FORGE code, trained models and source data for RNA tertiary-structure information mapping
Code, trained model artifacts, processed result tables, public-input manifests and figure source data supporting the manuscript "FORGE audits residue-level information encoded in RNA tertiary-structure geometry". The release contains the FORGE feature-extraction and analysis code, trained XGBoost model files for nucleotide identity and auxiliary atlas tasks, locked result artifacts used by the manuscript figures and tables, and manifests for the public PDB/Rfam/OpenKnot-derived inputs. Raw PDB/mmCIF coordinate caches and full third-party software repositories are not redistributed; they are identified by accession/source manifests and can be retrieved from their original public repositories. Version 0.2.0 adds the AlphaFold 3 forward-folding control supporting the Nature Machine Intelligence resubmission: raw AlphaFold 3 server job outputs for the four solved AI-designed pseudoknot constructs (real, FORGE-derived and R-Net-refined sequence classes), batch job requests, fine-grained comparison metrics (P-RMSD, secondary-structure F1, contact recovery), R-Net-guided refinement artifacts, forward-folding figures and the NMI manuscript LaTeX source. Zenodo record 22764225, published 2026-09-15, 13 file(s) totalling 207.4 MB (6 tabular, 4 other, 3 archive).
- Category
- Structural Biology
- Provider
- Leighton Gow and 3 others
- License
- CC-BY-4.0
- DOI
- 10.5281/zenodo.22764225
- Hosted on
- Zenodo
- Access
- Free and public. No account with the data provider is needed.
- Source
- https://doi.org/10.5281/zenodo.22764225
Data structure and loading code
Fields
archive | string |
path | string |
size_bytes | integer |
sha256 | string |
Files
Example file: https://zenodo.org/api/records/22764225/files/zenodo_file_manifest.tsv/content
Path pattern: Flat Zenodo record: every file hangs directly off the record, no directory tree.
Load the data
import pandas as pd
# zenodo_file_manifest.tsv (4.8 MB) streamed straight from Zenodo.
df = pd.read_csv("https://zenodo.org/api/records/22764225/files/zenodo_file_manifest.tsv/content", sep="\t", low_memory=False)
print(df.shape)
df.head()Written for a Scigantic notebook, where /mnt/archive is the mounted dataset.
Analyze this dataset without downloading it
On Scigantic, FORGE code, trained models and source data for RNA tertiary-structure information mapping opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.
Related Structural Biology datasets
- CryoET Data Portal 10453: Isolated Synaptic Vesicles from Mouse Brain
- CZII CryoET Object Identification Challenge: Experimental Training Tomograms with Particle Labels
- afMLevel: paired raw and levelled atomic force microscopy height images with foreground masks
- CryoET Data Portal 10004: C. elegans Serial Lift-Out Tomograms of Whole Worms
- Disclosing Pathogenic Variant Effects on the Structural Dynamics of the VAPB MSP Domain Causing Familial ALS
- CATH v4.4.0 protein domain classification with an S35-aware train/test split
- Processed data and analysis results for 104 RBPs
- Structural analyses define the molecular basis of clusterin chaperone function