From Single-Step Edit Response to Multi-Step Molecular Optimization
2026-05-11 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors address the challenge of changing a molecule's structure to achieve a specific property when there are few examples of similar molecules. They propose a new method called SMER, which breaks down molecule changes into small steps and predicts how each step affects the molecule's property. Their approach uses these predictions to plan multiple steps towards the desired result more reliably without relying heavily on complex external evaluations. This helps guide the molecule editing process more efficiently.
molecular optimizationchemical feasibilityedit predictionproperty shiftoracle-in-the-looptree searchstructural editsdirectional evaluationtrajectory planningweak supervision
Authors
Haojie Rao, Kun Li, Yida Xiong, Jiameng Chen, Wenbin Hu, Yizhen Zheng, Jiajun Yu, Duanhua Cao
Abstract
Conditional molecular optimization aims to edit a molecule to realize a specified property shift. In practice, structurally similar molecule data is scarce, while decisions are inherently action-level: at each step, the system must select one local structural edit from a candidate set that is strictly filtered by chemical feasibility rules. This level mismatch between supervision and decision makes oracle-in-the-loop search unstable in molecular optimization. Regressing on property differences between molecule pairs improves data efficiency but relies on oracle-in-the-loop search, entangling transformation effects with global context and providing limited guidance for selecting the next feasible edit, often resorting to oracle-in-the-loop search. For this reason, we propose a response-oriented discrete edit optimization approach comprising two tightly coupled components: a single-step molecular edit response predictor (SMER) and a multi-step planner that composes local predictions into optimization trajectories via guided tree search (SMER-Opt). The approach learns a directional evaluation model over edit actions to support constraint-aware planning. It mines weakly related molecule pairs and decomposes their structural differences into minimal edit units, turning endpoint property annotations into process-level supervision and yielding reusable, transferable action primitives. A directional edit evaluator then scores feasible candidate edits by their likelihood of moving the molecule toward the desired property change, substantially reducing dependence on external evaluator queries at decision time. Code is available at https://anonymous.4open.science/r/SMER.