ANI-2x at wB97X/def2-TZVPP: 8.5 Million Organic Molecule DFT Energies, ColabFit Conversion
- Provider
- Devereux, Smith, Huddleston, Barros, Zubatyuk, Isayev, Roitberg; 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-wB97X-def2TZVPP)
- Access
- Free and public. No account with the data provider is needed.
- DOI
- 10.60732/61569e2c
- Category
- Chemistry & Materials
- Source
- https://doi.org/10.1021/acs.jctc.0c00121
About this dataset
The wB97X/def2-TZVPP portion of the ANI-2x release from the Roitberg and Isayev groups: DFT energies for structures of 2 to 63 atoms containing H, C, N, O, S, F and Cl, recomputed in ORCA with the larger def2-TZVPP basis set. ANI-2x extends ANI-1x with sulfur and halogens and is used to train ANI and other transferable neural network potentials for drug-like chemistry. Configuration sets are divided by the number of atoms per structure, and dipoles are kept in the metadata. The ColabFit card counts 8,481,522 configurations and about 128 million atoms; the repository is about 13.4 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), configuration sets under cs/ with their mapping in cs_co_map/, 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 ANI-2x Zenodo release is CC-BY-4.0; cite Devereux et al., JCTC 2020.
How to load this dataset in Python
from datasets import load_dataset
ds = load_dataset("colabfit/ANI-2x-wB97X-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 at wB97X/def2-TZVPP: 8.5 Million Organic Molecule DFT Energies, 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
- Transition1x Training Split: Reaction Pathway DFT Energies and Forces, ColabFit Conversion
- Liquid Water and Ice Ih/Ic at Hybrid DFT (revPBE0-D3): Neural Network Training Set for Ab Initio Thermodynamics (Cheng et al. 2019, Materials Cloud), ColabFit Conversion
- UNEP-v1: 16-Element Metal and Alloy DFT Training Set for a Unified NeuroEvolution Potential, ColabFit Conversion
- (Ti:Mo)S2 Binary Alloy Phase Behavior: DFT Training Set for Cluster Expansion (Silva, Polcar and Kramer, Southampton), ColabFit Conversion
- Halide Perovskite Ion Migration MLFF phase transition
- ANI-2x wB97X/6-31G(d) Organic Molecule Conformers, ColabFit Conversion
- Lithium Titanate (Li4Ti5O12) Li-Ion Migration Paths and Simulated EELS, DFT Data, ColabFit Conversion
- CeO2 Surface Oxygen Vacancy MLFF