PROBE：先探测再编辑，面向 LLM 智能体的基于结构药物设计分子优化框架

View PDF HTML (experimental)

Abstract:Structure-based drug design increasingly employs LLM agents to iteratively refine ligands against a target pocket, yet a viable ligand must satisfy two often-conflicting objectives---binding affinity and druggability---which single optimization steps rarely improve together. To quantify this difficulty, we introduce two diagnostic metrics: the first measures how often a single edit improves both objectives, and the second measures how often a gain on one objective comes with a loss on the other. Applying these diagnostics to current LLM-agent pipelines exposes a consistent failure mode: the agent performs molecular editing without knowing how the pocket-ligand complex responds to local modifications, thus rarely achieving joint improvement. Inspired by medicinal chemists, who probe the pocket-ligand complex with controlled analog edits before choosing an optimization direction, we propose \textbf{PROBE}, an optimization framework built around edit--response probing. PROBE first decomposes the ligand into editable sites and builds a pocket-specific \textbf{site map} that flags where joint gains are plausible, where the two objectives are likely in tension, and where liability substructures should be changed; it then performs controlled probe edits whose responses are distilled into an \textbf{EditManual}. Guided by the site map and EditManual, PROBE runs an iterative multi-agent optimization loop. On the CrossDocked2020 benchmark, PROBE achieves state-of-the-art performance and substantially mitigates the failure modes exposed by our diagnostics metrics. Codes are in this https URL

Submission history

From: Zaifei Yang [view email]
[v1] Sat, 30 May 2026 06:06:51 UTC (972 KB)
[v2] Tue, 2 Jun 2026 07:09:41 UTC (970 KB)
[v3] Fri, 23 Oct 2026 13:42:47 UTC (988 KB)