Citing

If you use HelixForge, please cite the software:

Seetharam, A.S., Tibbs-Cortes, L., and Woodhouse, M.R. (2026). HelixForge: evidence-based reconciliation of deep-learning gene predictions with RNA-seq and protein homology. Intelligent Systems for Molecular Biology (ISMB) 2026. https://github.com/aseetharam/helixforge

A software DOI will be minted at release; prefer it over the repository URL once available.

Tools HelixForge builds on

HelixForge builds directly on two tools. Please cite them as well.

Helixer, the gene predictions HelixForge refines:

Holst, F. et al. (2025). Helixer: ab initio prediction of primary eukaryotic gene models combining deep learning and a hidden Markov model. Nature Methods. doi:10.1038/s41592-025-02939-1

Stiehler, F. et al. (2020). Helixer: cross-species gene annotation of large eukaryotic genomes using deep learning. Bioinformatics 36(22–23), 5291–5298. doi:10.1093/bioinformatics/btaa1044

Mikado, the reconciliation engine:

Venturini, L., Caim, S., Kaithakottil, G.G., Mapleson, D.L., and Swarbreck, D. (2018). Leveraging multiple transcriptome assembly methods for improved gene structure annotation. GigaScience 7(8), giy093. doi:10.1093/gigascience/giy093

If you run HelixForge with --hpc hypershell:

Lentner, G. and Gorenstein, L. (2022). HyperShell v2: Distributed Task Execution for HPC. PEARC '22, ACM. doi:10.1145/3491418.3535138

License

HelixForge is released under the MIT license.