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

Abstract

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.

Boosting DNA metabarcoding for biomonitoring with phylogenetic estimation of operational taxonomic units’ ecological profiles

“…In this study, we have introduced a new method based on phylogeny to compute biotic indices from DNA reads generated by metabarcoding workflows. The phylogenetic method is in line with the recent developments in taxonomy‐free approaches for bioassessment which aim to bypass taxonomic reference libraries in order to maximize the genetic information taken into account (e.g., Apothéloz‐Perret‐Gentil et al., ; Cordier et al., ). The phylogenetic OTU‐PITI approach has sound theoretical grounds, because the imputation of missing values is based on the phylogenetic signal (i.e., the nonindependence among species trait values because of their phylogenetic relatedness) which is a direct consequence of Darwin's principle of descent with modification (Felsenstein, ).…”

“…To circumvent this problem, it has been suggested to skip the conversion from DNA reads to taxonomic entities and work directly on molecular data (Keck, Vasselon, Tapolczai, Rimet, & Bouchez, ). In this respect, different strategies have been considered, including OTU‐based indices (Apothéloz‐Perret‐Gentil et al., ) or the use of supervised machine‐learning algorithms to process genetic inventories (Cordier et al., ). Alternatively, Keck, Rimet, Bouchez, and Franc (), Keck, Rimet, Franc, and Bouchez (), and Keck et al.…”

Responses of foraminifera communities to aquaculture‐derived organic enrichment as revealed by environmental DNA metabarcoding

“…Although eDNA metabarcoding has been shown to be a powerful and efficient alternative tool to monitor benthic impacts of fish farms, its application for routine regulatory benthic impact monitoring is still hotly debated (Cordier et al., , ; Forster et al., ; Keeley, Wood, & Pochon, ; Pawlowski et al., , ; Pochon et al., ; Stoeck, Kochems, Forster, Lejzerowicz, & Pawlowski, ; Stoeck, Frühe et al., ). In the countries where sediments are assessed using biological indices that require benthic faunal characterization, eDNA metabarcoding can replace traditional morpho‐taxonomy to calculate biological indices once there are enough reference sequences for benthic species in public databases and the ecological value of the targeted group of species is known (Pawlowski et al., , ).…”

“…Populating reference databases is slow and labour intensive, and does not get much attention. An alternative taxonomy‐free approach proposed to overcome this limitation is supervised machine learning, which can predict the ecological quality of sediments based on eDNA metabarcoding data of unclassified sediments and a training dataset (Cordier et al., , ). For countries where routine benthic monitoring relies heavily on geochemistry data (Cranford, Brager, & Wong, ), eDNA metabarcoding could significantly enhance existing approaches by providing a rapid and accurate means of generating biological data from sediments.…”

BBI: an R package for the computation of Benthic Biotic Indices from composition data

“…The composition data inferred by the molecular approach is being used in the same way as morphological data to compute BBI, by considering reads abundance as a proxy for species abundance (sensu gAMBI, see Aylagas et al 2014), although the direct comparison is not straightforward, because the abundance of reads is not necessarily reflecting accurately the abundance of the species (Elbrecht and Leese 2015, Vivien et al 2015, Dowle et al 2016. Such discrepancies led to the development of correcting factors, using the cell biovolume in the case of diatoms, to lower the effect of such quantification bias (Vasselon et al 2018) or to the use of machine learning algorithms to bypass the taxonomic assignment step when using metabarcoding data (Cordier et al 2017).…”