Generate ionic liquids with low-melting points

Installation

conda env create -f environment.yml
conda activate moima

Training

This project including three parts:

1. Expand the collected IL database by link prediction.

python step1_link_prediction/run.py

2. Train a VAE model to generate ILs.

python step2_vae_generation/train_vae.py

3. Train a melting point classification model for post-filtering.

python step3_post_filtering/train_logistic.py

I have also include the pre-trained models under each folder. So you can skip the above process if you just want to sample new ILs

Sampling

You can sample new ILs by running the following command:

python sample.py

How to cite

@article{D5DD00282F,
  author = {Ren, Gaopeng and Mroz, Austin and Philippi, Frederik and Welton, Tom and Jelfs, Kim E},
  doi = {10.1039/D5DD00282F},
  journal = {Digit. Discov.},
  pages = {--},
  publisher = {RSC},
  title = {{Deep learning-enabled discovery of low-melting-point ionic liquids}},
  url = {http://dx.doi.org/10.1039/D5DD00282F},
  year = {2025}
}