Chig-AIMD Scaffold Split (Train): DFT Energies and Forces for Chignolin Protein Conformations, ColabFit Conversion
- Provider
- Tong Wang, Xinheng He, Mingyu Li, Bin Shao, Tie-Yan Liu (Microsoft Research); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 5 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/Chig-AIMD_scaffold_train)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.60732/facc4255
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1038/s41597-023-02465-9
About this dataset
The training portion of the scaffold split of AIMD-Chig, released by Microsoft Research to train and test machine learning force fields on a whole protein. The authors ran replica exchange molecular dynamics (REMD), conventional MD and ab initio MD on chignolin, a 10-residue (166-atom) mini-protein, and collected about 2 million conformations with DFT energies and forces. The random split is listed separately. The ColabFit card counts 1,592,662 configurations and about 264 million C, H, N and O atoms; the repository is about 26 GB (measured 2026-11-19). This is the ColabFit Exchange conversion: configurations are Parquet files under co/ (structure, positions, cell, computed properties and metadata per row) with dataset-level information in ds.parquet; read them with pyarrow, pandas, polars or Hugging Face datasets, following the ColabFit configuration schema at materials.colabfit.org/docs. The original Figshare record is released under CC BY 4.0; cite Wang et al., Scientific Data 2023.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/Chig-AIMD_scaffold_train")
print(ds)Data structure
File types in sampled files: Parquet
Files
Example file: co/co_0.parquet
Analyze this dataset without downloading it
On Scigantic, Chig-AIMD Scaffold Split (Train): DFT Energies and Forces for Chignolin Protein Conformations, ColabFit Conversion 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.
This page is also available as Markdown and as JSON.
Related Chemistry & Materials datasets
- Cd- and Zn-Doped CsPbI3 Perovskite Energetics: DFT Training Set for GNN Stability Prediction (Eremin et al., AIRI), ColabFit Conversion
- CO2 Hydrogenation to Methanol on In2O3 and Pt-Doped In2O3: ML Force Field Training Data (Schaaf et al. 2023), ColabFit Conversion
- Vector-QM24 (VQM24): DFT Data for 836k Small Molecules, ColabFit Conversion
- WS22 Thymine (C5H6N2O2): Wigner-Sampled Conformations with PBE0 Energies and Forces (Pinheiro Jr et al. 2023, Zenodo), ColabFit Conversion
- QM9x: QM9 Recomputed at wB97X/6-31G(d) with Forces, ColabFit Conversion
- Open Molecules 2025 (OMol25) Neutral Training Set, ColabFit Conversion
- Mo-Nb-Ta-V-W Refractory High-Entropy Alloy tabGAP Training Data: DFT (Byggmästar et al. 2021, Fairdata), ColabFit Conversion
- Oxygen-Vacancy Defects in Cuprous Oxide Cu2O(111) Surfaces: DFT Slabs, ColabFit Conversion