Diffusion models in de novo drug design

A Alakhdar, B Poczos, N Washburn - Journal of Chemical …, 2024 - ACS Publications
Diffusion models have emerged as powerful tools for molecular generation, particularly in
the context of 3D molecular structures. Inspired by nonequilibrium statistical physics, these …

SurfDock is a surface-informed diffusion generative model for reliable and accurate protein–ligand complex prediction

D Cao, M Chen, R Zhang, Z Wang, M Huang, J Yu… - Nature …, 2024 - nature.com
Accurately predicting protein–ligand interactions is crucial for understanding cellular
processes. We introduce SurfDock, a deep-learning method that addresses this challenge …

Ligand-Conditioned Side Chain Packing for Flexible Molecular Docking

D Luo, X Qu, D Lu, Y Wang, L Dong… - Journal of Chemical …, 2025 - ACS Publications
Molecular docking is a crucial technique for elucidating protein–ligand interactions. Machine
learning-based docking methods offer promising advantages over traditional approaches …

Flexible docking via unbalanced flow matching

G Corso, VR Somnath, N Getz, R Barzilay… - ICML'24 Workshop …, 2024 - openreview.net
Diffusion models have emerged as a recent successful paradigm for molecular docking.
However, these methods treat the protein either as a rigid structure, or force the model to fold …

ApoDock: Ligand-Conditioned Sidechain Packing for Flexible Molecular Docking

D Luo, X Qu, D Lu, Y Wang, L Dong, B Wang - bioRxiv, 2024 - biorxiv.org
Molecular docking is a crucial technique for elucidating protein-ligand interactions. Machine
learning-based docking methods offer promising advantages over traditional approaches …

[PDF][PDF] Energy-Based Flow Matching for Molecular Docking

W Zhou, CI Sprague, H Azizpour - mlsb.io
Molecular docking, which predicts the bound structure of protein-ligand conformations, is
essential for structure-based drug design. Recent advances in generative modeling, such as …