Tiberius Mesangiospermae: Training Genomes and Annotations for Plant Model

15.3 GB of genomes and annotations used to train, validate, and test the Tiberius model for Mesangiospermae plants. The dataset was authored by Tomas Bruna and last updated on April 23, 2026. It includes some genomes not yet publicly released, provided with permission for reproducibility under the Fort Lauderdale Accord.

Use Cases

• Training machine learning models for plant genomics based on the provided genome sequences.
• Validating genomic prediction models using the included annotations.
• Reproducing the results of the Tiberius model study using the original training data.
• Comparing newly sequenced plant genomes against the provided reference set.

Strengths

• Large-scale dataset at 15.3 GB, suggesting substantial genomic content.
• Includes genomes not yet publicly released, offering unique data for reproducibility.
• Released under the permissive MIT license, facilitating reuse.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Some data has restricted use under the Fort Lauderdale Accord until official public release.

Provenance

Source

figshare; original data providers for specific genomes.

Collection Method

Likely compiled from public repositories and direct contributions for the Tiberius model study.

Freshness

Last updated 2026-04-23 21:24:00