EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing

David W Ludwig iD, Christopher Guptil, Nicholas R Alexander iD, Kateryna Zhalnina iD, Edi M-L Wipf iD, Albina Khasanova iD, Nicholas A Barber iD, Wesley Swingley iD, Donald M Walker iD, Joshua L Phillips iD

Bioinformatics · 2025

DOI: 10.1093/bioinformatics/btaf370 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2025. Verfasst von David W Ludwig und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Middle Tennessee State University, Murfreesboro, TN 37132, United States. Hauptthemen laut MEDLINE: Deep Learning, High-Throughput Nucleotide Sequencing, Sequence Analysis, DNA, Microbiota. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation High-throughput sequencing (HTS) is a modern sequencing technology used to profile microbiomes by sequencing thousands of short genomic fragments from the microorganisms within a given sample. This technology presents a unique opportunity for artificial intelligence to comprehend the underlying functional relationships of microbial communities. However, due to the unstructured nature of HTS data, nearly all computational models are limited to processing DNA sequences individually. This limitation causes them to miss out on key interactions between microorganisms, significantly hindering our understanding of how these interactions influence the microbial communities as a whole. Furthermore, most computational methods rely on post-processing of samples which could inadvertently introduce unintentional protocol-specific bias. Results Addressing these concerns, we present SetBERT, a robust pre-training methodology for creating generalized deep learning models for processing HTS data to produce contextualized embeddings and be fine-tuned for downstream tasks with explainable predictions. By leveraging sequence interactions, we show that SetBERT significantly outperforms other models in taxonomic classification with genus-level classification accuracy of 95%. Furthermore, we demonstrate that SetBERT is able to accurately explain its predictions autonomously by confirming the biological-relevance of taxa identified by the model. Availability and implementation All source code is available at https://github.com/DLii-Research/setbert. SetBERT may be used through the q2-deepdna QIIME 2 plugin whose source code is available at https://github.com/DLii-Research/q2-deepdna.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHigh-Throughput Nucleotide SequencingSequence Analysis, DNAMicrobiotaSoftwareComputational BiologyAlgorithms

Autor:innen und Institutionen

  • Department of Computer Science, Middle Tennessee State University, Murfreesboro, TN 37132, United States.
  • Department of Mathematics and Computer Science, Miami University, Oxford, OH 45056, United States.
  • Department of Biology, Middle Tennessee State University, Murfreesboro, TN 37132, United States.
  • Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, United States.
  • Department of Biology, San Diego State University, San Diego, CA 92182, United States.
  • Department of Biological Sciences, Northern Illinois University, DeKalb, IL 60115, United States.

ORCID-Profile: David W Ludwig, Nicholas R Alexander, Kateryna Zhalnina, Edi M-L Wipf, Albina Khasanova, Nicholas A Barber, Wesley Swingley, Donald M Walker, Joshua L Phillips

Förderung

  • National Science Foundation

Zitieren

APA

Ludwig, D. W., Guptil, C., Alexander, N. R., Zhalnina, K., Wipf, E. M., Khasanova, A., Barber, N. A., Swingley, W., Walker, D. M., & Phillips, J. L. (2025). SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaf370

Vancouver

Ludwig DW, Guptil C, Alexander NR, Zhalnina K, Wipf EM, Khasanova A, et al. SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing. Bioinformatics. 2025. doi:10.1093/bioinformatics/btaf370

BibTeX
@article{Ludwig2025,
  author = {Ludwig, David W and Guptil, Christopher and Alexander, Nicholas R and Zhalnina, Kateryna and Wipf, Edi M-L and Khasanova, Albina and Barber, Nicholas A and Swingley, Wesley and Walker, Donald M and Phillips, Joshua L},
  title = {SetBERT: the deep learning platform for contextualized embeddings and explainable predictions from high-throughput sequencing},
  journal = {Bioinformatics},
  year = {2025},
  doi = {10.1093/bioinformatics/btaf370}
}
Kostenlos starten →