# RGFN: Synthesizable Molecular Generation Using GFlowNets

arXiv: https://arxiv.org/abs/2406.08506 · HTML: https://mlsanity.com/paper/2406.08506/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 87 references that are in the map.
- First posted on arXiv 1 Jun 2024.

## Builds on (most cited first, 27 of 27)

- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Representation Learning on Graphs with Jumping Knowledge Networks](https://mlsanity.com/paper/1806.03536/) (2018)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [Graph Transformer Networks](https://mlsanity.com/paper/1911.06455/) (2019)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [GuacaMol: Benchmarking Models for De Novo Molecular Design](https://mlsanity.com/paper/1811.09621/) (2018)
- [GFlowNet Foundations](https://mlsanity.com/paper/2111.09266/) (2021)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Therapeutics Data Commons: Machine Learning Datasets and Tasks for Drug Discovery and Development](https://mlsanity.com/paper/2102.09548/) (2021)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [ChemBO: Bayesian Optimization of Small Organic Molecules with Synthesizable Recommendations](https://mlsanity.com/paper/1908.01425/) (2019)
- [The Synthesizability of Molecules Proposed by Generative Models](https://mlsanity.com/paper/2002.07007/) (2020)
- [Mol-CycleGAN - a generative model for molecular optimization](https://mlsanity.com/paper/1902.02119/) (2019)
- [Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning](https://mlsanity.com/paper/2004.12485/) (2020)
- [Conditional molecular design with deep generative models](https://mlsanity.com/paper/1805.00108/) (2018)
- [Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design](https://mlsanity.com/paper/2110.06389/) (2021)
- [3D molecule generation by denoising voxel grids](https://mlsanity.com/paper/2306.07473/) (2023)
- [A Model to Search for Synthesizable Molecules](https://mlsanity.com/paper/1906.05221/) (2019)
- [Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learning](https://mlsanity.com/paper/2004.14308/) (2020)
- [Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design](https://mlsanity.com/paper/2306.04620/) (2023)
- [Machine learning on DNA-encoded libraries: A new paradigm for hit-finding](https://mlsanity.com/paper/2002.02530/) (2020)
- [Multi-Fidelity Active Learning with GFlowNets](https://mlsanity.com/paper/2306.11715/) (2023)
- [Towards equilibrium molecular conformation generation with GFlowNets](https://mlsanity.com/paper/2310.14782/) (2023)
- [SILVR: Guided Diffusion for Molecule Generation](https://mlsanity.com/paper/2304.10905/) (2023)
- [Generative Active Learning for the Search of Small-molecule Protein Binders](https://mlsanity.com/paper/2405.01616/) (2024)
- [An efficient graph generative model for navigating ultra-large combinatorial synthesis libraries](https://mlsanity.com/paper/2211.04468/) (2022)
- [Bridging the Gap between Chemical Reaction Pretraining and Conditional Molecule Generation with a Unified Model](https://mlsanity.com/paper/2303.06965/) (2023)

## Built on by (most cited first, 30 of 41)

- [Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples](https://mlsanity.com/paper/2406.05673/) (2024)
- [Generative Flows on Synthetic Pathway for Drug Design](https://mlsanity.com/paper/2410.04542/) (2024)
- [Generative Artificial Intelligence for Navigating Synthesizable Chemical Space](https://mlsanity.com/paper/2410.03494/) (2024)
- [LLM-Augmented Chemical Synthesis and Design Decision Programs](https://mlsanity.com/paper/2505.07027/) (2025)
- [RetroGFN: Diverse and Feasible Retrosynthesis using GFlowNets](https://mlsanity.com/paper/2406.18739/) (2024)
- [Revisiting Non-Acyclic GFlowNets in Discrete Environments](https://mlsanity.com/paper/2502.07735/) (2025)
- [Exploring Synthesizable Chemical Space with Iterative Pathway Refinements](https://mlsanity.com/paper/2509.16084/) (2025)
- [Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems](https://mlsanity.com/paper/2510.04792/) (2025)
- [Compositional Flows for 3D Molecule and Synthesis Pathway Co-design](https://mlsanity.com/paper/2504.08051/) (2025)
- [Evaluating Molecule Synthesizability via Retrosynthetic Planning and Reaction Prediction](https://mlsanity.com/paper/2411.08306/) (2024)
- [Scalable and Cost-Efficient de Novo Template-Based Molecular Generation](https://mlsanity.com/paper/2506.19865/) (2025)
- [SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling](https://mlsanity.com/paper/2507.11818/) (2025)
- [Cell Morphology-Guided Small Molecule Generation with GFlowNets](https://mlsanity.com/paper/2408.05196/) (2024)
- [A Genetic Algorithm for Navigating Synthesizable Molecular Spaces](https://mlsanity.com/paper/2509.20719/) (2025)
- [SigmaDock: Untwisting Molecular Docking With Fragment-Based SE(3) Diffusion](https://mlsanity.com/paper/2511.04854/) (2025)
- [Secrets of GFlowNets' Learning Behavior: A Theoretical Study](https://mlsanity.com/paper/2505.02035/) (2025)
- [Catalyst GFlowNet for electrocatalyst design: A hydrogen evolution reaction case study](https://mlsanity.com/paper/2510.02142/) (2025)
- [gfnx: Fast and Scalable Library for Generative Flow Networks in JAX](https://mlsanity.com/paper/2511.16592/) (2025)
- [Efficient and Programmable Exploration of Synthesizable Chemical Space](https://mlsanity.com/paper/2512.00384/) (2025)
- [Mitigating Hallucinations in LM-Based TTS Models via Distribution Alignment Using GFlowNets](https://mlsanity.com/paper/2508.15442/) (2025)
- [Curriculum-Augmented GFlowNets For mRNA Sequence Generation](https://mlsanity.com/paper/2510.03811/) (2025)
- [Learning Shortest Paths with Generative Flow Networks](https://mlsanity.com/paper/2603.01786/) (2026)
- [LLM-Guided Dynamic Action Spaces for Synthesizable Molecular Optimization](https://mlsanity.com/paper/2604.07669/) (2026)
- [Iterative Foundation Model Fine-Tuning on Multiple Rewards](https://mlsanity.com/paper/2511.00220/) (2025)
- [SynCraft: Guiding Large Language Models to Predict Edit Sequences for Molecular Synthesizability Optimization](https://mlsanity.com/paper/2512.20333/) (2025)
- [Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors](https://mlsanity.com/paper/2602.04119/) (2026)
- [Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models](https://mlsanity.com/paper/2605.25681/) (2026)
- [Project Ariadne: Prompt-Conditioned Route Generation for Synthesis Planning](https://mlsanity.com/paper/2606.24184/) (2026)
- [CAi Copilot: Reducing Operational Workload in Molecular Design through Intent-Driven Agentic Workflows](https://mlsanity.com/paper/2608.06961/) (2026)
- [It Takes Two to Tango: Directly Optimizing for Constrained Synthesizability in Generative Molecular Design](https://mlsanity.com/paper/2410.11527/) (2024)

## Abstract (arXiv)

Generative models hold great promise for small molecule discovery, significantly increasing the size of search space compared to traditional in silico screening libraries. However, most existing machine learning methods for small molecule generation suffer from poor synthesizability of candidate compounds, making experimental validation difficult. In this paper we propose Reaction-GFlowNet (RGFN), an extension of the GFlowNet framework that operates directly in the space of chemical reactions, thereby allowing out-of-the-box synthesizability while maintaining comparable quality of generated candidates. We demonstrate that with the proposed set of reactions and building blocks, it is possible to obtain a search space of molecules orders of magnitude larger than existing screening libraries coupled with low cost of synthesis. We also show that the approach scales to very large fragment libraries, further increasing the number of potential molecules. We demonstrate the effectiveness of the proposed approach across a range of oracle models, including pretrained proxy models and GPU-accelerated docking.