Item request has been placed! ×
Item request cannot be made. ×
loading  Processing Request

New deep learning-based methods for visualizing ecosystem properties using environmental DNA metabarcoding data

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
  • Additional Information
    • Contributors:
      Centre d’Ecologie Fonctionnelle et Evolutive (CEFE); Université Paul-Valéry - Montpellier 3 (UPVM)-École Pratique des Hautes Études (EPHE); Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche pour le Développement (IRD France-Sud )-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Institut Agro Montpellier; Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Université de Montpellier (UM); Department of Environmental Systems Science ETH Zürich (D-USYS); Eidgenössische Technische Hochschule - Swiss Federal Institute of Technology Zürich (ETH Zürich); Swiss Federal Institute for Forest, Snow and Landscape Research WSL; Laboratoire d'Ecologie Alpine (LECA ); Université Savoie Mont Blanc (USMB Université de Savoie Université de Chambéry )-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA); MARine Biodiversity Exploitation and Conservation - MARBEC (UMR MARBEC ); Institut de Recherche pour le Développement (IRD)-Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM); Dynamique et durabilité des écosystèmes : de la source à l’océan (DECOD); Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro)-Institut Agro Rennes Angers; Institut national d'enseignement supérieur pour l'agriculture, l'alimentation et l'environnement (Institut Agro); SPYGEN Le Bourget-du-Lac; Departement Erdwissenschaften ETH Zürich (D-ERDW); ANR-21-AAFI-0001,FISH-PREDICT,Prédire la biodiversité des poissons récifaux(2021); ANR-20-LCV1-0008,Diag-ADNe,Diagnostic ADN environnemental des Milieux Marins(2020)
    • Publication Information:
      HAL CCSD
      Wiley/Blackwell
    • Publication Date:
      2023
    • Collection:
      EPHE (Ecole pratique des hautes études, Paris): HAL
    • Abstract:
      WOS:001067956300001 ; International audience ; Environmental DNA (eDNA) metabarcoding provides an efficient approach for documenting biodiversity patterns in marine and terrestrial ecosystems. The complexity of these data prevents current methods from extracting and analyzing all the relevant ecological information they contain, and new methods may provide better dimensionality reduction and clustering. Here we present two new deep learning-based methods that combine different types of neural networks (NNs) to ordinate eDNA samples and visualize ecosystem properties in a two-dimensional space: the first is based on variational autoencoders and the second on deep metric learning. The strength of our new methods lies in the combination of two inputs: the number of sequences found for each molecular operational taxonomic unit (MOTU) detected and their corresponding nucleotide sequence. Using three different datasets, we show that our methods accurately represent several biodiversity indicators in a two-dimensional latent space: MOTU richness per sample, sequence α-diversity per sample, Jaccard's and sequence β-diversity between samples. We show that our nonlinear methods are better at extracting features from eDNA datasets while avoiding the major biases associated with eDNA. Our methods outperform traditional dimension reduction methods such as Principal Component Analysis, t-distributed Stochastic Neighbour Embedding, Nonmetric Multidimensional Scaling and Uniform Manifold Approximation and Projection for dimension reduction. Our results suggest that NNs provide a more efficient way of extracting structure from eDNA metabarcoding data, thereby improving their ecological interpretation and thus biodiversity monitoring.
    • Relation:
      hal-04313526; https://hal.umontpellier.fr/hal-04313526; WOS: 001067956300001
    • Accession Number:
      10.1111/1755-0998.13861
    • Online Access:
      https://doi.org/10.1111/1755-0998.13861
      https://hal.umontpellier.fr/hal-04313526
    • Rights:
      http://creativecommons.org/licenses/by-nd/
    • Accession Number:
      edsbas.70B81464