Abstract:Molecular optimization in drug discovery aims to discover molecules with improved target properties, but practical lead optimization often requires more than high predicted scores. A useful candidate should also be actionable: it should be reachable from known molecules through valid local structural transformations, so that it can be interpreted as a plausible revision within an evolving chemical series. Existing de novo and single-molecule optimization methods do not explicitly model such reachability, especially when both the target molecules and the intermediate molecules connecting them to known compounds are unknown. In this work, we formulate actionable molecular optimization as sequential expansion of a molecule-transfer graph, where nodes are molecules and edges encode valid local transformations. We propose MolWorld, a molecule world model-guided framework that treats the current molecule-transfer graph as an evolving search state. At each iteration, MolWorld selects local anchor contexts, generates candidate molecules conditioned on these contexts, evaluates their properties, and uses a learned world model to update the evolving molecule world by retaining admissible candidates and inserting them into the molecule-transfer graph. The expanded molecule world then guides subsequent optimization. Experiments on property optimization and docking-based tasks show that MolWorld discovers high-property molecules while maintaining substantially stronger structural connectivity, supporting actionable and sequential molecular design.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2605.08954 [cs.LG] |
| (or arXiv:2605.08954v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08954 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yang Qiao [view email]
[v1]
Sat, 9 May 2026 13:50:56 UTC (5,762 KB)