mlsanityData to 7 Oct 2026

Unified Guidance for Geometry-Conditioned Molecular Generation

arXiv 2501.02526 ↗First posted 5 Jan 2025q-bio.BM cs.LGcited by 7

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Effectively designing molecular geometries is essential to advancing pharmaceutical innovations, a domain, which has experienced great attention through the success of generative models and, in particular, diffusion models. However, current molecular diffusion models are tailored towards a specific downstream task and lack adaptability. We introduce UniGuide, a framework for controlled geometric guidance of unconditional diffusion models that allows flexible conditioning during inference without the requirement of extra training or networks. We show how applications such as structure-based, fragment-based, and ligand-based drug design are formulated in the UniGuide framework and demonstrate on-par or superior performance compared to specialised models. Offering a more versatile approach, UniGuide has the potential to streamline the development of molecular generative models, allowing them to be readily used in diverse application scenarios.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 56 of its 84 references that are in the map. First posted on arXiv 5 Jan 2025.

Builds on

56 of 84 references.

Closest ancestors · 16

Same direction, newest first

  1. 2024Lift Your Molecules: Molecular Graph Generation in Latent Euclidean Space15 Jun
  2. 2024DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design26 Feb
  3. 2023Equivariant Flow Matching with Hybrid Probability Transport12 Dec
  4. 2023Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting21 Jul
  5. 2023Learning Joint 2D & 3D Diffusion Models for Complete Molecule Generation21 May
  6. 2023Coarse-to-Fine: a Hierarchical Diffusion Model for Molecule Generation in 3D5 May
  7. 2023Geometric Latent Diffusion Models for 3D Molecule Generation2 May
  8. 2023MiDi: Mixed Graph and 3D Denoising Diffusion for Molecule Generation17 Feb
  9. 2023Geometry-Complete Diffusion for 3D Molecule Generation and Optimization8 Feb
  10. 2022Structure-based Drug Design with Equivariant Diffusion Models24 Oct
  11. 2022Equivariant 3D-Conditional Diffusion Models for Molecular Linker Design11 Oct
  12. 2022DiGress: Discrete Denoising diffusion for graph generation29 Sep
4 more
  1. 2022MDM: Molecular Diffusion Model for 3D Molecule Generation13 Sep
  2. 2022Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem8 Jun
  3. 2022Protein Structure and Sequence Generation with Equivariant Denoising Diffusion Probabilistic Models26 May
  4. 2022Equivariant Diffusion for Molecule Generation in 3D31 Mar

Other references · 40

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2022Classifier-Free Diffusion Guidancecited by 5,717
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  9. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  10. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  11. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  12. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 620
28 more
  1. 2022LION: Latent Point Diffusion Models for 3D Shape Generationcited by 552
  2. 2023Universal Guidance for Diffusion Modelscited by 426
  3. 2018MolGAN: An implicit generative model for small molecular graphscited by 392
  4. 2022DiffDock: Diffusion Steps, Twists, and Turns for Molecular Dockingcited by 307
  5. 2018Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Modelscited by 270
  6. 2020Hierarchical Generation of Molecular Graphs using Structural Motifscited by 204
  7. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
  8. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  9. 2019Symmetry-adapted generation of 3d point sets for the targeted discovery of moleculescited by 171
  10. 2021E(n) Equivariant Normalizing Flowscited by 165
  11. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  12. 2022Semantic Image Synthesis via Diffusion Modelscited by 131
  13. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  14. 2022Diffusion-based Molecule Generation with Informative Prior Bridgescited by 104
  15. 2021Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Dockingcited by 81
  16. 2022Equivariant Energy-Guided SDE for Inverse Molecular Designcited by 72
  17. 2021Learning to Extend Molecular Scaffolds with Structural Motifscited by 70
  18. 2022MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Designcited by 66
  19. 2021Molecule Generation by Principal Subgraph Mining and Assemblingcited by 53
  20. 2023De Novo Molecular Generation via Connection-aware Motif Miningcited by 45
  21. 20223DLinker: An E(3) Equivariant Variational Autoencoder for Molecular Linker Designcited by 33
  22. 2020Learning a Continuous Representation of 3D Molecular Structures with Deep Generative Modelscited by 24
  23. 2022Zero-Shot 3D Drug Design by Sketching and Generatingcited by 24
  24. 2022Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Designcited by 19
  25. 2021Learning Equivariant Energy Based Models with Equivariant Stein Variational Gradient Descentcited by 10
  26. 2023MAGNet: Motif-Agnostic Generation of Molecules from Shapescited by 7
  27. 2023Shape-conditioned 3D Molecule Generation via Equivariant Diffusion Modelscited by 7
  28. 2023The power of motifs as inductive bias for learning molecular distributionscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Generative Modeling with Bayesian Sample Inferencecited by 4
  2. 2025Predictive Feature Caching for Training-free Acceleration of Molecular Geometry Generationcited by 1
  3. 2025Learning from B Cell Evolution: Adaptive Multi-Expert Diffusion for Antibody Design via Online Optimizationcited by 0
  4. 2026Latent Diffusion-Based 3D Molecular Recovery from Vibrational Spectracited by 0
  5. 2026TriGlue: a Biology-Inspired Generative Model for Generating Molecular Glue-Induced Ternary Complexcited by 0
  6. 2026SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatchcited by 0
  7. 2026GeoGAE: Scalable Graph-Level Autoencoding via Hyperball Cloud Representationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models in textitDe Novo Drug Design
  2. 2025UniMoMo: Unified Generative Modeling of 3D Molecules for De Novo Binder Design
  3. 2025MODA: A Unified 3D Diffusion Framework for Multi-Task Target-Aware Molecular Generation
  4. 2023Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
  5. 2026SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles
  6. 2025Diffusion Models at the Drug Discovery Frontier: A Review on Generating Small Molecules versus Therapeutic Peptides
  7. 2026Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraints
  8. 2024Context-Guided Diffusion for Out-of-Distribution Molecular and Protein Design