Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
Jul 24, 2023
Speakers
Yuxuan Song
Speaker · 0 followers
Jingjing Gong
Speaker · 0 followers
Wei-Ying Ma
Speaker · 0 followers
Yanyan Lan
Speaker · 0 followers
About
Generating desirable molecular structures in 3D is a fundamental problem for drug discovery. Despite the considerable progress we have achieved, existing methods usually generate molecules in atom resolution and ignore intrinsic local structures such as rings, which however are ubiquitous in drug-like biomolecules. Such problems make current methods suffer from poor valid rates for generated structures, especially when generating large molecules. In this paper, we utilize a coarse-to-fine strategy to tackle this problem, in which a Hierarchical Diffusion-based model (i.e. HierDiff) is proposed to preserve the validity of local segments without relying on autoregressive modeling. Specifically, HierDiff first generates coarse-grained molecule geometries via an equivariant diffusion process, where each coarse-grained node reflects a fragment in a molecule. Then the coarse-grained nodes are decoded into fine-grained fragments by a message-passing process and a newly designed iterative refined sampling module. Lastly, the fine-grained fragments are then assembled to derive a complete atomic molecular structure. Extensive experiments demonstrate that HierDiff consistently improves the quality of molecule generation over existing methods.Generating desirable molecular structures in 3D is a fundamental problem for drug discovery. Despite the considerable progress we have achieved, existing methods usually generate molecules in atom resolution and ignore intrinsic local structures such as rings, which however are ubiquitous in drug-like biomolecules. Such problems make current methods suffer from poor valid rates for generated structures, especially when generating large molecules. In this paper, we utilize a coarse-to-fine strat…
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
On the Robustness of Randomized Ensembles to Adversarial Perturbations
Watch later
Hassan Dbouk, …
Memory-Based Dual Gaussian Processes for Sequential Learning
Watch later
Paul Chang, …
Dual Propagation: Accelerating Contrastive Hebbian Learning with Dyadic Neurons
Watch later
