EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Tiberius: end-to-end deep learning with an HMM for gene prediction

Lars Gabriel iD, Felix Becker iD, Katharina J Hoff, Mario Stanke iD

Bioinformatics · 28.11.2024 · 40 (12)

DOI: 10.1093/bioinformatics/btae685 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 18.11.2024. Verfasst von Lars Gabriel und 3 weiteren Autor:innen. Beteiligte Einrichtung: Institute of Mathematics and Computer Science, University of Greifswald, Greifswald 17489, Germany. Hauptthemen laut MEDLINE: Deep Learning, Markov Chains. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation For more than 25 years, learning-based eukaryotic gene predictors were driven by hidden Markov models (HMMs), which were directly inputted a DNA sequence. Recently, Holst et al. demonstrated with their program Helixer that the accuracy of ab initio eukaryotic gene prediction can be improved by combining deep learning layers with a separate HMM postprocessor. Results We present Tiberius, a novel deep learning-based ab initio gene predictor that end-to-end integrates convolutional and long short-term memory layers with a differentiable HMM layer. Tiberius uses a custom gene prediction loss and was trained for prediction in mammalian genomes and evaluated on human and two other genomes. It significantly outperforms existing ab initio methods, achieving F1 scores of 62% at gene level for the human genome, compared to 21% for the next best ab initio method. In de novo mode, Tiberius predicts the exon−intron structure of two out of three human genes without error. Remarkably, even Tiberius’s ab initio accuracy matches that of BRAKER3, which uses RNA-seq data and a protein database. Tiberius’s highly parallelized model is the fastest state-of-the-art gene prediction method, processing the human genome in under 2 hours. Availability and implementation https://github.com/Gaius-Augustus/Tiberius

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMarkov ChainsHumansSoftwareAnimalsComputational BiologyGenome, HumanAlgorithms

Autor:innen und Institutionen

  • Institute of Mathematics and Computer Science, University of Greifswald, Greifswald 17489, Germany.
  • Center for Functional Genomics of Microbes, University of Greifswald, Greifswald 17489, Germany.

ORCID-Profile: Lars Gabriel, Felix Becker, Mario Stanke

Zitieren

APA

Gabriel, L., Becker, F., Hoff, K. J., & Stanke, M. (2024). Tiberius: end-to-end deep learning with an HMM for gene prediction. Bioinformatics, 40(12). https://doi.org/10.1093/bioinformatics/btae685

Vancouver

Gabriel L, Becker F, Hoff KJ, Stanke M. Tiberius: end-to-end deep learning with an HMM for gene prediction. Bioinformatics. 2024;40(12). doi:10.1093/bioinformatics/btae685

BibTeX
@article{Gabriel2024,
  author = {Gabriel, Lars and Becker, Felix and Hoff, Katharina J and Stanke, Mario},
  title = {Tiberius: end-to-end deep learning with an HMM for gene prediction},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {12},
  doi = {10.1093/bioinformatics/btae685}
}
Kostenlos starten →