Titre :

Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification

Auteur(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]

Titre de la revue :

Nature Communications

Nom court de la revue :

Nat Commun

Numéro :

11

Pagination :

5595

Éditeur :

Springer Nature

Date de publication :

2020-11-05

ISSN :

2041-1723

Discipline(s) HAL :

Sciences du Vivant [q-bio]
Informatique [cs]

Résumé en anglais : [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 ...
Lire la suite >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.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Établissement(s) :

INSERM
Université de Lille

Collections :

• Protéomique, Réponse Inflammatoire, Spectrométrie de Masse (PRISM) - U1192

Date de dépôt :

2022-06-15T13:58:02Z
2023-03-07T13:44:34Z