Semi-Supervised Junction Tree Variational Autoencoder for Molecular Property Prediction
This work addresses molecular property prediction for drug discovery and computational chemistry, offering an incremental improvement by incorporating semi-supervised learning into an existing generative model.
The authors tackled the problem of molecular property prediction with limited labeled data by proposing SeMole, a semi-supervised method that augments Junction Tree Variational Autoencoders, and demonstrated its benefits on the ZINC dataset with three molecular properties.
Molecular Representation Learning is essential to solving many drug discovery and computational chemistry problems. It is a challenging problem due to the complex structure of molecules and the vast chemical space. Graph representations of molecules are more expressive than traditional representations, such as molecular fingerprints. Therefore, they can improve the performance of machine learning models. We propose SeMole, a method that augments the Junction Tree Variational Autoencoders, a state-of-the-art generative model for molecular graphs, with semi-supervised learning. SeMole aims to improve the accuracy of molecular property prediction when having limited labeled data by exploiting unlabeled data. We enforce that the model generates molecular graphs conditioned on target properties by incorporating the property into the latent representation. We propose an additional pre-training phase to improve the training process for our semi-supervised generative model. We perform an experimental evaluation on the ZINC dataset using three different molecular properties and demonstrate the benefits of semi-supervision.