Berzelius Common Datasets

To avoid data duplication and save hard drive space, we provide access to a selection of public datasets frequently used in AI/ML research. The datasets are Ready-to-use under COMMON_DATASETS=/proj/common-datasets.

Users are encouraged to contact us to request corrections, updates, or the addition of new datasets.

Resource Version Directory Access License
Protein structure and bioinformatics
AlphaFold
BFD Not versioned AlphaFold Ready-to-use CC BY 4.0
MGnify 2022_05, 2018_12 AlphaFold Ready-to-use CC0
PDB Not versioned AlphaFold Ready-to-use CC0
PDB seqres Not versioned AlphaFold Ready-to-use CC0
PDB70 from_mmcif_200401 AlphaFold Ready-to-use CC BY 4.0
UniProt 2022_05 AlphaFold Ready-to-use CC BY 4.0
UniRef30 2021_03 AlphaFold Ready-to-use CC BY-SA 4.0
UniRef90 2022_05 AlphaFold Ready-to-use CC BY 4.0
LocalColabFold
ColabFold environmental database 2021_08 LocalColabFold Ready-to-use CC BY 4.0
PDB mmCIF Not versioned LocalColabFold Ready-to-use CC0
PDB100 2023_05_17 LocalColabFold Ready-to-use CC BY 4.0
PDB100 Foldseek template alignments 2023_05_17 LocalColabFold Ready-to-use CC BY 4.0
UniRef30 2023_02 LocalColabFold Ready-to-use CC BY 4.0
AlphaFold 3
BFD small Not versioned AlphaFold3 Ready-to-use CC BY 4.0
MGnify 2022_05 AlphaFold3 Ready-to-use CC0
Model parameters Not hosted Not provided on Berzelius Obtain separately Terms
NT 2023_02_23 AlphaFold3 Ready-to-use Not specified
PDB 2022_09_28 AlphaFold3 Ready-to-use CC0
PDB seqres 2022_09_28 AlphaFold3 Ready-to-use CC0
RFam 14_9 AlphaFold3 Ready-to-use CC
RNACentral Not versioned AlphaFold3 Ready-to-use CC0
UniProt 2021_04 AlphaFold3 Ready-to-use CC BY 4.0
UniRef90 2022_05 AlphaFold3 Ready-to-use CC BY 4.0
Foldseek
afdb 2025-10-08 Foldseek Ready-to-use CC BY 4.0
afdb50 2025-10-07 Foldseek Ready-to-use CC BY 4.0
bfvd 2025-09-12 Foldseek Ready-to-use CC BY 4.0
OpenFold
Alignment DBs Not versioned OpenFold Ready-to-use CC0
Alignments Not versioned OpenFold Ready-to-use CC0
ColabFold's environmental database 202108 OpenFold Ready-to-use MIT
Data caches Not versioned OpenFold Ready-to-use Apache 2.0
SoloSeq trained parameters Not versioned OpenFold Ready-to-use Apache 2.0
Trained parameters Not versioned OpenFold Ready-to-use Apache 2.0
Computer vision and image classification
CIFAR-10/100 Not versioned CIFAR Ready-to-use Not specified
COCO Not versioned COCO Ready-to-use CC BY 4.0
DomainNet Not versioned DomainNet Ready-to-use Terms
Fashion-MNIST Not versioned Fashion-MNIST Ready-to-use MIT
ImageNet Not versioned ImageNet Request via SUPR Terms
Imagenette Not versioned Imagenette Request via SUPR Terms
MNIST Not versioned MNIST Ready-to-use CC BY-SA 3.0
Places365 Not versioned Places Request via support Terms
Autonomous driving and robotics
General autonomous driving datasets
Argoverse v1.1, v2.0 Argoverse Request via SUPR Terms
Bench2Drive Not versioned Bench2Drive Ready-to-use CC-BY-NC-ND
KITTI Not versioned KITTI Ready-to-use Not specified
KITTI-360 Not versioned KITTI-360 Ready-to-use Not specified
MAN-TruckScenes v1.0 MAN-TruckScenes Ready-to-use CC BY-NC-SA 4.0
NAVSIM OpenScene v1.1 NAVSIM Request via SUPR OpenScene / nuPlan terms
nuImages v1.0 nuImages Request via SUPR Terms
nuPlan v1.1 nuPlan Request via SUPR Terms
OpenScene v1.1 OpenScene Request via SUPR CC BY-NC-SA 4.0 + nuPlan terms
PandaSet v1.0 PandaSet Ready-to-use CC BY 4.0
View-of-Delft Not versioned View-of-Delft Request via SUPR Terms
Zenseact Open Dataset Not versioned Zenseact-Open-Dataset Request via SUPR Terms
nuScenes
CAN bus expansion v1.0 nuScenes Request via SUPR Terms
Full dataset v1.0 nuScenes Request via SUPR Terms
Lidarseg v1.0 nuScenes Request via SUPR Terms
Map expansion v1.3 nuScenes Request via SUPR Terms
Panoptic v1.0 nuScenes Request via SUPR Terms
Waymo Open Dataset
Motion Dataset 1.2.1, 1.3.0 Waymo Request via support Terms
Perception Dataset 1.4.3, 2.0.1 Waymo Request via support Terms

User Area

User support

Guides, documentation and FAQ.

Getting access

Applying for projects and login accounts.

System status

Everything OK!

No reported problems

Self-service

SUPR
NSC Express