Tiberius Web Server

Tiberius is a deep learning-based tool for ab initio eukaryotic gene structure prediction. It combines a CNN, bidirectional LSTM, and a differentiable HMM end-to-end, and matches the accuracy of tools that require extrinsic evidence, using genomic sequence alone.

Upload a genome FASTA file, select the clade that best matches your organism, and optionally receive a gene annotation in GTF or GFF3 format by email. No registration required.

Note: Accepted file types are .fa.gz and .fasta.gz (gzip-compressed FASTA, max 500 MB). Results are stored for 45 days; email addresses deleted after the result notification is sent.

Genome FASTA * Help
Clade model * Help	Choose the clade that most closely matches your organism.
Email Help	Optional. If provided, results and error notifications are sent to this address.
Help	I confirm that the uploaded genome does not contain personalized human genomic data. *
Help	I consent to the processing of my personal data (uploaded genome sequence and, if provided, email address) in accordance with the Data Privacy Protection Declaration. *

* required field

Read the tutorial

Output files

GTF, GFF3, coding sequences, and protein sequences (all gzip-compressed).

Runtime estimates

Runtime depends on genome size and resource availability. Jobs are automatically routed to GPU nodes when available (substantially faster) or CPU nodes otherwise. A typical insect genome (~400 Mb) takes approximately 30 min on GPU or 2–4 h on CPU. A mammalian genome (~2.5 Gb) takes approximately 2–4 h on GPU or 12–24 h on CPU.

Citation

If you use results from this server, please cite:

Gabriel L., Brůna T., Kaur A., Krishnan A., Ortmann F., Salamov A., Talbot S., Becker F., Krieg R., Wheat C.W., Grigoriev I.V., Stanke M., Hoff K.J. (2026). Accurate ab initio gene prediction in eukaryotes with Tiberius in multiple clades. bioRxiv. https://doi.org/10.64898/2026.04.24.720536

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):btae685. https://doi.org/10.1093/bioinformatics/btae685

Source code

Tiberius is open-source software (license: Apache 2.0).
→ github.com/Gaius-Augustus/Tiberius

Funding

This web server was developed with support from the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation), Projektnummer 552910312 (project AI-GUSTUS).