<scp>ORDNA</scp> : Deep‐learning‐based ordination for raw environmental <scp>DNA</scp> samples

Abstract Environmental DNA (eDNA) metabarcoding has revolutionized biodiversity monitoring, offering non‐invasive tools to assess ecosystem health. The complexity of eDNA metabarcoding data poses major challenges for conventional ordination methods in understanding assemblage similarities and assessing biodiversity patterns. Here, we introduce ORDNA (ORDination via Deep Neural Algorithm), a new deep learning method tailored for eDNA sample ordination. Leveraging artificial neural networks, ORDNA processes raw sequences from eDNA samples directly, bypassing potentially biased and cumbersome expert‐based bioinformatic steps. The method is trained with a contrastive self‐supervised learning approach, the triplet loss, to derive a two‐dimensional representation of eDNA samples based on their read composition. We apply ORDNA to four distinct eDNA datasets, demonstrating its robustness and superiority over traditional ordination techniques in capturing and visualizing ecological patterns. Our results underline the potential of deep learning in advancing eDNA analysis, with ORDNA serving as a promising tool for more accurate and efficient biodiversity assessments.

Authors

Institutions

Publication Details

Journal
Methods in Ecology and Evolution
Published
2025-04-03
DOI
https://doi.org/10.1111/2041-210x.70033
Primary Topic
Environmental DNA in Biodiversity Studies
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

ORDNA : Deep‐learning‐based ordination for raw environmental DNA samples

Adrien Mestrot, Sébastien Brosse, Romane Rozanski, Camille P. Albouy et al.
Methods in Ecology and Evolution
Environmental DNA in Biodiversity Studies
article

ORDNA : Deep‐learning‐based ordination for raw environmental DNA samples

Adrien Mestrot, Sébastien Brosse, Romane Rozanski, Camille P. Albouy, Flurin Leugger, Shuo Zong, Laura Medici, Théophile Sanchez, Letizia Lamperti, Michele Volpi, Steven Stalder, Aline Frossard, Loïc Pellissier, Stéphanie Manel, Fernanda Kuhn, Xingguo Han
article en

Abstract

Abstract Environmental DNA (eDNA) metabarcoding has revolutionized biodiversity monitoring, offering non‐invasive tools to assess ecosystem health. The complexity of eDNA metabarcoding data poses major challenges for conventional ordination methods in understanding assemblage similarities and assessing biodiversity patterns. Here, we introduce ORDNA (ORDination via Deep Neural Algorithm), a new deep learning method tailored for eDNA sample ordination. Leveraging artificial neural networks, ORDNA processes raw sequences from eDNA samples directly, bypassing potentially biased and cumbersome expert‐based bioinformatic steps. The method is trained with a contrastive self‐supervised learning approach, the triplet loss, to derive a two‐dimensional representation of eDNA samples based on their read composition. We apply ORDNA to four distinct eDNA datasets, demonstrating its robustness and superiority over traditional ordination techniques in capturing and visualizing ecological patterns. Our results underline the potential of deep learning in advancing eDNA analysis, with ORDNA serving as a promising tool for more accurate and efficient biodiversity assessments.

Methods in Ecology and EvolutionVol. 17(2)
University of Bern (CH), Centre National de la Recherche Scientifique (FR), Oeschger Centre for Climate Change Research (CH), Université Toulouse III - Paul Sabatier (FR), École Pratique des Hautes Études (FR), Université Fédérale de Toulouse Midi-Pyrénées (FR), Institut Universitaire de France (FR), Université de Montpellier (FR), Université Paris Sciences et Lettres (FR), Swiss Federal Institute for Forest, Snow and Landscape Research (CH), ETH Zurich (CH), Centre d'Écologie Fonctionnelle et Évolutive (FR), Swiss Data Science Center (CH), Evolution et Diversité Biologique (FR), Institut de Recherche pour le Développement (FR)
San Diego Supercomputer Center, Agence Nationale de la Recherche, Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
Life in Land
Openalex Percentile: Top 93%
Environmental DNA in Biodiversity Studies
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.