Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching

• URL: http://arxiv.org/abs/2602.13136v1
• Date: Fri, 13 Feb 2026 17:39:21 GMT
• Title: Order Matters in Retrosynthesis: Structure-aware Generation via Reaction-Center-Guided Discrete Flow Matching
• Abstract summary: We propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a positional inductive bias.<n>Our method achieves state-of-the-art performance on both USPTO-50k (61.2% top-1) and the large-scale USPTO-Full (51.3% top-1) with predicted reaction centers.
• Score: 18.649082246599267
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Template-free retrosynthesis methods treat the task as black-box sequence generation, limiting learning efficiency, while semi-template approaches rely on rigid reaction libraries that constrain generalization. We address this gap with a key insight: atom ordering in neural representations matters. Building on this insight, we propose a structure-aware template-free framework that encodes the two-stage nature of chemical reactions as a positional inductive bias. By placing reaction center atoms at the sequence head, our method transforms implicit chemical knowledge into explicit positional patterns that the model can readily capture. The proposed RetroDiT backbone, a graph transformer with rotary position embeddings, exploits this ordering to prioritize chemically critical regions. Combined with discrete flow matching, our approach decouples training from sampling and enables generation in 20--50 steps versus 500 for prior diffusion methods. Our method achieves state-of-the-art performance on both USPTO-50k (61.2% top-1) and the large-scale USPTO-Full (51.3% top-1) with predicted reaction centers. With oracle centers, performance reaches 71.1% and 63.4% respectively, surpassing foundation models trained on 10 billion reactions while using orders of magnitude less data. Ablation studies further reveal that structural priors outperform brute-force scaling: a 280K-parameter model with proper ordering matches a 65M-parameter model without it.

Related papers

• RetroMPA: A Molecular Property-Aware Auxiliary Framework for Enhancing Retrosynthesis Prediction [23.136601313495785]
  RetroMPA is a model-agnostic chemical filter designed to recalibrate and optimize the predictive pathways of existing algorithms.<n>RetroMPA consistently improves top-1 accuracy across eight representative retrosynthesis models by an average of 5.50% on USPTO-50K.<n>Wet-lab experiments provide preliminary support for the practical utility of the framework.
  arXiv  Detail & Related papers  (2026-08-17T05:03:30Z)
• RETROSPECT: RETROsynthesis via Sequential Prediction, and Chemically Transformed-ranking [0.004129405224409433]
  Single-step retrosynthesis needs both accurate first-ranked suggestions and candidate lists that are rich enough for downstream selection.<n>Our system, RETROSPECT, combines a single Transformer proposal model, which we call the ChemAlign Transformer, with a Lambda reranker.<n>The generator is trained with hybrid root-aligned and random SMILES augmentation, Pre-LayerNorm, tied embeddings, exponential moving average weights, and a differentiable atom-balance auxiliary loss.
  arXiv  Detail & Related papers  (2026-06-05T11:45:36Z)
• Representation-Guided Discrete Molecular Graph Retrosynthesis [50.11269464321367]
  Graph-oriented representation guidance (GRG) achieves 58.6 / 77.2 / 83.4 / 87.1 top-1 / 3 / 5 / 10 accuracy on USPTO-50k.<n> GRG consistently improves all top-k metrics in out-of-distribution settings.<n> GRG reduces the number of epochs by 35% and the wall-clock time by 30% to reach comparable performance.
  arXiv  Detail & Related papers  (2026-05-23T06:49:17Z)
• RxnNano:Training Compact LLMs for Chemical Reaction and Retrosynthesis Prediction via Hierarchical Curriculum Learning [20.904697361501174]
  We argue that the core challenge lies in instilling these knowledge into the models.<n>We propose a unified framework that prioritizes chemical understanding over scale through three key innovations.
  arXiv  Detail & Related papers  (2026-02-10T07:42:23Z)
• DeepMech: A Machine Learning Framework for Chemical Reaction Mechanism Prediction [2.15242029196761]
  We present DeepMech, an interpretable graph-based deep learning framework to generate chemical reaction mechanisms.<n>DeepMech achieves 98.98 +/-0.12% accuracy in predicting elementary steps and 95.94 +/-0.21% in complete CRM tasks.
  arXiv  Detail & Related papers  (2025-09-19T11:14:46Z)
• RETRO SYNFLOW: Discrete Flow Matching for Accurate and Diverse Single-Step Retrosynthesis [23.422202032748924]
  We model single-step retrosynthesis planning and introduce RETRO SYNFLOW (RSF) a discrete flow-matching framework.<n>We employ Feynman-Kac steering with Sequential Monte Carlo based resampling to steer promising generations at inference.
  arXiv  Detail & Related papers  (2025-06-04T20:46:05Z)
• Interpretable Deep Learning for Polar Mechanistic Reaction Prediction [43.95903801494905]
  We introduce PMechRP (Polar Mechanistic Reaction Predictor), a system that trains machine learning models on the PMechDB dataset.<n>We train compare a range of machine learning models, including transformer-based, graph-based and two-step siamese architectures.<n>Our best-performing approach was a hybrid model, which combines a 5-ensemble of Chemformer models with a two-step Siamese framework.
  arXiv  Detail & Related papers  (2025-04-22T02:31:23Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• CLEAR: Conv-Like Linearization Revs Pre-Trained Diffusion Transformers Up [64.38715211969516]
  We introduce a convolution-like local attention strategy termed CLEAR, which limits feature interactions to a local window around each query token.<n>Experiments indicate that, by fine-tuning the attention layer on merely 10K self-generated samples for 10K iterations, we can effectively transfer knowledge from a pre-trained DiT to a student model with linear complexity.
  arXiv  Detail & Related papers  (2024-12-20T17:57:09Z)
• Diffusion Model with Representation Alignment for Protein Inverse Folding [53.139837825588614]
  Protein inverse folding is a fundamental problem in bioinformatics, aiming to recover the amino acid sequences from a given protein backbone structure.<n>We propose a novel method that leverages diffusion models with representation alignment (DMRA)<n>In experiments, we conduct extensive evaluations on the CATH4.2 dataset to demonstrate that DMRA outperforms leading methods.
  arXiv  Detail & Related papers  (2024-12-12T15:47:59Z)
• Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models [24.912841472542322]
  Graph diffusion models, dominant in graph generative modeling, remain underexplored for graph-to-graph translation tasks.<n>We show how alignment dramatically improves discrete diffusion model performance from 5% to a SOTA-matching 54.7% top-1 accuracy.
  arXiv  Detail & Related papers  (2024-05-27T20:57:19Z)
• UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment [51.49238426241974]
  This paper introduces UAlign, a template-free graph-to-sequence pipeline for retrosynthesis prediction. By combining graph neural networks and Transformers, our method can more effectively leverage the inherent graph structure of molecules.
  arXiv  Detail & Related papers  (2024-03-25T03:23:03Z)
• Retrosynthesis Prediction with Local Template Retrieval [112.23386062396622]
  Retrosynthesis, which predicts the reactants of a given target molecule, is an essential task for drug discovery. In this work, we introduce RetroKNN, a local reaction template retrieval method. We conduct comprehensive experiments on two widely used benchmarks, the USPTO-50K and USPTO-MIT.
  arXiv  Detail & Related papers  (2023-06-07T03:38:03Z)
• Retrosynthetic Planning with Dual Value Networks [107.97218669277913]
  We propose a novel online training algorithm, called Planning with Dual Value Networks (PDVN) PDVN alternates between the planning phase and updating phase to predict the synthesizability and cost of molecules. On the widely-used USPTO dataset, our PDVN algorithm improves the search success rate of existing multi-step planners.
  arXiv  Detail & Related papers  (2023-01-31T16:43:53Z)
• RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning [107.64562550844146]
  Retrosynthesis is an emerging research area of deep learning. We propose a new approach that reformulating retrosynthesis into a selection problem of reactants from a candidate set of commercially available molecules. For learning the score functions, we also propose a novel contrastive training scheme with hard negative mining.
  arXiv  Detail & Related papers  (2021-05-03T12:47:57Z)
• State-of-the-Art Augmented NLP Transformer models for direct and single-step retrosynthesis [0.0]
  We investigated the effect of different training scenarios on predicting retrosynthesis of chemical compounds. Data augmentation, which is a powerful method used in image processing, eliminated the effect of data memorization by neural networks.
  arXiv  Detail & Related papers  (2020-03-05T18:11:11Z)

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.