Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation

• URL: http://arxiv.org/abs/2608.27429v2
• Date: Fri, 28 Aug 2026 11:35:19 GMT
• Title: Mechanistic Reaction Prediction via Discrete Flow Matching on Graph-Structured Electron Occupation
• Abstract summary: We introduce MAELLE (MechAnistic Edit fLow-matching on eLectron rEarrangements), which instead models reactions as discrete flow matching over electron occupation vectors.<n>MaELLE achieves competitive performance on the USPTO-480K benchmark compared with leading reaction prediction models.
• Score: 3.82321341141483
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Chemical reactions are fundamentally transformations in electron space, yet most machine learning approaches model them either through de novo generation of product molecules or through heuristic graph edits that operate directly on molecular topology. We introduce MAELLE (MechAnistic Edit fLow-matching on eLectron rEarrangements), 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 interpolants between the reactants and products, we generalize the discrete flow matching mixture path to an edit-based formulation, where the electron moves are interpolated using Optimal Transport, yielding a mechanism-like set of moves without elementary step annotations. MAELLE achieves competitive performance on the USPTO-480K benchmark compared with leading reaction prediction models. Beyond in-distribution learning, we evaluate robustness across two out-of-distribution settings - structural complexity and reaction type - and find that MAELLE maintains strong performance where existing methods degrade. Finally, because the learned flow operates over the full electron redistribution, MAELLE naturally recovers mechanistic trajectories that align with known chemistry and can predict side products of a reaction.

Related papers

• Zatom-1: A Multimodal Flow Foundation Model for 3D Molecules and Materials [51.342983349686556]
  General-purpose 3D chemical modeling encompasses molecules and materials, requiring both generative and predictive capabilities.<n>We introduce Zatom-1, the first end-to-end, fully open-source foundation model that unifies generative and predictive learning of 3D molecules and materials.
  arXiv  Detail & Related papers  (2026-02-24T20:52:39Z)
• From Static Spectra to Operando Infrared Dynamics: Physics Informed Flow Modeling and a Benchmark [67.29937933325849]
  Operando IR Prediction aims to forecast the time-resolved evolution of spectral fingerprints'' from a single static spectrum.<n>OpIRSpec-7K comprises 7,118 high-quality samples across 10 distinct battery systems.<n>ABCC significantly outperforms state-of-the-art static, sequential, and generative baselines.
  arXiv  Detail & Related papers  (2026-02-20T18:58:43Z)
• Teaching Language Models Mechanistic Explainability Through Arrow-Pushing [3.488381738536745]
  Chemical reaction mechanisms provide crucial insight into synthesizability.<n>Current Computer-Assisted Synthesis Planning (CASP) systems lack mechanistic grounding.<n>We introduce a computational framework for teaching language models to predict chemical reaction mechanisms.
  arXiv  Detail & Related papers  (2025-12-05T13:57:50Z)
• Flow matching for reaction pathway generation [1.8420084274819617]
  MolGEN is a conditional flow-matching framework that learns an optimal transport path to transport Gaussian priors to target chemical distributions.<n>On benchmarks used by TSDiff and OA-ReactDiff, MolGEN surpasses TS geometry accuracy and barrier-height prediction while reducing sampling to sub-second.<n>MolGEN also supports open-ended product generation with competitive top-k accuracy and avoids mass/electron-balance violations common to sequence models.
  arXiv  Detail & Related papers  (2025-07-14T17:54:47Z)
• SynBridge: Bridging Reaction States via Discrete Flow for Bidirectional Reaction Prediction [33.428877102021254]
  The essence of a chemical reaction lies in the redistribution and reorganization of electrons.<n>We propose SynBridge, a bidirectional flow-based generative model to achieve multi-task reaction prediction.
  arXiv  Detail & Related papers  (2025-07-11T10:35:13Z)
• Transferable Learning of Reaction Pathways from Geometric Priors [1.3170830344441016]
  MEPIN is a scalable machine-learning method for efficiently predicting MEPs from reactant and product geometries.<n>Our method enables the exploration of large chemical reaction spaces with efficient, data-driven predictions of reaction pathways.
  arXiv  Detail & Related papers  (2025-04-21T18:20:53Z)
• Predicting Chemical Reaction Outcomes Based on Electron Movements Using Machine Learning [5.191954242696695]
  We present Reactron, the first electron-based machine learning model for general reaction prediction.<n>We demonstrate the high predictive performance of Reactron over existing product-only models.<n>With robust performance in both in- and out-of-distribution, Reactron embodies human-like reasoning in chemistry.
  arXiv  Detail & Related papers  (2025-03-13T09:31:51Z)
• Learning Chemical Reaction Representation with Reactant-Product Alignment [50.28123475356234]
  RAlign is a novel chemical reaction representation learning model for various organic reaction-related tasks.<n>By integrating atomic correspondence between reactants and products, our model discerns the molecular transformations that occur during the reaction.<n>We introduce a reaction-center-aware attention mechanism that enables the model to concentrate on key functional groups.
  arXiv  Detail & Related papers  (2024-11-26T17:41:44Z)
• Pre-trained Molecular Language Models with Random Functional Group Masking [54.900360309677794]
  We propose a SMILES-based underlineem Molecular underlineem Language underlineem Model, which randomly masking SMILES subsequences corresponding to specific molecular atoms. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities.
  arXiv  Detail & Related papers  (2024-11-03T01:56:15Z)
• ReactAIvate: A Deep Learning Approach to Predicting Reaction Mechanisms and Unmasking Reactivity Hotspots [4.362338454684645]
  We develop an interpretable attention-based GNN that achieved near-unity and 96% accuracy for reaction step classification. Our model adeptly identifies key atom(s) even from out-of-distribution classes. This generalizabilty allows for the inclusion of new reaction types in a modular fashion, thus will be of value to experts for understanding the reactivity of new molecules.
  arXiv  Detail & Related papers  (2024-07-14T05:53:18Z)
• Doubly Stochastic Graph-based Non-autoregressive Reaction Prediction [59.41636061300571]
  We propose a new framework called that combines two doubly self-attention mappings to obtain electron redistribution predictions. We show that our approach consistently improves the predictive performance of non-autoregressive models.
  arXiv  Detail & Related papers  (2023-06-05T14:15:39Z)
• GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation [102.85440102147267]
  We propose a novel generative model named GeoDiff for molecular conformation prediction. We show that GeoDiff is superior or comparable to existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-06T09:47:01Z)
• Non-Autoregressive Electron Redistribution Modeling for Reaction Prediction [26.007965383304864]
  We devise a non-autoregressive learning paradigm that predicts reaction in one shot. We formulate a reaction as an arbitrary electron flow and predict it with a novel multi-pointer decoding network. Experiments on the USPTO-MIT dataset show that our approach has established a new state-of-the-art top-1 accuracy.
  arXiv  Detail & Related papers  (2021-06-08T16:39:08Z)
• Non-autoregressive electron flow generation for reaction prediction [15.98143959075733]
  We devise a novel decoder that avoids such sequential generating and predicts the reaction in a Non-Autoregressive manner. Inspired by physical-chemistry insights, we represent edge edits in a molecule graph as electron flows, which can then be predicted in parallel. Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.
  arXiv  Detail & Related papers  (2020-12-16T10:01:26Z)
• Graph Neural Network for Hamiltonian-Based Material Property Prediction [56.94118357003096]
  We present and compare several different graph convolution networks that are able to predict the band gap for inorganic materials. The models are developed to incorporate two different features: the information of each orbital itself and the interaction between each other. The results show that our model can get a promising prediction accuracy with cross-validation.
  arXiv  Detail & Related papers  (2020-05-27T13:32:10Z)
• Retrosynthesis Prediction with Conditional Graph Logic Network [118.70437805407728]
  Computer-aided retrosynthesis is finding renewed interest from both chemistry and computer science communities. We propose a new approach to this task using the Conditional Graph Logic Network, a conditional graphical model built upon graph neural networks.
  arXiv  Detail & Related papers  (2020-01-06T05:36:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.