HTML.png
         isPartOf:
            name:Journal of Cheminformatics
            issn:
               1758-2946
            volumeNumber:13
            type:
               Periodical
               PublicationVolume
         publisher:
            name:Springer International Publishing
            logo:
               url:https://www.springernature.com/app-sn/public/images/logo-springernature.png
               type:ImageObject
            type:Organization
         author:
               name:Florian Huber
               url:http://orcid.org/0000-0002-3535-9406
               affiliation:
                     name:Netherlands eScience Center
                     address:
                        name:Netherlands eScience Center, Amsterdam, The Netherlands
                        type:PostalAddress
                     type:Organization
               email:[email protected]
               type:Person
               name:Sven van der Burg
               url:http://orcid.org/0000-0003-1250-6968
               affiliation:
                     name:Netherlands eScience Center
                     address:
                        name:Netherlands eScience Center, Amsterdam, The Netherlands
                        type:PostalAddress
                     type:Organization
               type:Person
               name:Justin J. J. van der Hooft
               url:http://orcid.org/0000-0002-9340-5511
               affiliation:
                     name:Wageningen University
                     address:
                        name:Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
                        type:PostalAddress
                     type:Organization
               type:Person
               name:Lars Ridder
               url:http://orcid.org/0000-0002-7635-9533
               affiliation:
                     name:Netherlands eScience Center
                     address:
                        name:Netherlands eScience Center, Amsterdam, The Netherlands
                        type:PostalAddress
                     type:Organization
               type:Person
         isAccessibleForFree:1
         type:ScholarlyArticle
      context:https://schema.org
ScholarlyArticle:
      headline:MS2DeepScore: a novel deep learning similarity measure to compare tandem mass spectra
      description: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.
      datePublished:2021-10-29T00:00:00Z
      dateModified:2021-10-29T00:00:00Z
      pageStart:1
      pageEnd:14
      license:http://creativecommons.org/publicdomain/zero/1.0/
      sameAs:https://doi.org/10.1186/s13321-021-00558-4
      keywords:
         Mass spectrometry
         Metabolomics
         Spectral similarity measure
         Supervised machine learning
         Deep learning
         Computer Applications in Chemistry
         Documentation and Information in Chemistry
         Theoretical and Computational Chemistry
         Computational Biology/Bioinformatics
      image:
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig1_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig2_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig3_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig4_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig5_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig6_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig7_HTML.png
         https://media.springernature.com/lw1200/springer-static/image/art%3A10.1186%2Fs13321-021-00558-4/MediaObjects/13321_2021_558_Fig8_HTML.png
      isPartOf:
         name:Journal of Cheminformatics
         issn:
            1758-2946
         volumeNumber:13
         type:
            Periodical
            PublicationVolume
      publisher:
         name:Springer International Publishing
         logo:
            url:https://www.springernature.com/app-sn/public/images/logo-springernature.png
            type:ImageObject
         type:Organization
      author:
            name:Florian Huber
            url:http://orcid.org/0000-0002-3535-9406
            affiliation:
                  name:Netherlands eScience Center
                  address:
                     name:Netherlands eScience Center, Amsterdam, The Netherlands
                     type:PostalAddress
                  type:Organization
            email:[email protected]
            type:Person
            name:Sven van der Burg
            url:http://orcid.org/0000-0003-1250-6968
            affiliation:
                  name:Netherlands eScience Center
                  address:
                     name:Netherlands eScience Center, Amsterdam, The Netherlands
                     type:PostalAddress
                  type:Organization
            type:Person
            name:Justin J. J. van der Hooft
            url:http://orcid.org/0000-0002-9340-5511
            affiliation:
                  name:Wageningen University
                  address:
                     name:Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
                     type:PostalAddress
                  type:Organization
            type:Person
            name:Lars Ridder
            url:http://orcid.org/0000-0002-7635-9533
            affiliation:
                  name:Netherlands eScience Center
                  address:
                     name:Netherlands eScience Center, Amsterdam, The Netherlands
                     type:PostalAddress
                  type:Organization
            type:Person
      isAccessibleForFree:1
["Periodical","PublicationVolume"]:
      name:Journal of Cheminformatics
      issn:
         1758-2946
      volumeNumber:13
Organization:
      name:Springer International Publishing
      logo:
         url:https://www.springernature.com/app-sn/public/images/logo-springernature.png
         type:ImageObject
      name:Netherlands eScience Center
      address:
         name:Netherlands eScience Center, Amsterdam, The Netherlands
         type:PostalAddress
      name:Netherlands eScience Center
      address:
         name:Netherlands eScience Center, Amsterdam, The Netherlands
         type:PostalAddress
      name:Wageningen University
      address:
         name:Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
         type:PostalAddress
      name:Netherlands eScience Center
      address:
         name:Netherlands eScience Center, Amsterdam, The Netherlands
         type:PostalAddress
ImageObject:
      url:https://www.springernature.com/app-sn/public/images/logo-springernature.png
Person:
      name:Florian Huber
      url:http://orcid.org/0000-0002-3535-9406
      affiliation:
            name:Netherlands eScience Center
            address:
               name:Netherlands eScience Center, Amsterdam, The Netherlands
               type:PostalAddress
            type:Organization
      email:[email protected]
      name:Sven van der Burg
      url:http://orcid.org/0000-0003-1250-6968
      affiliation:
            name:Netherlands eScience Center
            address:
               name:Netherlands eScience Center, Amsterdam, The Netherlands
               type:PostalAddress
            type:Organization
      name:Justin J. J. van der Hooft
      url:http://orcid.org/0000-0002-9340-5511
      affiliation:
            name:Wageningen University
            address:
               name:Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
               type:PostalAddress
            type:Organization
      name:Lars Ridder
      url:http://orcid.org/0000-0002-7635-9533
      affiliation:
            name:Netherlands eScience Center
            address:
               name:Netherlands eScience Center, Amsterdam, The Netherlands
               type:PostalAddress
            type:Organization
PostalAddress:
      name:Netherlands eScience Center, Amsterdam, The Netherlands
      name:Netherlands eScience Center, Amsterdam, The Netherlands
      name:Bioinformatics Group, Wageningen University, Wageningen, The Netherlands
      name:Netherlands eScience Center, Amsterdam, The Netherlands

External Links {🔗}(121)

Analytics and Tracking {📊}

Google Tag Manager

Libraries {📚}

Clipboard.js
Prism.js

CDN Services {📦}

Crossref

4.68s.

LINK . SPRINGER . COM {}