HyperTaxa improves microbial classification using genome representations
HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference
Artificial Intelligence
Summary
Microbial species are being sequenced faster than ever, making it hard to identify new species that aren't in existing databases. The authors present HyperTaxa, a new method that represents entire microbial genomes in a way that captures their structure and relates it to known taxonomy. This approach allows predictions about species that haven't been directly seen before, improving identification especially at broad taxonomic levels like genus and family. Their tests show HyperTaxa works better than some other advanced methods for telling microbes apart.
What this means in practice
- •For microbial diagnostic teams: Use HyperTaxa to identify microbes beyond existing reference genomes for more accurate taxonomic classification in clinical and environmental samples.
- •For bioinformatics platform developers: Incorporate HyperTaxa’s genome representation approach to enhance microbial identification tools handling incomplete or novel genome data.
Authors
Akash Rao, Sushim Gupta, Vishalini Ramnath, Akhilesh Ramachandran, Sathyanarayanan Aakur
Abstract
Reliable microbial taxonomic inference is challenged by the rapid growth of newly sequenced organisms and incomplete reference coverage. While alignment- and database-driven tools remain essential for reference-backed identification, they are not designed for learned inference over species absent from genome-level training. We introduce HyperTaxa, a taxonomy-aligned representation learning framework for open-set microbial taxonomic inference. HyperTaxa encodes whole genomes as multiscale hyperspectral k-mer transition fields and aligns these representations to a taxonomy-derived semantic space using a two-stage Node2Vec-to-MDS procedure that combines local graph structure with global hierarchical distance preservation. The resulting space supports zero-shot inference over species excluded from genome-level training but represented in the taxonomy, generalized zero-shot inference over seen and unseen species, and cascaded genus-to-species prediction. Across benchmark and large-scale disjoint-species evaluations, HyperTaxa improves taxonomic prediction over pseudo-image and transformer-graph baselines, with the strongest gains at higher taxonomic ranks. Ablations further show that multiscale transition encoding and taxonomy-aware alignment are key contributors to generalization. These results position HyperTaxa as a complementary taxonomy-aware representation and candidate-generation framework for microbial identification under incomplete reference coverage and open-set uncertainty.