# Energy-based View of Retrosynthesis

arXiv: https://arxiv.org/abs/2007.13437 · HTML: https://mlsanity.com/paper/2007.13437/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Jul 2020.

## Built on by (most cited first, 24 of 24)

- [Root-aligned SMILES: A Tight Representation for Chemical Reaction Prediction](https://mlsanity.com/paper/2203.11444/) (2022)
- [RetroBridge: Modeling Retrosynthesis with Markov Bridges](https://mlsanity.com/paper/2308.16212/) (2023)
- [Towards Data-and Knowledge-Driven Artificial Intelligence: A Survey on Neuro-Symbolic Computing](https://mlsanity.com/paper/2210.15889/) (2022)
- [Discrete Langevin Sampler via Wasserstein Gradient Flow](https://mlsanity.com/paper/2206.14897/) (2022)
- [Graph Neural Networks for Molecules](https://mlsanity.com/paper/2209.05582/) (2022)
- [Retrosynthesis Prediction with Local Template Retrieval](https://mlsanity.com/paper/2306.04123/) (2023)
- [FusionRetro: Molecule Representation Fusion via In-Context Learning for Retrosynthetic Planning](https://mlsanity.com/paper/2209.15315/) (2022)
- [RetroComposer: Composing Templates for Template-Based Retrosynthesis Prediction](https://mlsanity.com/paper/2112.11225/) (2021)
- [SemiRetro: Semi-template framework boosts deep retrosynthesis prediction](https://mlsanity.com/paper/2202.08205/) (2022)
- [MARS: A Motif-based Autoregressive Model for Retrosynthesis Prediction](https://mlsanity.com/paper/2209.13178/) (2022)
- [Equivariant Denoisers Cannot Copy Graphs: Align Your Graph Diffusion Models](https://mlsanity.com/paper/2405.17656/) (2024)
- [Retrosynthesis prediction enhanced by in-silico reaction data augmentation](https://mlsanity.com/paper/2402.00086/) (2024)
- [Hitchhiker's guide on the relation of Energy-Based Models with other generative models, sampling and statistical physics: a comprehensive review](https://mlsanity.com/paper/2406.13661/) (2024)
- [Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction](https://mlsanity.com/paper/2411.08306/) (2024)
- [mathsfG2Retro as a Two-Step Graph Generative Models for Retrosynthesis Prediction](https://mlsanity.com/paper/2206.04882/) (2022)
- [A Unified View of Deep Learning for Reaction and Retrosynthesis Prediction: Current Status and Future Challenges](https://mlsanity.com/paper/2306.15890/) (2023)
- [Modeling Diverse Chemical Reactions for Single-step Retrosynthesis via Discrete Latent Variables](https://mlsanity.com/paper/2208.05482/) (2022)
- [Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis](https://mlsanity.com/paper/2508.10967/) (2025)
- [MotifRetro: Exploring the Combinability-Consistency Trade-offs in retrosynthesis via Dynamic Motif Editing](https://mlsanity.com/paper/2305.15153/) (2023)
- [Evolutionary Retrosynthetic Route Planning](https://mlsanity.com/paper/2310.05186/) (2023)
- [RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction](https://mlsanity.com/paper/2312.10900/) (2023)
- [Retrosynthesis Prediction via Search in (Hyper) Graph](https://mlsanity.com/paper/2402.06772/) (2024)
- [Variational Potential Flow: A Novel Probabilistic Framework for Energy-Based Generative Modelling](https://mlsanity.com/paper/2407.15238/) (2024)
- [Chemical knowledge-informed framework for privacy-aware retrosynthesis learning](https://mlsanity.com/paper/2502.19119/) (2025)

## Abstract (arXiv)

Retrosynthesis -- the process of identifying a set of reactants to synthesize a target molecule -- is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified perspective provides critical insights about EBM variants through a comprehensive assessment of performance. Additionally, we present a novel dual variant within the framework that performs consistent training over Bayesian forward- and backward-prediction by constraining the agreement between the two directions. This model improves state-of-the-art performance by 9.6% for template-free approaches where the reaction type is unknown.