Transfer learning graph representations of molecules for pKa, 13C-NMR, and solubility
Open Access
- 1 April 2024
- journal article
- research article
- Published by Canadian Science Publishing in Canadian Journal of Chemistry
- Vol. 102 (4) , 275-288
Abstract
We explore transfer learning models from a pre-trained graph convolutional neural network representation of molecules, obtained from SchNet, to predict 13C-NMR, pKa, and log S solubility. SchNet learns a graph representation of a molecule by associating each atom with an “embedding vector” and interacts the atom-embeddings with each other by leveraging graph convolutional filters on their interatomic distances. We pre-trained SchNet on molecular energy and demonstrate that the pre-trained atomistic embeddings can then be used as a transferable representation for a wide array of properties. On the one hand, for atomic properties such as micro-pK1 and 13C-NMR, we investigate two models, one linear and one neural net, that input pre-trained atom-embeddings of a particular atom (e.g. carbon) and predict a local property (e.g., 13C-NMR). On the other hand, for molecular properties such as solubility, a size-extensive graph model is built using the embeddings of all atoms in the molecule as input. For all cases, qualitatively correct predictions are made with relatively little training data (<1000 training points), showcasing the ease with which pre-trained embeddings pick up on important chemical patterns. The proposed models successfully capture well-understood trends of pK1 and solubility. This study advances our understanding of current neural net graph representations and their capacity for transfer learning applications in chemistry.Keywords
All Related Versions
Funding Information
- Canada Research Chairs
- Natural Sciences and Engineering Research Council of Canada (RGPIN-2020-04306)
- Canada Foundation for Innovation (JELF)
- New Brunswick Innovation Foundation (RAI2019-020)
This publication has 73 references indexed in Scilit:
- Prediction of chemical shift in NMR: A reviewMagnetic Resonance in Chemistry, 2021
- Transfer learning for solvation free energies: From quantum chemistry to experimentsChemical Engineering Journal, 2021
- Learning Representations of Molecules and Materials with Atomistic Neural Networks2020
- NMR signal processing, prediction, and structure verification with machine learning techniquesMagnetic Resonance in Chemistry, 2020
- An explicit-solvent hybrid QM and MM approach for predicting pKa of small molecules in SAMPL6 challengeJournal of Computer-Aided Molecular Design, 2018
- Facilitating quality control for spectra assignments of small organic molecules: nmrshiftdb2 – a free in‐house NMR database with integrated LIMS for academic service laboratoriesMagnetic Resonance in Chemistry, 2015
- Principal component analysisWIREs Computational Statistics, 2010
- SPARTA+: a modest improvement in empirical NMR chemical shift prediction by means of an artificial neural networkJournal of Biomolecular NMR, 2010
- QSPR Prediction of pKa for Benzoic Acids in Different SolventsQSAR & Combinatorial Science, 2008
- Neural Network Based QSPR Study for Predicting pKa of Phenols in Different SolventsQSAR & Combinatorial Science, 2007