Fast processing of environmental DNA metabarcoding sequence data using convolutional neural networks

1The intensification of anthropogenic pressures have increased consequences on biodiversity and ultimately on the functioning of ecosystems. To monitor and better understand biodiversity responses to environmental changes using standardized and reproducible methods, novel high-throughput DNA sequencing is becoming a major tool. Indeed, organisms shed DNA traces in their environment and this "environmental DNA" (eDNA) can be collected and sequenced using eDNA metabarcoding. The processing of large volumes of eDNA metabarcoding data remains challenging, especially its transformation to relevant taxonomic lists that can be interpreted by experts. Speed and accuracy are two major bottlenecks in this critical step. Here, we investigate whether convolutional neural networks (CNN) can optimize the processing of short eDNA sequences. We tested whether the speed and accuracy of a CNN are comparable to that of the frequently used OBITools bioinformatic pipeline. We applied the methodology on a massive eDNA dataset collected in Tropical South America (French Guiana), where freshwater fishes were targeted using a small region (60pb) of the 12S ribosomal RNA mitochondrial gene. We found that the taxonomic assignments from the CNN were comparable to those of OBITools, with high correlation levels and a similar match to the regional fish fauna. The CNN allowed the processing of raw fastq files at a rate of approximately 1 million sequences per minute which was 150 times faster than with OBITools. Once trained, the application of CNN to new eDNA metabarcoding data can be automated, which promises fast and easy deployment on the cloud for future eDNA analyses.