GeNet: Deep Representations for Metagenomics
This work addresses the problem of efficient and accurate metagenomic classification for researchers in genomics and bioinformatics, offering a method that reduces memory usage while maintaining performance, though it appears incremental as it builds on existing classification approaches.
The paper tackles metagenomic classification from raw DNA sequences by introducing GeNet, which exploits hierarchical label structure for training, resulting in competitive precision and recall with significantly lower memory requirements compared to state-of-the-art methods like Kraken and Centrifuge, and achieving over 90% accuracy in a pathogen detection task.
We introduce GeNet, a method for shotgun metagenomic classification from raw DNA sequences that exploits the known hierarchical structure between labels for training. We provide a comparison with state-of-the-art methods Kraken and Centrifuge on datasets obtained from several sequencing technologies, in which dataset shift occurs. We show that GeNet obtains competitive precision and good recall, with orders of magnitude less memory requirements. Moreover, we show that a linear model trained on top of representations learned by GeNet achieves recall comparable to state-of-the-art methods on the aforementioned datasets, and achieves over 90% accuracy in a challenging pathogen detection problem. This provides evidence of the usefulness of the representations learned by GeNet for downstream biological tasks.