Helixer: ab initio prediction of primary eukaryotic gene models combining deep learning and a hidden Markov model
The accurate identification of genes is vital for understanding biological function, yet this remains challenging across many newly sequenced or less-studied species. Here we present Helixer, an artificial intelligence-based tool for ab initio gene prediction that delivers highly accurate gene models across fungal, plant, vertebrate and invertebrate genomes. Unlike traditional methods, Helixer operates without requiring additional experimental data such as RNA sequencing, making it broadly applicable to diverse species. We show that Helixer's pretrained models achieve accuracy on par with or exceeding current tools, producing gene annotations that closely match expert-curated references across multiple evaluation metrics. Its design enables immediate use on genomes without retraining, providing an efficient, accessible solution for genome annotation in both research and applied settings. The tool is available as an open-source software for local installation via GitHub. An online web interface is also available as well as through the Galaxy ToolShed.
Authors
- Sebastian Triesch (ORCID: https://orcid.org/0000-0001-7796-4631)
- Björn Usadel (ORCID: https://orcid.org/0000-0003-0921-8041)
- Oliver Ebenhöh (ORCID: https://orcid.org/0000-0002-7229-7398)
- Anthony Bolger
- Rainer Schwacke
- Niklas Kiel (ORCID: https://orcid.org/0000-0002-8153-8835)
- Andreas P.M. Weber (ORCID: https://orcid.org/0000-0003-0970-4672)
- Felicitas Kindel (ORCID: https://orcid.org/0009-0000-6149-0224)
- Felix Holst
- Janina Maß (ORCID: https://orcid.org/0000-0002-0752-7732)
- Christopher Günther
- Alisandra K. Denton (ORCID: https://orcid.org/0000-0002-1132-0224)
- Nima P. Saadat (ORCID: https://orcid.org/0000-0002-1262-6591)
- Marie Bolger (ORCID: https://orcid.org/0000-0001-6335-1578)
Institutions
- Forschungszentrum Jülich (DE)
- Bureau de Coopération Interuniversitaire (CA)
- Cluster of Excellence on Plant Sciences (DE)
- Heinrich Heine University Düsseldorf (DE)
Publication Details
- Journal
- Nature Methods
- Published
- 2025-11-24
- DOI
- https://doi.org/10.1038/s41592-025-02939-1
- Citations
- 15
- Primary Topic
- Genomics and Phylogenetic Studies
- Type
- article
- Field-Weighted Citation Impact
- 12.09
Funders
- Deutsche Forschungsgemeinschaft
- Bundesministerium für Bildung und Forschung
- Forschungszentrum Jülich
- Heinrich-Heine-Universität Düsseldorf
- German Network for Bioinformatics Infrastructure