RIDE: Reference-Anchored Inference-Time Diffusion Editing for Scaffold Hopping

2026-09-28

AI Summary

This study addresses the challenge in diffusion-based molecular scaffold hopping of balancing two-dimensional (2D) structural novelty with three-dimensional (3D) shape preservation. To this end, we propose RIDE (Reasoning-time Inference Diffusion Editing), a framework that restores reference noise trajectories, selects editing segments, and employs value-guided sampling. This approach maintains 3D similarity without requiring explicit rewards while remaining compatible with diverse reward functions. Experimental results demonstrate that, compared to baseline methods, RIDE reduces 2D similarity by 11.7% and improves 3D similarity by 7.3%, successfully generating structurally diverse novel molecules with highly matched 3D shapes.

Abstract

Scaffold hopping is a critical task in drug discovery, which seeks to discover new, structurally distinct molecules that share key functional groups and similar 3D shape with a reference binding ligand. Existing diffusion-based scaffold hopping methods formulate the problem as conditional generation of scaffolds given the functional groups. However, they lack a principled mechanism to jointly enforce 2D structural novelty and preserve the 3D shape of the reference ligand. Here, we introduce RIDE, a Reference-anchored Inference-time Diffusion Editing framework for scaffold hopping. RIDE recovers the reference diffusion noise trajectory conditioned on the binding pocket and functional groups, selects an optimal trajectory segment for editing via noise perturbation, and conducts a value-guided scaffold sampling to generate new scaffolds. Extensive experimental results demonstrate that, compared to baselines, RIDE consistently generates scaffolds with lower 2D similarity and higher 3D similarity to the reference, with an average improvements of 11.7% and 7.3%, respectively. Further analysis reveals that RIDE can accommodate various reward functions, and can preserve 3D similarity even when this is not explicitly included in the reward. Two case studies illustrate RIDE's ability to generate distinct scaffolds with different structures and properties, and its ability to introduce substantial 2D variation while maintaining very high 3D similarity. RIDE is publicly available at https://anonymous.4open.science/r/RIDE-C8A0.

Problem

• Scaffold Hopping
• Drug Discovery
• Diffusion Models
• 3D Shape Similarity
• 2D Structural Novelty

Innovation

• Scaffold Hopping
• Diffusion Editing
• Inference-Time Guidance
• Value-Guided Sampling
• Drug Discovery