CITATION.bib

@Article{D2DD00058J,
author ="Winter, Benedikt and Winter, Clemens and Schilling, Johannes and Bardow, André",
title  ="A smile is all you need: predicting limiting activity coefficients from SMILES with natural language processing",
journal  ="Digital Discovery",
year  ="2022",
pages  ="-",
publisher  ="RSC",
doi  ="10.1039/D2DD00058J",
url  ="http://dx.doi.org/10.1039/D2DD00058J",
abstract  ="The knowledge of mixtures’ phase equilibria is crucial in nature and technical chemistry. Phase equilibria calculations of mixtures require activity coefficients. However{,} experimental data on activity coefficients are often limited due to the high cost of experiments. For an accurate and efficient prediction of activity coefficients{,} machine learning approaches have been recently developed. However{,} current machine learning approaches still extrapolate poorly for activity coefficients of unknown molecules. In this work{,} we introduce a SMILES-to-properties-transformer (SPT){,} a natural language processing network{,} to predict binary limiting activity coefficients from SMILES codes. To overcome the limitations of available experimental data{,} we initially train our network on a large dataset of synthetic data sampled from COSMO-RS (10 million data points) and then fine-tune the model on experimental data (20 870 data points). This training strategy enables the SPT to accurately predict limiting activity coefficients even for unknown molecules{,} cutting the mean prediction error in half compared to state-of-the-art models for activity coefficient predictions such as COSMO-RS and UNIFACDortmund{,} and improving on recent machine learning approaches."}