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