datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
vertebrate_genomessmall_vertebrate_genomes_8192Angiosperm_65_genomes_8192bp_rcgenomes-brassicales-balanced-v1More info: https://github.com/songlab-cal/gpn
mammalian-genomes-cdsAngiosperm_65_genomes_8192bp
Revision Notice!
This dataset was updated on 2025-12-010 to correct the duplicated sequences, see issues here. The update replaces the previous version
in this repository.
Old version: b5b4eadfd32c6baea27a3e6fb7275ea34f064e87
🌱 Angiosperm_65_genomes_8192bp: 8,192 bp Genomic Windows from 65 Angiosperm Genomes
This dataset provides tokenized 8,192 base-pair (bp) genomic windows across 65 plant genomes from the Phytozome database. It is formatted using the Hugging Face… See the full description on the dataset page: https://huggingface.co/datasets/plantcad/Angiosperm_65_genomes_8192bp.Angiosperm_16_genomesexperiment_one_viral_genomes_val_setmammal_genomes_8192experiment_one_viral_genomes_val_set_v2experiment_one_viral_genomes_test_setexperiment_one_viral_genomes_train_set_v2many_mammal_genomes_8192experiment_one_viral_genomes_train_setexperiment_one_viral_genomes_test_set_v2experiment_one_viral_genomes_train_setexperiment_one_viral_genomes_val_setexperiment_one_viral_genomes_test_setAngiosperm_4_genomes_2048bpThis dataset is derived from Angiosperm 65 Genomes 8192 bp by PlantCAD (licence not specified at time of writing).
Redistribution is limited to non-commercial research under the CC-BY-NC-ND-4.0 licence. Attribution to the original dataset is preserved.
If you are the rights holder and wish to clarify or modify the licensing terms, please get in touch.
This is a small subset of the original dataset, containing only 4 assemblies and 2048bp.
Dataset created on: 2025-10-27 10:11:22… See the full description on the dataset page: https://huggingface.co/datasets/dpelacani/Angiosperm_4_genomes_2048bp.Angiosperm_16_genomes_shardedgenomes-mammals-balanced-v1Angiosperm_8_genomes_8192bpThis dataset is derived from Angiosperm 65 Genomes 8192 bp by PlantCAD (licence not specified at time of writing).
Redistribution is limited to non-commercial research under the CC-BY-NC-ND-4.0 licence. Attribution to the original dataset is preserved.
If you are the rights holder and wish to clarify or modify the licensing terms, please get in touch.
This is a small subset of the original dataset, containing only 8 assemblies for quick experimentation and testing.
Dataset created on:… See the full description on the dataset page: https://huggingface.co/datasets/dpelacani/Angiosperm_8_genomes_8192bp.genomes-mammals-balanced-v1-1024NTV3-alllayer-152-genomes-32k-activations