A curated liquid crystal database and machine learning framework for identifying liquid crystal molecules and predicting phase transition temperatures.
We constructed a curated liquid crystal database and developed machine learning models to:
- Identify whether a molecule is a liquid crystal or not
- Predict melting temperature (Tm)
- Predict clearing temperature (Tc)
In addition, we developed a user-friendly web interface for easy access and prediction: http://www.liquidcrystal-predictor.com/
The dataset includes liquid crystal molecules with curated experimentally measured phase transition temperatures. Specifically, the following datasets are provided in the raw_data/ folder:
- Liquid crystal vs. non-liquid crystal classification dataset
- Melting temperature dataset of liquid crystals
- Clearing temperature dataset of liquid crystals
This project is released under the MIT License.