2026-05-29原文

TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models

Metagenomic taxonomic annotation identifies microbial origins of DNA fragments. Traditional similarity-based methods struggle with high diversity and incomplete databases. TaxDistill uses a knowledge distillation framework with a 500M-parameter genomic foundation model (GenomeOcean) as teacher to generate soft labels, reducing label noise. Experiments on seven CAMI2 datasets show TaxDistill outperforms baselines, e.g., improving F1 score on Gastrointestinal dataset from 0.763 to 0.941.

Article intelligence

EngineersAdvanced

Key points

TaxDistill reduces label noise in metagenomic classification via knowledge distillation
Introduces GenomeOcean, a 500M-parameter genomic foundation model as teacher
Outperforms existing baselines on seven CAMI2 datasets
F1 score on Gastrointestinal dataset improved from 0.763 to 0.941

Why it matters

This matters because taxDistill reduces label noise in metagenomic classification via knowledge distillation.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.28868] TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models

[Submitted on 22 May 2026]

Title:TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models

View a PDF of the paper titled TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models, by Rongye Ye and 4 other authors

View PDF HTML (experimental)

Abstract:Metagenomic taxonomic annotation aims to identify the microbial origins of DNA fragments in environmental samples. Traditional methods that rely on sequence similarity are often constrained by the high microbial diversity and the incompleteness of reference databases, which has motivated the development of learning approaches such as Taxometer that perform post hoc correction to learn more informative metagenomic sequence representations. However, these methods typically rely on labels derived from similarity search tools during training, which inevitably introduces noise that can impair representation learning and degrade classification performance. To address this issue, we propose TaxDistill, a knowledge distillation framework for metagenomic classification. We introduce GenomeOcean, a 500M parameter genomic foundation model, as the teacher network to extract deep semantic features and generate soft labels based on confidence. By distilling this soft label information into a lightweight student network, TaxDistill effectively reduces the label noise introduced by initial retrieval tools. Comprehensive experiments on seven diverse CAMI2 datasets demonstrate that TaxDistill outperforms existing baselines in most scenarios. For instance, on the Gastrointestinal dataset, it improves the F1 score of MMseqs2 from 0.763 to 0.941, outperforming the Taxometer baseline. Overall, TaxDistill provides a reliable method for label correction in complex metagenomic analysis.

Comments: The manuscript contains 14 pages, 7 figures, and 3 tables

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.28868 [cs.LG]

(or arXiv:2605.28868v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.28868

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Rongye Ye [view email] [v1] Fri, 22 May 2026 08:03:29 UTC (3,080 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled TaxDistill: Improving Metagenomic Taxonomic Annotation via Distilled Genomic Foundation Models, by Rongye Ye and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)