EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MetaTransformer: deep metagenomic sequencing read classification using self-attention models

Alexander Wichmann iD, Etienne Buschong, André Müller iD, Daniel Jünger, Andreas Hildebrandt, Thomas Hankeln, Bertil Schmidt iD

NAR Genomics and Bioinformatics · 05.07.2023 · 5 (3)

DOI: 10.1093/nargab/lqad082 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, online erschienen am 11.09.2023. Verfasst von Alexander Wichmann und 6 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Computer Science, Johannes Gutenberg University, Staudingerweg 9, 55128 Mainz, Rhineland-Palatinate, Germany. Die Arbeit wurde bisher 31-mal zitiert (Crossref) und nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Carl-Zeiss-Stiftung, German Federal Ministry of Education and Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has emerged as a paradigm that revolutionizes numerous domains of scientific research. Transformers have been utilized in language modeling outperforming previous approaches. Therefore, the utilization of deep learning as a tool for analyzing the genomic sequences is promising, yielding convincing results in fields such as motif identification and variant calling. DeepMicrobes, a machine learning-based classifier, has recently been introduced for taxonomic prediction at species and genus level. However, it relies on complex models based on bidirectional long short-term memory cells resulting in slow runtimes and excessive memory requirements, hampering its effective usability. We present MetaTransformer, a self-attention-based deep learning metagenomic analysis tool. Our transformer-encoder-based models enable efficient parallelization while outperforming DeepMicrobes in terms of species and genus classification abilities. Furthermore, we investigate approaches to reduce memory consumption and boost performance using different embedding schemes. As a result, we are able to achieve 2× to 5× speedup for inference compared to DeepMicrobes while keeping a significantly smaller memory footprint. MetaTransformer can be trained in 9 hours for genus and 16 hours for species prediction. Our results demonstrate performance improvements due to self-attention models and the impact of embedding schemes in deep learning on metagenomic sequencing data.

Autor:innen und Institutionen

  • Institute of Computer Science, Johannes Gutenberg University, Staudingerweg 9, 55128 Mainz, Rhineland-Palatinate, Germany.
  • Institute of Organic and Molecular Evolution (iomE), Johannes Gutenberg University, J.-J. Becher-Weg 30A, 55128 Mainz, Rhineland-Palatinate, Germany.

ORCID-Profile: Alexander Wichmann, André Müller, Bertil Schmidt

Förderung

  • Carl-Zeiss-Stiftung
  • German Federal Ministry of Education and Research

Zitieren

APA

Wichmann, A., Buschong, E., Müller, A., Jünger, D., Hildebrandt, A., Hankeln, T., & Schmidt, B. (2023). MetaTransformer: deep metagenomic sequencing read classification using self-attention models. NAR Genomics and Bioinformatics, 5(3). https://doi.org/10.1093/nargab/lqad082

Vancouver

Wichmann A, Buschong E, Müller A, Jünger D, Hildebrandt A, Hankeln T, et al. MetaTransformer: deep metagenomic sequencing read classification using self-attention models. NAR Genomics and Bioinformatics. 2023;5(3). doi:10.1093/nargab/lqad082

BibTeX
@article{Wichmann2023,
  author = {Wichmann, Alexander and Buschong, Etienne and Müller, André and Jünger, Daniel and Hildebrandt, Andreas and Hankeln, Thomas and Schmidt, Bertil},
  title = {MetaTransformer: deep metagenomic sequencing read classification using self-attention models},
  journal = {NAR Genomics and Bioinformatics},
  year = {2023},
  volume = {5},
  number = {3},
  doi = {10.1093/nargab/lqad082}
}
Kostenlos starten →