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

archivestring
pathstring
size_bytesinteger
sha256string

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