AUTHOR=Mayr Fritz , Wieder Marcus , Wieder Oliver , Langer Thierry 

TITLE=Improving Small Molecule pKa Prediction Using Transfer Learning With Graph Neural Networks

JOURNAL=Frontiers in Chemistry

VOLUME=10

YEAR=2022

URL=https://www.frontiersin.org/journals/chemistry/articles/10.3389/fchem.2022.866585

DOI=10.3389/fchem.2022.866585

ISSN=2296-2646

ABSTRACT=<p>Enumerating protonation states and calculating microstate pK<sub><italic>a</italic></sub> values of small molecules is an important yet challenging task for lead optimization and molecular modeling. Commercial and non-commercial solutions have notable limitations such as restrictive and expensive licenses, high CPU/GPU hour requirements, or the need for expert knowledge to set up and use. We present a graph neural network model that is trained on 714,906 calculated microstate pK<sub><italic>a</italic></sub> predictions from molecules obtained from the ChEMBL database. The model is fine-tuned on a set of 5,994 experimental pK<sub><italic>a</italic></sub> values significantly improving its performance on two challenging test sets. Combining the graph neural network model with Dimorphite-DL, an open-source program for enumerating ionization states, we have developed the open-source Python package pkasolver, which is able to generate and enumerate protonation states and calculate pK<sub><italic>a</italic></sub> values with high accuracy.</p>