Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
[Sztuczna inteligencja] Autorzy: Nguyen Xuan-Vu, Octavian Susanu, Daniel Armstrong i 1 więcej
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 mixture path to discrete electron rearrangements using Optimal Transport, yielding a sequence of me…
- Kategoria arxiv
- cs.AI
- Kategoria
- Sztuczna inteligencja