哪些信息能在蛋白口袋间迁移？智能体结构导向药物设计中的分子优化经验复用
What Transfers Across Protein Pockets? Experience Reuse in Molecular Optimization for Agentic Structure-Based Drug Design
AI 导读
LLM 智能体通过逐步编辑配体并对接来优化蛋白口袋中的分子，研究者用 CrossDocked2020 测试集口袋的完整运行日志分析经验库的键值能否迁移到从未见过的新口袋。
正文 · 原文
Abstract:LLM agents optimize a ligand in a protein pocket by editing it step by step and docking each edit. Recent agents first spend extra dockings probing the complex with controlled edits; guidance induced from these probes is reported to help more than the chemical knowledge the model already carries. The probes are then discarded with the instance that produced them, so the obvious next step is to keep them in an experience base, letting a new pocket inherit what earlier ones already paid for. Such a base is read through a \emph{key}: the record properties under which past edits are pooled and a new one is looked up. Using the full log of one such run over the CrossDocked2020 test-set pockets, we ask whether its keys recur on a pocket the base has never seen and still separate improving from worsening edits. \crchange{Using} the contacts at the site being edited, the action, and the round as \crchange{a} key, the base separates them sharply. Within our analysis, this separation is largely explained by how much the edit changed the molecule's size, the action, and the round, none of which describes the target. That is not because the target is irrelevant: naming it outright separates them several times more sharply. For a pocket absent from the base, transfer must rely on a description rather than its identity. Among the exact-match descriptions we evaluate, the more specific ones rarely recur, whereas the coarser ones provide little separation; the signals that do transfer primarily describe the edit and the molecule it produced rather than the target. Under the representations and lookup scheme studied here, an experience base may be more useful for prioritizing an agent's own proposals for docking than for directly prescribing what to build.
| Subjects: | Artificial Intelligence (cs.AI); Biomolecules (q-bio.BM) |
| Cite as: | arXiv:2610.32620 [cs.AI] |
| (or arXiv:2610.32620v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32620 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zaifei Yang [view email]
[v1]
Fri, 23 Oct 2026 13:38:42 UTC (20 KB)
来源：arXiv cs.AI · arxiv.org