FragFlex: Fragment-Based Flexible Molecular Generation for Exploring Vast Chemical Space
On the map: Diffusion models → Flow matching, time series and science
Abstract (arXiv)
Drug discovery requires efficient exploration of an astronomically large chemical space. Molecular graph diffusion models offer a promising approach to this task, but many require graph size to be fixed before generation. Although atom-level insertion and deletion can enable flexible-size generation, jointly modeling molecular size, atom types, and bonds while maintaining chemical validity remains challenging. We introduce FragFlex, a flexible-length discrete diffusion model that performs node insertion and deletion at the fragment level. During denoising, FragFlex jointly learns the size, fragment identities, and inter-fragment connectivity of the fragment graph. A neural attachment-site predictor and valence-aware assembler then convert the generated fragment graph into an atom-level molecule. In large-scale experiments generating 10 million molecules, FragFlex achieves near-perfect chemical validity while maintaining high uniqueness, demonstrating a strong balance between the two.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 20 of its 34 references that are in the map. First posted on arXiv 11 Oct 2026.
Builds on
20 of 34 references.
Closest ancestors · 5
Same direction, newest first
- 2025Graph Diffusion that can Insert and Delete6 Jun
- 2025FragFM: Hierarchical Framework for Efficient Molecule Generation via Fragment-Level Discrete Flow Matching19 Feb
- 2024IFH: a Diffusion Framework for Flexible Design of Graph Generative Models23 Aug
- 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
- 2022Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations5 Feb
Other references · 15
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
- 2024Simple and Effective Masked Diffusion Language Modelscited by 848
- 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 765
- 2023Discrete Diffusion Modeling by Estimating the Ratios of the Data Distributioncited by 745
- 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 652
- 2018GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoderscited by 383
- 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 305
- 2017Grammar Variational Autoencodercited by 285
- 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 208
- 2018Constrained Graph Variational Autoencoders for Molecule Designcited by 185
- 2021GraphDF: A Discrete Flow Model for Molecular Graph Generationcited by 180
3 more
- 2023Graph Generation with Diffusion Mixturecited by 55
- 2025Any-Order Flexible Length Masked Diffusioncited by 51
- 2024A Review on Fragment-based De Novo 2D Molecule Generationcited by 4
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D
- 2025DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform
- 20243M-Diffusion: Latent Multi-Modal Diffusion for Language-Guided Molecular Structure Generation
- 2025DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra
- 2024GraphXForm: Graph transformer for computer-aided molecular design
- 2025FragmentGPT: A Unified GPT Model for Fragment Growing, Linking, and Merging in Molecular Design
- 2025Graph Diffusion Transformers are In-Context Molecular Designers
- 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design