Your browser doesn't support javascript.
loading
Predicting the Ecological Quality Status of Marine Environments from eDNA Metabarcoding Data Using Supervised Machine Learning.
Cordier, Tristan; Esling, Philippe; Lejzerowicz, Franck; Visco, Joana; Ouadahi, Amine; Martins, Catarina; Cedhagen, Tomas; Pawlowski, Jan.
Afiliación
  • Cordier T; Department of Genetics and Evolution, University of Geneva , Boulevard d'Yvoy 4, CH 1205 Geneva, Switzerland.
  • Esling P; IRCAM, UMR 9912, Université Pierre et Marie Curie , 4 place Jussieu, 75005 Paris, France.
  • Lejzerowicz F; Department of Genetics and Evolution, University of Geneva , Boulevard d'Yvoy 4, CH 1205 Geneva, Switzerland.
  • Visco J; ID-Gene ecodiagnostics, Ltd. , chemin des Aulx 14, 1228 Plan-les-Ouates, Switzerland.
  • Ouadahi A; Department of Genetics and Evolution, University of Geneva , Boulevard d'Yvoy 4, CH 1205 Geneva, Switzerland.
  • Martins C; Marine Harvest ASA , Sandviksboder 77AB, Bergen, 5035 Bergen, Norway.
  • Cedhagen T; Department of Bioscience, Section of Aquatic Biology, University of Aarhus , Building 1135, Ole Worms allé 1, DK-8000 Aarhus, Denmark.
  • Pawlowski J; Department of Genetics and Evolution, University of Geneva , Boulevard d'Yvoy 4, CH 1205 Geneva, Switzerland.
Environ Sci Technol ; 51(16): 9118-9126, 2017 Aug 15.
Article en En | MEDLINE | ID: mdl-28665601
Monitoring biodiversity is essential to assess the impacts of increasing anthropogenic activities in marine environments. Traditionally, marine biomonitoring involves the sorting and morphological identification of benthic macro-invertebrates, which is time-consuming and taxonomic-expertise demanding. High-throughput amplicon sequencing of environmental DNA (eDNA metabarcoding) represents a promising alternative for benthic monitoring. However, an important fraction of eDNA sequences remains unassigned or belong to taxa of unknown ecology, which prevent their use for assessing the ecological quality status. Here, we show that supervised machine learning (SML) can be used to build robust predictive models for benthic monitoring, regardless of the taxonomic assignment of eDNA sequences. We tested three SML approaches to assess the environmental impact of marine aquaculture using benthic foraminifera eDNA, a group of unicellular eukaryotes known to be good bioindicators, as features to infer macro-invertebrates based biotic indices. We found similar ecological status as obtained from macro-invertebrates inventories. We argue that SML approaches could overcome and even bypass the cost and time-demanding morpho-taxonomic approaches in future biomonitoring.
Asunto(s)
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Foraminíferos / Código de Barras del ADN Taxonómico / Aprendizaje Automático Supervisado Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Environ Sci Technol Año: 2017 Tipo del documento: Article País de afiliación: Suiza Pais de publicación: Estados Unidos
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Foraminíferos / Código de Barras del ADN Taxonómico / Aprendizaje Automático Supervisado Tipo de estudio: Prognostic_studies / Risk_factors_studies Idioma: En Revista: Environ Sci Technol Año: 2017 Tipo del documento: Article País de afiliación: Suiza Pais de publicación: Estados Unidos