Unified Molecule Generation and Property Prediction

Modeling the joint distribution of the data samples and their properties allows to construct a single model for both data generation and property prediction, with synergistic capabilities 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 mask together with a unified pre-training scheme. We show that Hyformer rivals other joint models, as well as state-of-the-art molecule generation and property prediction models. Additionally, we show the benefits of joint modeling in downstream tasks of molecular representation learning, hit identification and antimicrobial peptide design.

@article{izdebski2025_2504.16559,
  title={ Unified Molecule Generation and Property Prediction },
  author={ Adam Izdebski and Jan Olszewski and Pankhil Gawade and Krzysztof Koras and Serra Korkmaz and Valentin Rauscher and Jakub M. Tomczak and Ewa Szczurek },
  journal={arXiv preprint arXiv:2504.16559},
  year={ 2025 }
}