mlsanityData to 14 Oct 2026

SynCoGen: Synthesizable 3D Molecule Generation via Joint Reaction and Coordinate Modeling

arXiv 2507.11818 ↗First posted 16 Jul 2025cs.LGcited by 5

Not on the map. Why?

Abstract (arXiv)

Synthesizability remains a critical bottleneck in generative molecular design. While recent advances have addressed synthesizability in 2D graphs, extending these constraints to 3D for geometry-based conditional generation remains largely unexplored. In this work, we present SynCoGen (Synthesizable Co-Generation), a single framework that combines simultaneous masked graph diffusion and flow matching for synthesizable 3D molecule generation. SynCoGen samples from the joint distribution of molecular building blocks, chemical reactions, and atomic coordinates. To train the model, we curated SynSpace, a dataset family containing over 1.2M synthesis-aware building block graphs and 7.5M conformers. SynCoGen achieves state-of-the-art performance in unconditional small molecule graph and conformer co-generation. For protein ligand generation in drug discovery, the amortized model delivers superior performance in both molecular linker design and pharmacophore-conditioned generation across diverse targets without relying on any scoring functions. Overall, this multimodal non-autoregressive formulation represents a foundation for a range of molecular design applications, including analog expansion, lead optimization, and direct de novo design.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 47 of its 72 references that are in the map. First posted on arXiv 16 Jul 2025.

Builds on

47 of 72 references.

References · 47

  1. 2022Flow Matching for Generative Modelingcited by 5,702
  2. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  3. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  4. 2023Stochastic Interpolants: A Unifying Framework for Flows and Diffusionscited by 939
  5. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 927
  6. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 879
  7. 2024Simple and Effective Masked Diffusion Language Modelscited by 848
  8. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 752
  9. 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
  10. 2024Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Designcited by 305
  11. 2023Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Actioncited by 302
  12. 2022Torsional Diffusion for Molecular Conformer Generationcited by 263
35 more
  1. 2020GEOM: Energy-annotated molecular conformations for property prediction and molecular generationcited by 243
  2. 2022Structure-based Drug Design with Equivariant Diffusion Modelscited by 217
  3. 2018Fr'echet ChemNet Distance: A metric for generative models for molecules in drug discoverycited by 194
  4. 2023One Transformer Fits All Distributions in Multi-Modal Diffusion at Scalecited by 187
  5. 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
  6. 2023SE(3)-Stochastic Flow Matching for Protein Backbone Generationcited by 150
  7. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Designcited by 122
  8. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generationcited by 98
  9. 2023Diffusion Bridge Mixture Transports, Schr"odinger Bridge Problems and Generative Modelingcited by 80
  10. 2023CoDi: Co-evolving Contrastive Diffusion Models for Mixed-type Tabular Synthesiscited by 78
  11. 2020The Synthesizability of Molecules Proposed by Generative Modelscited by 68
  12. 2020Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learningcited by 57
  13. 2024Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generationcited by 54
  14. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generationcited by 50
  15. 2021Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Designcited by 44
  16. 2024ET-Flow: Equivariant Flow-Matching for Molecular Conformer Generationcited by 43
  17. 2024SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matchingcited by 41
  18. 2024RGFN: Synthesizable Molecular Generation Using GFlowNetscited by 41
  19. 2019A Model to Search for Synthesizable Moleculescited by 37
  20. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimizationcited by 37
  21. 2020Molecular Design in Synthetically Accessible Chemical Space via Deep Reinforcement Learningcited by 32
  22. 2020Barking up the right tree: an approach to search over molecule synthesis DAGscited by 31
  23. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generationcited by 27
  24. 2023Re-evaluating Retrosynthesis Algorithms with Syntheseuscited by 27
  25. 2024SynFlowNet: Design of Diverse and Novel Molecules with Synthesis Constraintscited by 26
  26. 2024Generative Flows on Synthetic Pathway for Drug Designcited by 20
  27. 2024A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generationcited by 18
  28. 2024Generative Artificial Intelligence for Navigating Synthesizable Chemical Spacecited by 18
  29. 2024ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug designcited by 13
  30. 2024Procedural Synthesis of Synthesizable Moleculescited by 6
  31. 2025Compositional Flows for 3D Molecule and Synthesis Pathway Co-designcited by 6
  32. 2025Scalable and Cost-Efficient de Novo Template-Based Molecular Generationcited by 5
  33. 2023RLSynC: Offline-Online Reinforcement Learning for Synthon Completioncited by 4
  34. 2024TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Modelscited by 3
  35. 2025Active Learning on Synthons for Molecular Designcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025Efficient and Programmable Exploration of Synthesizable Chemical Spacecited by 3
  2. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profilescited by 0
  3. 2026On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimizationcited by 0
  4. 2026DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Modelscited by 0
  5. 2026Fraglingo: Molecular Design via Attachment-Aware Autoregressive Fragment Generationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Applications of Modular Co-Design for De Novo 3D Molecule Generation
  2. 2025Apo2Mol: 3D Molecule Generation via Dynamic Pocket-Aware Diffusion Models
  3. 2026Language-Informed Flow Matching for Trend-Guided Structure-Based 3D Molecular Generation
  4. 2025FlexiFlow: decomposable flow matching for generation of flexible molecular ensemble
  5. 2026Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
  6. 2025FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation
  7. 2026Geometric Flow Matching for Molecular Conformation Generation via Manifold Decomposition
  8. 2024BindGPT: A Scalable Framework for 3D Molecular Design via Language Modeling and Reinforcement Learning