arXiv：cs.AI· Yuto Suzuki, Paul Awolade, Daniel V. LaBarbera, Farnoush Banaei-Kashani·· 6 小时前AI 评分39
FRAGMENTA：小数据场景下基于片段生成的端到端药物先导优化框架，支持智能体调优
FRAGMENTA: Efficient End-to-end Fragmentation-based Generative Model with Agentic Tuning for Drug Lead Optimization in Small Data Regime
AI 导读
FRAGMENTA 是一个面向小数据药物先导优化的端到端框架，由片段生成器 LVSEF 和将专家对话反馈转化为生成目标的智能体系统组成。在三个小数据集（11-104 个分子）上，LVSEF 在最小数据场景下优于 SOTA 方法，训练速度快约 16 倍。在真实癌症药物发现部署中，Human-Agent FRAGMENTA 识别出的对接分数良好（< -6）的分子数量接近基线方法的两倍。
正文
Abstract:Molecule generation from extremely limited training data is a key challenge in drug discovery. Existing fragment-based methods are more suitable than atom-based approaches in this regime, but typically optimize fragment selection separately from downstream generation. Expert feedback is also especially valuable with limited data, yet translating such feedback into model objectives usually requires AI engineering expertise. We introduce FRAGMENTA, an end-to-end framework for small-data drug lead optimization with two components: (1) LVSEF, a fragment-based generator that jointly optimizes fragmentation and generation through a tabular reward-update mechanism, and (2) an agentic system that converts conversational expert feedback into updated generative objectives. Across three small-data datasets (11--104 molecules), LVSEF outperforms state-of-the-art methods in the smallest-data settings, matches them at larger scales, and trains ${\sim}16\times$ faster. On three public protein targets, iterative closed-loop optimization improves final-round discovery yield by up to ${\sim}16%$ over one-shot LVSEF-only on kinase, with gains depending on how well feedback matches target chemistry. In a real-world cancer drug-discovery deployment, Human-Agent FRAGMENTA identified nearly twice as many molecules with favorable docking scores ($< -6$) as baseline methods.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2511.20510 [cs.AI] |
| (or arXiv:2511.20510v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2511.20510 arXiv-issued DOI via DataCite |
Submission history
From: Yuto Suzuki [view email]
[v1]
Tue, 25 Nov 2025 17:17:54 UTC (11,115 KB)
[v2]
Wed, 26 Nov 2025 02:35:22 UTC (11,115 KB)
[v3]
Tue, 6 Oct 2026 15:35:51 UTC (9,321 KB)
来源：arXiv：cs.AI · arxiv.org