Disentangled autoencoding equivariant diffusion model for controlled generation of 3D molecules

Controlled generation of 3D molecules is highly valuable in drug design, enabling targeted modifications that preserve core structure and binding-relevant geometry while improving developability-related properties. While equivariant diffusion models achieve state-of-the-art de novo 3D molecule generation, reliably controlling multiple molecular properties remains challenging. A key limitation is structural: diffusion models typically lack an explicit latent space for targeted manipulation. We propose a semantics-guided equivariant autoencoding diffusion model that learns a disentangled semantic embedding of 3D molecules via an auxiliary encoder, to achieve fine-grained control over the generative denoising process. This semantic embedding enables efficient retrieval, random generation and controlled generation. By directly manipulating the embedding, we effectively steer the molecular generation toward desired compositions, shapes and physicochemical properties, and further enhance the generation quality with retrieval-augmented generation (RAG) using the embedding as the query. Importantly, the disentangled embedding offers significant advantages for joint manipulation of multiple properties. Experiments demonstrate precise and data-efficient property control while preserving non-targeted properties.