MOF-AABBA

This repository contains scripts for generating AABBA autocorrelation vectors for metalorganic frameworks (MOFs) and is associated to the publication Machine Learning the Hydrogen Adsorption Capacity of Metal Organic Frameworks.

Setup

Start by cloning this repository on your machine. Next, navigate into the root directory of the project and run the following command in order to install the required environment.

conda env create -f env.yml

To generate featurized graphs of your MOFs run the command

python get_featurized_graphs.py cif_dir/

where cif_dir/ is the directory with your CIF files. This will automatically create a folder featurized_graphs/ containing the featurized graphs as pickle files. To obtain the corresponding AABBA autocorrelations run

python get_autocorrelations.py featurized_graphs/

The autocorrelation vectors will be saved into a CSV file autocorrelations.csv.