CoChat
Sign Up
PreprintCited by 161Genomics and Phylogenetic StudiesMachine Learning in BioinformaticsFractal and DNA sequence analysis

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Helixer– de novo Prediction of Primary Eukaryotic Gene Models Combining Deep Learning and a Hidden Markov Model

Open access
Holst, Felix, Bolger, Anthony, Günther, Christopher, Maß, Janina, Triesch, Sebastian, Kindel, Felicitas, Kiel, Niklas, Saadat, Nima, Ebenhöh, Oliver, Usadel, Björn, Schwacke, Rainer, Bolger, Marie, Weber, Andreas P.M., Denton, Alisandra K.·2023·Nature Methods
DOI 10.1101/2023.02.06.527280PMC PMC13076211

Preprint — published as 10.1038/s41592-025-02939-1

Open this paper in CoChat — free accountOpen PDF

Abstract

A bstract: Gene structural annotation is a critical step in obtaining biological knowledge from genome sequences yet remains a major challenge in genomics projects. Current de novo Hidden Markov Models are limited in their capacity to model biological complexity; while current pipelines are resource-intensive and their results vary in quality with the available extrinsic data. Here, we build on our previous work in applying Deep Learning to gene calling to make a fully applicable, fast and user friendly tool for predicting primary gene models from DNA sequence alone. The quality is state-of-the-art, with predictions scoring closer by most measures to the references than to predictions from other de novo tools. Helixer’s predictions can be used as is or could be integrated in pipelines to boost quality further. Moreover, there is substantial potential for further improvements and advancements in gene calling with Deep Learning. Helixer is open source and available at https://github.com/weberlab-hhu/Helixer A web interface is available at https://www.plabipd.de/helixer_main.html

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2023.02.06.527280

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 41

  1. 10.1038/nbt.3300 · DOI · Paper page
  2. 10.1093/nar/25.17.3389 · DOI · Paper page
  3. Mohammad Ruhul Amin , Alisa Yurovsky , Yingtao Tian , and Steven Skiena . Deepannotator: Genome annotation with deep learning. In Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, pages 254–259, 2018.
  4. Eric Arazo , Diego Ortego , Paul Albert , Noel E. O’Connor , and Kevin McGuinness . Pseudo-labeling and confirmation bias in deep semi-supervised learning. CoRR, abs/1908.02983, 2019. URL http://arxiv.org/abs/1908.02983. · arXiv
  5. 2021, Effective gene expression prediction from sequence by integrating long-range interactions, Nature methods, 18, 1196, 10.1038/s41592-021-01252-x · DOI · Paper page
  6. 2020, Glycosylphosphatidylinositol-anchor synthesis in plants: a glycobiology perspective, Frontiers in Plant Science, 11, 611188, 10.3389/fpls.2020.611188 · DOI
  7. Marie Bolger , Rainer Schwacke , and Björn Usadel . Mapman visualization of rna-seq data using mercator4 functional annotations. Solanum tuberosum: Methods and Protocols, pages 195–212, 2021. · DOI
  8. 2020, Language models are few-shot learners, Advances in neural information processing systems, 33, 1877
  9. 2021, Braker2: automatic eukaryotic genome annotation with genemark-ep+ and augustus supported by a protein database, NAR genomics and bioinformatics, 3, lqaa108, 10.1093/nargab/lqaa108 · DOI
  10. Andrew M Dai and Quoc V Le . Semi-supervised sequence learning. Advances in neural information processing systems, 28, 2015.
  11. Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . Bert: Pre-training of deep bidirectional transformers for language understanding, 2018. URL https://arxiv.org/abs/1810.04805. · arXiv
  12. 10.1186/s13059-019-1727-y · DOI · Paper page
  13. 2022, Discovering faster matrix multiplication algorithms with reinforcement learning, Nature, 610, 47, 10.1038/s41586-022-05172-4 · DOI · Paper page
  14. 10.1093/nar/gkg770 · DOI
  15. 2018, A deep recurrent neural network discovers complex biological rules to decipher rna protein-coding potential, Nucleic acids research, 46, 8105, 10.1093/nar/gky567 · DOI
  16. 10.1186/1471-2105-12-1 · DOI
  17. 10.1105/tpc.014407 · DOI
  18. 2019, Deep learning for symbolic mathematics, arXiv preprint
  19. 10.1093/bioinformatics/btac454 · DOI
  20. 2019, Deep splicing code: Classifying alternative splicing events using deep learning, Genes, 10, 587, 10.3390/genes10080587 · DOI
  21. 10.1016/j.pbi.2019.12.009 · DOI
  22. 10.1038/s41586-019-1312-2 · DOI
  23. 2019, Mapman4: a refined protein classification and annotation framework applicable to multi-omics data analysis, Molecular plant, 12, 879, 10.1016/j.molp.2019.01.003 · DOI
  24. 10.1038/nature16961 · DOI · Paper page
  25. 10.1093/bioinformatics/btv351 · DOI · Paper page
  26. 2021, Prediction of eukaryotic exons using bidirectional lstm-rnn based deep learning model, Int. J, 9, 275
  27. 10.1186/gb-2006-7-s1-s10 · DOI
  28. 10.1093/bioinformatics/btg1080 · DOI · Paper page
  29. 10.1093/nar/gkl200 · DOI · Paper page
  30. 2020, Helixer: cross-species gene annotation of large eukaryotic genomes using deep learning, Bioinformatics, 36, 5291
  31. 10.1126/science.278.5338.631 · DOI
  32. 10.1101/gr.081612.108 · DOI
  33. 10.1101/2022.12.06.519256 · DOI
  34. Ashish Vaswani , Noam Shazeer , Niki Parmar , Jakob Uszkoreit , Llion Jones , Aidan N Gomez , Łukasz Kaiser , and Illia Polosukhin . Attention is all you need. Advances in neural information processing systems, 30, 2017.
  35. 1967, Error bounds for convolutional codes and an asymptotically optimum decoding algorithm, IEEE transactions on Information Theory, 13, 260, 10.1109/TIT.1967.1054010 · DOI
  36. 2021, Uncovering transcriptional dark matter via gene annotation independent single-cell rna sequencing analysis, Nature Communications, 12, 2158, 10.1038/s41467-021-22496-3 · DOI
  37. 10.1186/s12859-019-3306-3 · DOI
  38. 2021, Neurotis: Enhancing the prediction of translation initiation sites in mrna sequences via a hybrid dependency network and deep learning framework, Knowledge-Based Systems, 212, 106459, 10.1016/j.knosys.2020.106459 · DOI
  39. 10.1038/nrg3174 · DOI · Paper page
  40. 10.1186/s13059-022-02601-5 · DOI · Paper page
  41. Yi Zhang , Xinan Liu , James N MacLeod , and Jinze Liu . Deepsplice: Deep classification of novel splice junctions revealed by rna-seq. In 2016 IEEE international conference on bioinformatics and biomedicine (BIBM), pages 330–333. IEEE, 2016. · DOI

Cited by

Sorted by citations

Metadata

Authors
Holst, F., Bolger, A., Günther, C., Maß, J., Triesch, S., Kindel, F., Kiel, N., Saadat, N., Ebenhöh, O., Usadel, B., Schwacke, R., Bolger, M., Weber, A. P. M., & Denton, A. K.
Affiliations
  • Heinrich Heine University Düsseldorf (DE)
  • Forschungszentrum Jülich (DE)
  • Cluster of Excellence on Plant Sciences (DE)
Corresponding author
Bolger, Marie
ORCID
Venue
Nature Methods
Publisher
openRxiv
Published
2023-02-06
Volume
23
Issue
4
Pages
732-739
ISSN
1548-7091 (ISSN-L)
DOI
10.1101/2023.02.06.527280
PMC
PMC13076211
OpenAlex
W4416571000
Cited by
161
References
1
Citations by year
2026: 92 · 2025: 39 · 2024: 25 · 2023: 4
FWCI
38.83
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Nature Methods (publishedVersion, cc-by)
  • bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • JuSER (Forschungszentrum Jülich) (submittedVersion, other-oa)
  • JuSER Publikationsportal
Funders
  • Deutsche Forschungsgemeinschaft (031A533B, 497667402, 031A537C, EXC-2048, EXC-2048/1, 031A534A, 031A537B, 031A535A, HIDSS-004, 031A538A, 390686111, 031A532B, 2048/1, 031A533A)
  • Bundesministerium für Bildung und Forschung (031A537C, 031A533A, 031A535A, 031A537B, 031A533A, 031A538A, 031A533B, 031A535A, 031A537C, 031A534A, 031A532B, 031A538A, 031A534A, 031A532B, 031A533B, 031A537B)
  • Forschungszentrum Jülich
  • Heinrich-Heine-Universität Düsseldorf
  • German Network for Bioinformatics Infrastructure (031A533A, 031A534A, 031A538A, 031 A535 A, 031 A537B, 031A537B, 031A533A, 031A538A, 031A533B, 031A535A, 031A537C, 031A534A, 031A532B, 031 A532B, 031 A533B, #031A537C)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Genomics and Phylogenetic Studies
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Machine Learning in Bioinformatics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Fractal and DNA sequence analysis
Keywords
ab initio gene prediction, eukaryotic genomes, deep learning, hidden Markov models, genome annotation, gene models, fungal genome, plant genome, vertebrate genomes, invertebrate genomes, pre-trained models
MeSH terms
Deep Learning, Hidden Markov Models, Animals, Markov Chains, Models, Genetic, Software, Computational Biology, Genomics, Eukaryota, Molecular Sequence Annotation

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review