RosettaCommons / RosettaCommons/foundry
[BUG] RFD3 is missing training data artifacts
Open
@r-krishna is already working on this.
Since May 8, 2026.
bug
- Dominant language
- Python
- Stars
- 966
- Forks
- 181
- Avg merge
- 4d 4h
- Merged PRs (30d)
- 2
Description
Describe the bug
RFD3's training resources contain most of the required materials for others to reproduce its results. However, a few key data artifacts are currently missing, which makes exact reproducibility unattainable for the time being.
Expected behavior
In no particular order, the following data artifacts (i.e., data files or datasets) should be publicly available for download, to make RFD3's training fully reproducible.
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/train/pdb/na_complex_distillation.yaml#L12
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/train/rfd3_monomer_distillation.yaml#L21
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/val_examples/bcov_ppi_easy_medium_with_ori.yaml#L4-L151
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/dna_binder_design5.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/dna_binder_long.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/dna_binder_short.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/indexed.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/mcsa_41_short_rigid.yaml#L9
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/mcsa_41.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/sm_binder_hbonds_short.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/sm_binder_hbonds.yaml#L6
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/unconditional_deep.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/unconditional.yaml#L6
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/datasets/val/unindexed.yaml#L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/paths/data/default.yaml#L6-L7
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/paths/data/default.yaml#L12-L13
- https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/paths/data/default.yaml#L18
- (Probably optional): https://github.com/RosettaCommons/foundry/blob/cee116dc5598d2c0c6087701914c5185aac98b48/models/rfd3/configs/paths/data/default.yaml#L16
Additional context
Thank you for open-sourcing RFD3's code and configs! These are significant resources from which the research community has already begun benefitting.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.