[论文] Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-St...
研究领域: ML 作者: Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong, Philippe Schwaller 发布时间: 2026-08-27 arXiv: 2608.27429
论文概要
研究领域: ML 作者: Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong, Philippe Schwaller 发布时间: 2026-08-27 arXiv: 2608.27429
中文摘要
化学反应本质上是电子空间中的变换,但大多数机器学习方法要么通过从头生成分子产物来建模,要么通过直接操作分子拓扑的启发式图编辑。我们引入了MAELLE(基于电子重排的机械编辑流匹配),它将反应建模为电子占据向量上的离散流匹配。具体而言,我们将反应物到产物的映射表述为在连续时间马尔可夫链(CTMC)上的图结构整数电子占据空间,定义在所有键合、非键合和氢位点上。为构建中间编辑轨迹,我们使用最优传输将离散流匹配混合路径推广到离散电子重排,产生一系列机械可解释的编辑移动,无需基本步骤注释。MAELLE在USPTO-480K基准上与领先的反应预测模型达到竞争性能。在结构复杂性和反应类型两个分布外设置中,MAELLE保持强大性能而现有方法性能下降。
原文摘要
Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through \textit{de novo} generation of product molecules or through heuristic graph edits that operate directly on molecular topology. We introduce MAELLE (\textbf{M}ech\textbf{A}nistic \textbf{E}dit f\textbf{L}ow-matching on e\textbf{L}ectron r\textbf{E}arrangements), which instead models reactions as discrete flow matching over electron occupation vectors. Concretely, we formulate the reactant-to-product mapping as a Continuous-time Markov Chain (CTMC) over the graph-structured integer-valued electron occupation space defined on all bonding, non-bonding, and hydrogen sites. To construct the intermediate edit trajectories, we generalize the discrete flow matching ...
*自动采集于 2026-08-30*
#论文 #arXiv #ML #小凯