Timezone: »

Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
Bo Qiang · Yuxuan Song · Minkai Xu · Jingjing Gong · Bowen Gao · Hao Zhou · Wei-Ying Ma · Yanyan Lan

Thu Jul 27 04:30 PM -- 06:00 PM (PDT) @ Exhibit Hall 1 #525
Event URL: https://github.com/qiangbo1222/HierDiff »

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 leads to poor quality in generated structures, especially when generating large molecules. Fragment-based molecule generation is a promising strategy, however, it is nontrivial to be adapted for 3D non-autoregressive generations because of the combinational optimization problems. 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.

Author Information

Bo Qiang (Peking University)
Yuxuan Song (Tsinghua University)
Yuxuan Song

Ph. D. students at AIR, Tsinghua Univerisity. Previous at Bytedance, MSRA, SJTU CS.

Minkai Xu (Stanford University)
Jingjing Gong (Tsinghua University, Tsinghua University)
Bowen Gao (Institute for AI Industry Research, Tsinghua University)
Hao Zhou (Tsinghua University, Tsinghua University)
Wei-Ying Ma (Tsinghua University)
Yanyan Lan (Tsinghua University, Tsinghua University)

More from the Same Authors