Command Palette
Search for a command to run...
MOF Property Diversity Metal-Organic Framework Property Dataset
MOF Property Diversity is a Metal-Organic Framework (MOF) property dataset released in 2026, designed to provide representative MOF data for materials informatics research and to support tasks such as material property analysis, clustering, and machine learning.
The dataset contains 900 representative MOF samples, covering information on electronic properties, pore structures, material composition, and property diversity, including key attributes such as PBE band gap, PLD (Pore Limiting Diameter), and LCD (Largest Cavity Diameter).
Dataset Composition
- MOF Identification Information: Includes MOF identifiers and chemical formulas.
- PBE Band Gap: Band gaps calculated using the PBE method, ranging approximately from 0.10 – 6.45 eV.
- PLD: Pore Limiting Diameter.
- LCD: Largest Cavity Diameter.
- Pore Accessibility Ratio: Pore accessibility ratio, calculated from PLD/LCD.
- Elemental Composition Proportions: Includes composition proportions of different elements and metal atom proportions.
- Molecular Weight: Molecular weights calculated based on MOF chemical formulas.
- Atomic Number and Atomic Mass Statistics: Includes statistical features of atomic numbers and atomic masses.
- Composition Entropy: Features used to describe the diversity of MOF chemical compositions.
- Band Gap and Pore Size Grouping: Records grouping information of samples in the band gap and pore size space.
- Diversity Selection Basis: Records the selection basis for samples included in the corresponding diversity categories.
- Diversity Percentile: Records the diversity percentile of samples in the relevant attribute space.
The dataset performs diversity sample selection from three complementary property dimensions:
- Electronic Diversity: 287 MOFs.
- Pore Diversity: 309 MOFs.
- Composition Diversity: 304 MOFs.
Citation
@misc{abdullah_khan_2026,
title={MOF Property Diversity Dataset},
url={https://www.kaggle.com/dsv/18877606},
DOI={10.34740/KAGGLE/DSV/18877606},
publisher={Kaggle},
author={Abdullah Khan},
year={2026}
}
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.