用检索增强框架生成药物分子编辑，更贴近化学家实际设计思路。
Retrieval-Augmented Foundation Models for Matched Molecular Pair Transformations to Recapitulate Medicinal Chemistry Intuition
- 基于大规模分子对数据训练基础模型，实现变量到变量的可控生成
- 在通用和专利数据集上提升生成多样性与新颖性，可控性更强
- 适合药物发现中需要精准化学修饰的场景，尤其适合项目定制化需求
匹配分子对（MMPs）捕捉了药物化学家常用的局部化学修改模式，但现有机器学习方法要么在分子层面操作、编辑控制能力有限，要么仅在小规模数据和小型模型上学习。我们提出一种变量到变量的类似物生成范式，并在大规模匹配分子对变换（MMPT）数据上训练基础模型，以生成多样化的输出变量。为实现实际控制，开发了提示机制，使用户可在生成时指定偏好变换模式。进一步提出MMPT-RAG框架，通过外部参考类似物提供上下文引导，实现从项目特定系列的泛化。在通用化学语料库和专利特定数据集上的实验表明，该方法在多样性、新颖性和可控性方面均有提升，并能在实际发现场景中复现合理类似物结构。
原文摘要 · Abstract (English)
Matched molecular pairs (MMPs) capture the local chemical edits that medicinal chemists routinely use to design analogs, but existing ML approaches either operate at the whole-molecule level with limited edit controllability or learn MMP-style edits from restricted settings and small models. We propose a variable-to-variable formulation of analog generation and train a foundation model on large-scale MMP transformations (MMPTs) to generate diverse variables conditioned on an input variable. To enable practical control, we develop prompting mechanisms that let the users specify preferred transformation patterns during generation. We further introduce MMPT-RAG, a retrieval-augmented framework that uses external reference analogs as contextual guidance to steer generation and generalize from project-specific series. Experiments on general chemical corpora and patent-specific datasets demonstrate improved diversity, novelty, and controllability, and show that our method recovers realistic analog structures in practical discovery scenarios.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。