Predicting the Ecological Quality Status of Marine Environments from eDNA Metabarcoding Data Using Supervised Machine Learning.

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.

Environmental Monitoring: Inferring the Diatom Index from Next-Generation Sequencing Data.

Diatoms are widely used as bioindicators for the assessment of water quality in rivers and streams. Classically, the diatom biotic indices are based on the relative abundance of morphologically identified species weighted by their autoecological value. Obtaining such indices is time-consuming, costly, and requires excellent taxonomic expertise, which is not always available. Here we tested the possibility to overcome these limitations using a next-generation sequencing (NGS) approach to identify and quantify diatoms found in environmental DNA and RNA samples. We analyzed 27 river sites in the Geneva area (Switzerland), in order to compare the values of the Swiss Diatom Index (DI-CH) computed either by microscopic quantification of diatom species or directly from NGS data. Despite gaps in the reference database and variations in relative abundance of analyzed species, the diatom index shows a significant correlation between morphological and molecular data indicating similar biological quality status for the majority of sites. This proof-of-concept study demonstrates the potential of the NGS approach for identification and quantification of diatoms in environmental samples, opening new avenues toward the routine application of genetic tools for bioassessment and biomonitoring of aquatic ecosystems.