Skip to content
DraconiticResearch
Search Sources API
182,460 studies31 sourcesUpdated 38 min ago
Peer-reviewedCC BY 4.0Nucleic Acids Research

Fast and accurate taxonomic domain assignment of short metagenomic reads using BBERT

  • Dmitry Alekhin1
  • Moshe Alon1,2
  • Tomer Sidi3
  • Stav Perez Mazeh1,4
  • Gon Carmi5
  • Omri M Finkel2
  • Amir Erez1
5 affiliations
  1. 1Racah Institute of Physics, The Hebrew University of Jerusalem , Edmond J. Safra Campus, Givat Ram, Jerusalem 9190401 ,
  2. 2Department of Plant & Environmental Sciences, The Alexander Silberman Institute of Life Sciences, The Hebrew University of Jerusalem , Edmond J. Safra Campus, Givat Ram, Jerusalem 9190401 ,
  3. 3Department of Computer Science, University of Haifa , Haifa 3303221 ,
  4. 4Benin School of Computer Science and Engineering, The Hebrew University of Jerusalem , Edmond J. Safra Campus, Givat Ram, Jerusalem 9190401 ,
  5. 5Institute of Plant Sciences, Newe Ya’ar Research Center, Agricultural Research Organization (ARO), Volcani Institute , Ramat Yishay 30095 ,
Read full textPDFDOICite

Abstract

Shotgun metagenomes from complex environments such as soil uncover vast biodiversity. Yet most short reads produced by shotgun sequencing cannot be taxonomically or functionally annotated, as they lack a sufficiently comprehensive reference, obscuring the true structure and function of microbial communities. We introduce BBERT, a nucleotide large language model optimized for short reads. Testing on a large cohort of soil metagenomes, we found that BBERT identifies bacterial sequence syntax without relying on reference databases, enabling accurate assignment of taxonomic domain, coding potential, and reading frame directly from reads as short as 100 bp. BBERT is small and fast enough to analyze metagenomes using a modest GPU and can be used to convert short metagenomic reads directly to bacterial amino acid sequences for downstream applications. BBERT also improves de novo metagenomic assembly, reducing mismatches and gaps while accelerating runtime. Using metagenomes from wild legume nodules, we demonstrate that BBERT filtering improves bin quality while significantly accelerating de novo assembly. By providing fast, reference-free classification of short reads, BBERT unlocks large metagenomic archives for more accurate ecological and evolutionary analyses.

Related

  1. CroCoDeEL: accurate control-free detection of cross-sample contamination in metagenomic data
    Lindsay Goulet, Florian Plaza Oñate, Alexandre Famechon +5
    Nature CommunicationsPeer-reviewedCC BY10 citedMolecular biology & gene regulationOpenAlex
  2. Clinical severity score-guided metagenomic analysis identifying gut microbial taxonomic and functional markers for severe hepatitis E progression
    Haiyan Shi, Yanfei Chen, Xiaoli Liu +8
    mSystemsPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationPMC
  3. SpaMOAL is a deep learning method that enables accurate spatial domain identification from multi-omics data
    Jinxia Wang, Yuying Huo, Rui Zhao +4
    PLOS BiologyPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationGenetics & genomicsPLOS
  4. Accurate MAG reconstruction from a complex soil microbiome through combined short- and HiFi long-reads metagenomics
    Carole Belliardo, Nicolas Maurice, Arthur Pere +13
    Environmental MicrobiomePeer-reviewedCC BY 4.0Full text2 citedProteomics & metabolomicsBioinformatics & computational biologyHAL
  5. Voyager: rapid taxonomic characterization of long-read mixed-species sequencing samples in sorted motif distance space.
    Sverre Branders, Manfred G Grabherr, Rafi Ahmad
    Genome biologyPeer-reviewedCC BYFull text1 citedMolecular biology & gene regulationEurope PMC

Cite

BibTeXRIS
BibTeX
@article{alekhin2026fast,
  title = {{Fast and accurate taxonomic domain assignment of short metagenomic reads using BBERT}},
  author = {Dmitry Alekhin and Moshe Alon and Tomer Sidi and Stav Perez Mazeh and Gon Carmi and Omri M Finkel and Amir Erez},
  journal = {Nucleic Acids Research},
  year = {2026},
  month = oct,
  doi = {10.1093/nar/gkag1002},
  url = {https://academic.oup.com/nar/article/doi/10.1093/nar/gkag1002/8971853},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Fast and accurate taxonomic domain assignment of short metagenomic reads using BBERT
AU  - Dmitry Alekhin
AU  - Moshe Alon
AU  - Tomer Sidi
AU  - Stav Perez Mazeh
AU  - Gon Carmi
AU  - Omri M Finkel
AU  - Amir Erez
PY  - 2026
DA  - 2026/10/01
JO  - Nucleic Acids Research
DO  - 10.1093/nar/gkag1002
UR  - https://academic.oup.com/nar/article/doi/10.1093/nar/gkag1002/8971853
AB  - Shotgun metagenomes from complex environments such as soil uncover vast biodiversity. Yet most short reads produced by shotgun sequencing cannot be taxonomically or functionally annotated, as they lack a sufficiently comprehensive reference, obscuring the true structure and function of microbial communities. We introduce BBERT, a nucleotide large language model optimized for short reads. Testing on a large cohort of soil metagenomes, we found that BBERT identifies bacterial sequence syntax without relying on reference databases, enabling accurate assignment of taxonomic domain, coding potential, and reading frame directly from reads as short as 100 bp. BBERT is small and fast enough to analyze metagenomes using a modest GPU and can be used to convert short metagenomic reads directly to bacterial amino acid sequences for downstream applications. BBERT also improves de novo metagenomic assembly, reducing mismatches and gaps while accelerating runtime. Using metagenomes from wild legume nodules, we demonstrate that BBERT filtering improves bin quality while significantly accelerating de novo assembly. By providing fast, reference-free classification of short reads, BBERT unlocks large metagenomic archives for more accurate ecological and evolutionary analyses.
SN  - 0305-1048
SN  - 1362-4962
ER  -