HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference
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.
Related
- InsectDCT: A generalized pipeline for detection, taxonomic classification, and tracking of insects in camera-trap recordings
- Generalized modeling reveals stabilizing mechanisms in cross-feeding microbial communities
- Genome-resolved metagenomics reveals the taxonomic and functional landscape of the rumen microbiome in Japanese Black × Holstein cattle and its associations with carcass traits
- The use of sequence databases for taxonomic research in phytovirology and the application of factor analysis of correspondences to the clustering of geminiviruses
- From deployment to functioning ecosystems: assessing taxonomic richness and community composition on modular shellfish reefs using environmental DNA metabarcoding
BibTeX
@misc{rao2026hypertaxa,
title = {{HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference}},
author = {Akash Rao and Sushim Gupta and Vishalini Ramnath and Akhilesh Ramachandran and Sathyanarayanan Aakur},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.25673},
eprint = {2610.25673},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.25673},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference
AU - Akash Rao
AU - Sushim Gupta
AU - Vishalini Ramnath
AU - Akhilesh Ramachandran
AU - Sathyanarayanan Aakur
PY - 2026
DA - 2026/10/19
PB - arXiv
DO - 10.48550/arxiv.2610.25673
UR - https://arxiv.org/abs/2610.25673
AB - 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.
ER -