Cumulative learning enables convolutional ...
Document type :
Article dans une revue scientifique: Article original
PMID :
Permalink :
Title :
Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification
Author(s) :
Seddiki, Khawla [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
CHU de Québec–Université Laval
Saudemont, Philippe [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Precioso, Frederic [Auteur]
Ogrinc, Nina [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Wisztorski, Maxence [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Salzet, Michel [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
FOURNIER, Isabelle [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Droit, Arnaud [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
CHU de Québec–Université Laval
Saudemont, Philippe [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Precioso, Frederic [Auteur]
Ogrinc, Nina [Auteur]
Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Wisztorski, Maxence [Auteur]

Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Salzet, Michel [Auteur]

Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
FOURNIER, Isabelle [Auteur]

Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192
Droit, Arnaud [Auteur]
Journal title :
Nature Communications
Abbreviated title :
Nat Commun
Volume number :
11
Pages :
5595
Publisher :
Springer Nature
Publication date :
2020-11-05
ISSN :
2041-1723
HAL domain(s) :
Sciences du Vivant [q-bio]
Informatique [cs]
Informatique [cs]
English abstract : [en]
Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have ...
Show more >Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have been investigated but these models require time-consuming preprocessing steps to remove artifacts, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn representations from raw data. However, their effectiveness decreases when the number of available training samples is small, which is a common situation in medicine. In this work, we investigate transfer learning on 1D-CNNs, then we develop a cumulative learning method when transfer learning is not powerful enough. We propose to train the same model through several classification tasks over various small datasets to accumulate knowledge in the resulting representation. By using rat brain as the initial training dataset, a cumulative learning approach can have a classification accuracy exceeding 98% for 1D clinical MS-data. We show the use of cumulative learning using datasets generated in different biological contexts, on different organisms, and acquired by different instruments. Here we show a promising strategy for improving MS data classification accuracy when only small numbers of samples are available.Show less >
Show more >Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have been investigated but these models require time-consuming preprocessing steps to remove artifacts, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn representations from raw data. However, their effectiveness decreases when the number of available training samples is small, which is a common situation in medicine. In this work, we investigate transfer learning on 1D-CNNs, then we develop a cumulative learning method when transfer learning is not powerful enough. We propose to train the same model through several classification tasks over various small datasets to accumulate knowledge in the resulting representation. By using rat brain as the initial training dataset, a cumulative learning approach can have a classification accuracy exceeding 98% for 1D clinical MS-data. We show the use of cumulative learning using datasets generated in different biological contexts, on different organisms, and acquired by different instruments. Here we show a promising strategy for improving MS data classification accuracy when only small numbers of samples are available.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
Administrative institution(s) :
INSERM
Université de Lille
Université de Lille
Submission date :
2022-06-15T13:58:02Z
2023-03-07T13:44:34Z
2023-03-07T13:44:34Z
Files
- 2020-11-05-s41467-020-19354-z.pdf
- Version éditeur
- Open access
- Access the document