Generative Molecular Morphing for Flexible-Size Design via Unbalanced Optimal Transport
For molecular design, this addresses the limitation of fixed-size models in capturing property-size relationships, enabling better property steering and scaffold integration.
Morph introduces a flexible-size generative model for 3D molecular design using unbalanced optimal transport, matching fixed-size SOTA models while enabling out-of-distribution generation where prior models fail.
The success of generative molecular design hinges on a model's steerability toward high-reward samples. Because many molecular properties are intrinsically linked to molecular size, accurately capturing the joint distribution of properties and the number of atoms is essential. However, current diffusion and flow-based models fix the number of atoms, which ultimately limits their ability to navigate this complex relationship. To address this, we introduce Morph, a flexible-size generative model for conditional and unconditional 3D molecular design based on geometric graphs. By dynamically adapting size, Morph can seamlessly integrate existing structural priors, like scaffolds, and significantly enhances property steering. We show that Morph matches current fixed-size state-of-the-art models while offering the benefit of unparalleled sampling flexibility. We demonstrate out-of-distribution generation in regimes where previous models fail, paving the way for enhanced generative modeling for molecular design.