# Zeo-1: DFT Energies and Stresses for Zeolite Frameworks from the IZA Database, ColabFit Conversion

## Facts

- Provider: Leonid Komissarov and Toon Verstraelen (Ghent University); ColabFit conversion
- License: CC-BY-4.0 (https://archive.materialscloud.org/records/3xmh2-vv758)
- Size: 4 files
- Format: Parquet (in sampled files)
- Stored at: Hugging Face, https://huggingface.co/datasets/colabfit/Zeo-1_SD_2022
- Access: public, readable without an account
- DOI: https://doi.org/10.60732/7eb1fefb
- Category: Chemistry & Materials
- Source: https://doi.org/10.1038/s41597-022-01160-5
- Page: https://scigantic.com/archive/ab651afb-72d0-5f74-9e4c-156f5badfe02
- Keywords: Chemistry & Materials, DFT, Parquet, Hugging Face

## About

Zeo-1 is a computational dataset of zeolite structures built by Komissarov and Verstraelen (Ghent University) to train machine learning potentials for microporous aluminosilicates and related frameworks. Structures come from the Database of Zeolite Structures of the International Zeolite Association (IZA), with calculations run in the Amsterdam Modeling Suite (AMS). Each configuration carries a total energy and the Cauchy stress tensor. The ColabFit card counts 12,929 unique configurations and about 1.84 million atoms over 15 elements (Al, Ba, Be, C, Ca, Cs, F, Ge, H, K, Li, N, Na, O, Si); the repository is about 228 MB (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 Materials Cloud Archive record is released under CC-BY-4.0; cite Komissarov and Verstraelen, Scientific Data 2022.

## Load the data

```python
from datasets import load_dataset
ds = load_dataset("colabfit/Zeo-1_SD_2022")
print(ds)
```

## Data structure

File types in sampled files: Parquet

Example file: `co/co_0.parquet`

## Open it

- In a hosted notebook with the data mounted: https://scigantic.com/archive/ab651afb-72d0-5f74-9e4c-156f5badfe02
- Full record as JSON (schema card included): https://api.scigantic.com/api/archives/ab651afb-72d0-5f74-9e4c-156f5badfe02
- Over MCP: `get_schema_card` with id `ab651afb-72d0-5f74-9e4c-156f5badfe02` at https://api.scigantic.com/mcp

## Related topics

- [Parquet datasets](https://scigantic.com/topics/parquet)
- [Chemistry & Materials datasets](https://scigantic.com/topics/chemistry-and-materials)
- [DFT datasets](https://scigantic.com/topics/dft)
