ANI-2x Conformers Recomputed at wB97M-D3(BJ)/def2-TZVPP, ColabFit Conversion
- Provider
- Huddleston, Zubatyuk, Smith, Roitberg, Isayev, Pickering, Devereux, Barros (ANI-2x); ColabFit conversion
- License
- CC-BY-4.0 (source)
- Size
- 98 files
- Format
- Parquet (in sampled files)
- Stored at
- Hugging Face (https://huggingface.co/datasets/colabfit/ANI-2x-wB97MD3BJ-def2TZVPP)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.5281/zenodo.10108942
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1021/acs.jctc.0c00121
About ANI-2x Conformers Recomputed at wB97M-D3(BJ)/def2-TZVPP, ColabFit Conversion
The ANI-2x organic conformer set recomputed in ORCA at the range-separated meta-GGA hybrid wB97M with D3 dispersion and Becke-Johnson damping, def2-TZVPP basis. Molecules have 2 to 63 atoms over H, C, N, O, S, F and Cl and come from the ANI-2x active-learning sampling of torsions, dimers and off-equilibrium geometries. ColabFit counts 9,649,788 configurations and about 146.7 million atoms labelled with total energies; uncorrected SCF energies and dipoles are kept in the metadata, and configuration sets are divided by molecule size. It is the highest-accuracy dispersion-corrected label set in the ANI-2x Zenodo release and pairs with the wB97X/6-31G(d), wB97M-V and B97-3c versions on identical geometries, which makes it useful for delta-learning and for checking how much a potential depends on the reference functional. This is the ColabFit Exchange conversion: configurations sit in Parquet files under co/ (positions, cell, species, 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 schema at materials.colabfit.org/docs. Released by the authors on Zenodo under CC-BY-4.0; cite Devereux et al., J. Chem. Theory Comput. 2020.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/ANI-2x-wB97MD3BJ-def2TZVPP")
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, ANI-2x Conformers Recomputed at wB97M-D3(BJ)/def2-TZVPP, 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
- Hydrogen Combustion Reaction Channels (wB97X-V IRC, AIMD and Normal Modes), ColabFit Conversion
- Pure Magnesium (Mg) DFT Reference Set for Neural Network Potential Fitting (Yin, Stricker and Curtin 2020, Materials Cloud), ColabFit Conversion
- WS22 SMA, 2-(1-(methylimino)methyl)phenol (C8H9NO): Wigner-Sampled Conformations with PBE0 Energies and Forces (Pinheiro Jr et al. 2023, Zenodo), ColabFit Conversion
- Li-Ion Diffusion Barriers in Disordered Rock-Salt Li(2-x)VO2F Oxyfluorides: NEB DFT (Chang et al. 2021, Materials Cloud), ColabFit Conversion
- Ca Migration in Brownmillerite Ca2Fe2O5, Ca2Mn2O5 and Marokite CaMn4O8: DFT for Calcium-Ion Batteries (Arroyo-de Dompablo 2019, Materials Cloud), ColabFit Conversion
- Open Molecules 2025 (OMol25) Full Training Set, ColabFit Conversion
- Halide Perovskite Ion Migration MLFF neutral iodide interstitial
- Benzene Crystal Polymorphs: Thermalized PBE-TS DFT Snapshots (Kapil and Engel 2022), ColabFit Conversion