Geometric Relevance Is Not Sufficient: Evaluating Focused Post-Training Supervision in Diffusion Docking
cs.LG, q-bio.BM
Submitted: 2026-11-05
Updated: 2026-11-05
Comments: 17 pages, 5 figures; accepted at the NeurIPS 2026 AI4DD Workshop
License: http://creativecommons.org/licenses/by/4.0/
The gist: Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution…
Terminology
Abstract
Diffusion-based molecular docking requires learning a corrective score field across a broad corruption distribution, yet individual pose errors can differ substantially in their structural consequences. This creates a post-training conflict between preserving broad score-field coverage and concentrating supervision on corrections that appear more relevant to docking geometry. Using DiffDock, a fixed-budget study compares broad continuation with torsional supervision focused on Cartesian consequence or conditional target consistency, and with a broad/focused mixture. Evaluation separates fixed score fidelity, generated-pose quality, best-of-10 sampling capacity, and confidence-selected Top-1 docking performance. At <5 Angstrom, broad continuation had the highest mean Top-1 success among trained policies, and focused or mixed supervision showed no consistent advantage under the tested budget. The starting model had better fixed score fidelity, whereas the evaluated broad-continuation model had higher mean Top-1 success with the same aggregate best-of-10 recovery. Focusing supervision on structurally consequential or more consistently specified corrections did not consistently improve returned-pose success over broad continuation.
Sources
- Uni-Mol Docking V2: Towards Realistic and Accurate Binding Pose Prediction
- PoseBusters: AI-based docking methods fail to generate physically valid poses or generalise to novel sequences
- DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
- Deep Confident Steps to New Pockets: Strategies for Docking Generalization
- AgenticPosesRanker: An Agentic AI Framework for Physically Grounded Ranking of Protein-Ligand Docking Poses
- Assessing the potential of deep learning for protein-ligand docking
- Score-Based Generative Modeling through Stochastic Differential Equations
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis