Synergistic Benefits of Joint Molecule Generation and Property Prediction
By: Adam Izdebski , Jan Olszewski , Pankhil Gawade and more
Potential Business Impact:
Builds new medicines by learning and predicting.
Modeling the joint distribution of data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic benefits reaching beyond purely generative or predictive models. However, training joint models presents daunting architectural and optimization challenges. Here, we propose Hyformer, a transformer-based joint model that successfully blends the generative and predictive functionalities, using an alternating attention mechanism and a joint pre-training scheme. We show that Hyformer is simultaneously optimized for molecule generation and property prediction, while exhibiting synergistic benefits in conditional sampling, out-of-distribution property prediction and representation learning. Finally, we demonstrate the benefits of joint learning in a drug design use case of discovering novel antimicrobial~peptides.
Similar Papers
Improved Molecular Generation through Attribute-Driven Integrative Embeddings and GAN Selectivity
Machine Learning (CS)
Creates new molecules with special features.
All You Need Is Synthetic Task Augmentation
Machine Learning (CS)
Teaches computers to guess molecule traits better.
Transformers for molecular property prediction: Domain adaptation efficiently improves performance
Machine Learning (CS)
Finds better medicines faster by learning from drug data.