@article{fdi:010096350,
  title = {{F}ine-grained assignment of unknown marine e{DNA} sequences using neural networks},
  author = {{V}illon, {S}{\'e}bastien and {M}angeas, {M}organ and {B}erteaux-{L}ecellier, {V}. and {V}igliola, {L}aurent and {L}ecellier, {G}ael},
  editor = {},
  language = {{ENG}},
  abstract = {{E}nvironmental {DNA} (e{DNA}) metabarcoding is an innovative tool that is transforming ecological research. {I}t offers a simple and effective method for simultaneously detecting numerous species across a wide range of environments. {T}he method relies on assigning {DNA} sequences sampled from the environment to taxa, which is straightforward for species that have already been sequenced and are represented in reference databases. {H}owever, existing bioinformatics tools often fail to deliver accurate, fine-grained assignments when target species are absent from these databases. {T}his limitation arises from handcrafted classification thresholds that do not account for nucleotide positional information. {H}ere, we propose a deep neural architecture specifically designed to exploit both nucleotide identity and positional patterns in short {TELEO} sequences. {U}sing an in-silico validation framework based on {NCBI} genbank sequences, we compare our approach with several state-of-the-art bioinformatics tools ({O}bitools, {K}raken2, {L}olo), as well as alternative sequence embedding methods, under controlled conditions. {O}ur approach yields significantly higher classification accuracy at the genus and family levels, achieving average accuracies of 94.7% at the genus level and 86.5% at the family level, substantially outperforming the tested reference-based pipelines. {T}he method remains robust with limited training data and shows improved performance when nucleotide positional information is preserved through sequence alignment. {T}hese results demonstrate the potential of {AI}-powered e{DNA} metabarcoding to complement existing taxonomic assignment tools, particularly in contexts where reference databases are incomplete or species-level resolution is not achievable, thereby supporting biodiversity monitoring and ecosystem management.},
  keywords = {biodiversity monitoring ; environmental {DNA} ; bioinformatics ; deep learning algorithms ; convolutional neural networks {CNN} ; fish diversity ; ecological survey},
  booktitle = {},
  journal = {{B}iology},
  volume = {15},
  numero = {3},
  pages = {285 [16 p.]},
  year = {2026},
  DOI = {10.3390/biology15030285},
  URL = {https://www.documentation.ird.fr/hor/fdi:010096350},
}