AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Taming Generative Co-Folding Prior for Molecular Docking with Diffusion Bridge

Shikun Feng, Zipeng Yang, Qiuyi Li, Mingze Yin, Xiaoyuan Zhang, Tingjun Hou, Yiheng Zhu

NeurIPS 2026 · Probabilistic and scientific modeling › Molecules and proteins · approach: Structure-based molecule design with diffusion

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes adapting a generative co-folding prior (AlphaFold 3-style) to molecular docking via a diffusion bridge, based only on the truncated abstract.

Problem

Molecular docking predicts protein-ligand complex 3D structure conditioned on an input protein (apo for flexible, holo for rigid docking); co-folding models like AlphaFold 3 are accurate but the abstract is truncated before stating their limitation.

Approach

Uses a generative co-folding prior and a diffusion bridge to connect the input receptor state to the predicted complex; specific mechanism not stated in the available abstract.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
model docking as apo-to-holo diffusion bridge instead of noise-to-structureProtenix-Mini AF3 baseline · PoseBusters 20 stepslDDT (%): 84.79 -> 90.41Improved
single-step BridgeDock vs 20-step AF3 baselineBridgeDock · PoseBusters 1 step% ligand RMSD < 2A: 68.61 (20-step AF3) -> 69.86 (1-step)Improved
apo-conditioned fine-tuning without bridge (AF3-SFT-Apo) (ablation)AF3 baseline · PoseBusters 20 steps% ligand RMSD < 2A: 68.61 -> 70.14Improved
add apo-to-holo bridge on top of apo conditioning (ablation)AF3-SFT-Apo · PoseBusters 20 steps% ligand RMSD < 2A: 70.14 -> 73.21Improved
add AF3 alignment (reparameterize bridge states to AF3 denoising schedule) (ablation)BridgeDock · PoseBusters 20 steps% ligand RMSD < 2A: 68.42 -> 73.21Improved
add AF3 alignment (ablation)BridgeDock · PoseBusters 20 stepsmean ligand RMSD (A): 2.77 -> 2.26Improved
BridgeDock vs Protenix baseline on median RMSDBridgeDock · PDBBind testmedian ligand RMSD: 0.99 -> 1.09Hurt
vary diffusion-time offset delta from 1 to 0.001 (ablation)BridgeDock · PoseBusters 20 steps% ligand RMSD < 2A: 71.77 to 73.21No clear effect
use BridgeDock with larger Protenix-Base v1.0.0 backboneBridgeDock-v1 · FoldBench protein-ligandsuccess rate (%): 56.97 -> 59.33Improved
BridgeDock vs pocket-aware docking baselinesBridgeDock · PDBBind test% ligand RMSD < 2A: 42.90 (Re-Dock) -> 71.00Improved

Limitations

Experimental setup

Builds on: AlphaFold 3

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy