End-to-end learning of evolutionary models to find coding regions in genome alignments

Mertsch, Darvin; Stanke, Mario

doi:10.1093/bioinformatics/btac028

Cited by 3 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tiberius has a de novo mode that uses evolutionary evidence from multiple unannotated genomes. This evidence, generated by ClaMSA [24] using 64 species in the Zoonomia project alignment [1], provides site-specific coding probabilities. These are summarized into four values per position, representing the logit values for codon start sites.…”

Section: Tiberius De Novomentioning

confidence: 99%

Tiberius: End-to-End Deep Learning with an HMM for Gene Prediction

Gabriel,

Becker,

Hoff

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

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. 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.

show abstract

Section: Tiberius De Novomentioning

confidence: 99%

Tiberius: End-to-End Deep Learning with an HMM for Gene Prediction

Gabriel,

Becker,

Hoff

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Comparative Genome Annotation

Nachtweide,

Romoth,

Stanke

2024

Methods in Molecular Biology

View full text Add to dashboard Cite

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

Gabriel,

Becker,

Hoff

et al. 2024

Bioinformatics

View full text Add to dashboard Cite

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

show abstract

End-to-end learning of evolutionary models to find coding regions in genome alignments

Cited by 3 publications

References 17 publications

Tiberius: End-to-End Deep Learning with an HMM for Gene Prediction

Tiberius: End-to-End Deep Learning with an HMM for Gene Prediction

Comparative Genome Annotation

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

Contact Info

Product

Resources

About