cs.AIOct 19, 2026

HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic Inference

Authors: Akash Rao, Sushim Gupta, Vishalini Ramnath, Akhilesh Ramachandran, Sathyanarayanan Aakur

Organizations: CSSE Department, Auburn University, Auburn, AL, USA · Oklahoma Animal Disease Diagnostic Laboratory, Oklahoma State University, Stillwater, OK, USA

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Fig. 1: Overview of HyperTaxa . Multiscale kk -mer transition fields encode genome structure, while the microbial taxonomy provides hierarchical and distance constraints. A genome encoder maps these representations into a latent space aligned with taxonomy-derived embeddings, enabling zero-shot and generalized zero-shot inference.
Fig. 2: Genome representation and taxonomy embedding geometry. a–b. TEPI pseudo-image and HyperTaxa multiscale kk -mer transition representation for B. contaminans . c–d. Node2Vec and MDS taxonomy-embedding similarities; MDS yields clearer taxonomic separation. *contrast-enhanced.
Fig. 3: Zero-shot Top-1 accuracy on the TEPI benchmark.
Fig. 4: ZSL and GZSL performance. a. HyperTaxa outperforms MGNet/TEPI across all ranks in ZSL. b. In GZSL, MDS alignment yields the strongest performance, indicating improved hierarchical generalization.
Fig. 5: Hierarchical inference and ablations. a. Cascaded genus →\rightarrow species prediction improves accuracy. b. Increasing the number and range of hyperspectral kk -mer transition channels improves zero-shot generalization. c. CNN+MDS provides the strongest zero-shot performance among encoder and alignment variants.
More in this topic

Bioinformatics

See all 39 papers

Explore similar work

CardsList

  1. Set-Aggregated Genome Embeddings for Microbiome Abundance Prediction

    May 12, 2026Younhun Kim, Georg K. Gerber, Travis E. GibsonRepresentation LearningGenomics

    1Brigham and Women’s Hospital, Boston, MA, USA · 2Harvard Medical School, Boston, MA, USA

  2. Hierarchy-Guided Multimodal Representation Learning for Taxonomic Inference

    Mar 26, 2026Sk Miraj Ahmed, Xi Yu, Yunqi Li +2Hierarchical Representation LearningMultimodal Robustness

    Computing and Data Sciences, Brookhaven National Laboratory, Upton, NY 11973, USA · Rutgers University, New Brunswick, NJ, USA

  3. DeepTaxon: An Interpretable Retrieval-Augmented Multimodal Framework for Unified Species Identification and Discovery

    Apr 27, 2026Jiawei Wang, Ming Lei, Yaning Yang +8Retrieval-Augmented ClassificationAI-Assisted Scientific Research

    National University of Singapore · Hunan University · Xiangtan University +4