EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Zero-shot deep learning for the annotation of unknown eDNA sequences using co-occurrences and phylogenetic embeddings

Steven Stalder, Théophile Sanchez, Michele Volpi iD, Stéphanie Manel, David Mouillot, Arnaud Auber, Morgane Bruno, Virginie Marques, Camille Albouy iD, Loïc Pellissier iD

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1013776 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Steven Stalder und 9 weiteren Autor:innen. Beteiligte Einrichtung: Swiss Data Science Center, ETH Zürich and EPFL, Zürich, Switzerland. Hauptthemen laut MEDLINE: Deep Learning, Phylogeny, DNA, Environmental, DNA Barcoding, Taxonomic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 68 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Swiss Data Science Center (SDSC), Swiss National Supercomputing Centre (CSCS), FishPredict.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The advent of environmental DNA (eDNA) metabarcoding marks a transformative era in large-scale biodiversity monitoring. However, the analysis of eDNA datasets is limited by incomplete reference databases and the increasing volume of data requiring processing from raw sequences to annotated taxonomic lists. To curate taxonomic lists from eDNA analysis, geographic constraints are used by expert in post-analysis, which may introduce potential biases in assignments. Instead of relying on expert intervention, a combination of taxonomic and geographic co-occurrences could be directly integrated into machine learning to automatize and improve taxonomic annotation. Here, we introduce a deep learning approach applied to the taxonomic assignment of eDNA sequences, which leverages a species reference database, species co-occurrence data, and a phylogeny to enhance annotation directly from raw sequences. The phylogeny provides the structure to the network’s embedding space in which DNA sequences are placed utilizing an artificial neural network (ANN). We train an additional ANN from the phylogenetic embedding and co-occurrence species data to learn coherent species combinations from the whole collection of eDNA sequences, as opposed to single sequences only. When applied directly to the raw sequences, this method correctly predicts unseen species (i.e., those not contained in the reference database), out of more than 31,000 possibilities, in about 24% of the tested cases by relying on phylogenetic embeddings and geographic modulation. The trained ANNs discern species relationships accurately from the raw data, which facilitates the process of associating sequences with taxa—even those absent from reference databases. When we use real eDNA samples, our predictions mostly agree with those from a traditional bioinformatic pipeline, highlighting the potential of our method for the annotation of the increasing number of eDNA sequences.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPhylogenyDNA, EnvironmentalDNA Barcoding, TaxonomicMolecular Sequence AnnotationNeural Networks, ComputerComputational BiologyBiodiversity

Substanzen

DNA, Environmental

Autor:innen und Institutionen

  • Swiss Data Science Center, ETH Zürich and EPFL, Zürich, Switzerland.
  • Ecosystems and Landscape Evolution, Swiss Federal Institute for Forest, Snow and Landscape Research (WSL), Birmensdorf, Switzerland.
  • Ecosystems and Landscape Evolution, Department of Environmental Systems Science, ETH Zürich, Zürich, Switzerland.
  • CEFE, University of Montpellier, CNRS, EPHE-PSL University, IRD, Montpellier, France.
  • Institut Universitaire de France, Paris, France.
  • MARBEC, University of Montpellier, CNRS, Ifremer, IRD, Montpellier, France.

ORCID-Profile: Michele Volpi, Camille Albouy, Loïc Pellissier

Förderung

  • Swiss Data Science Center (SDSC)
  • Swiss National Supercomputing Centre (CSCS)
  • FishPredict
  • ANR/SNF
  • CSCS
  • ANR FishPredict

Zitieren

APA

Stalder, S., Sanchez, T., Volpi, M., Manel, S., Mouillot, D., Auber, A., Bruno, M., Marques, V., Albouy, C., & Pellissier, L. (2025). Zero-shot deep learning for the annotation of unknown eDNA sequences using co-occurrences and phylogenetic embeddings. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1013776

Vancouver

Stalder S, Sanchez T, Volpi M, Manel S, Mouillot D, Auber A, et al. Zero-shot deep learning for the annotation of unknown eDNA sequences using co-occurrences and phylogenetic embeddings. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1013776

BibTeX
@article{Stalder2025,
  author = {Stalder, Steven and Sanchez, Théophile and Volpi, Michele and Manel, Stéphanie and Mouillot, David and Auber, Arnaud and Bruno, Morgane and Marques, Virginie and Albouy, Camille and Pellissier, Loïc},
  title = {Zero-shot deep learning for the annotation of unknown eDNA sequences using co-occurrences and phylogenetic embeddings},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1013776}
}
Kostenlos starten →