From Single-Step Edit Response to Multi-Step Molecular Optimization

TL;DR

This paper introduces SMER-Opt, a novel approach for molecular optimization that combines a response predictor with a guided tree search to efficiently generate property-shifting molecule edits.

Contribution

It proposes a response-oriented discrete edit optimization framework with a directional evaluation model and a multi-step planner, improving stability and data efficiency in molecular design.

Findings

Reduces dependence on oracle-in-the-loop search during optimization.

Learns transferable action primitives from weakly related molecule pairs.

Scores candidate edits based on their likelihood to achieve property changes.

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.