mlsanityData to 7 Oct 2026

Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization

arXiv 2407.01648 ↗First posted 1 Jul 2024q-bio.BM cs.LG q-bio.QMcited by 25

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

Abstract (arXiv)

Generating ligand molecules for specific protein targets, known as structure-based drug design, is a fundamental problem in therapeutics development and biological discovery. Recently, target-aware generative models, especially diffusion models, have shown great promise in modeling protein-ligand interactions and generating candidate drugs. However, existing models primarily focus on learning the chemical distribution of all drug candidates, which lacks effective steerability on the chemical quality of model generations. In this paper, we propose a novel and general alignment framework to align pretrained target diffusion models with preferred functional properties, named AliDiff. AliDiff shifts the target-conditioned chemical distribution towards regions with higher binding affinity and structural rationality, specified by user-defined reward functions, via the preference optimization approach. To avoid the overfitting problem in common preference optimization objectives, we further develop an improved Exact Energy Preference Optimization method to yield an exact and efficient alignment of the diffusion models, and provide the closed-form expression for the converged distribution. Empirical studies on the CrossDocked2020 benchmark show that AliDiff can generate molecules with state-of-the-art binding energies with up to -7.07 Avg. Vina Score, while maintaining strong molecular properties. Code is available at https://github.com/MinkaiXu/AliDiff.

Key facts. Cited by 25 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 26 of its 44 references that are in the map. First posted on arXiv 1 Jul 2024.

Builds on

26 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design26 Feb
  2. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generation6 Mar

Other references · 24

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 7,916
  4. 2020Learning to summarize from human feedbackcited by 2,562
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  6. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  7. 2023A General Theoretical Paradigm to Understand Learning from Human Preferencescited by 906
  8. 2023Diffusion Model Alignment Using Direct Preference Optimizationcited by 767
  9. 2018Junction Tree Variational Autoencoder for Molecular Graph Generationcited by 647
  10. 2020GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generationcited by 301
  11. 2017Grammar Variational Autoencodercited by 283
  12. 2022Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pocketscited by 182
12 more
  1. 20233D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Predictioncited by 176
  2. 2024Generalized Preference Optimization: A Unified Approach to Offline Alignmentcited by 155
  3. 2022A 3D Generative Model for Structure-Based Drug Designcited by 148
  4. 2024Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Controlcited by 136
  5. 2022Generating 3D Molecules for Target Protein Bindingcited by 104
  6. 2024Noise Contrastive Alignment of Language Models with Explicit Rewardscited by 85
  7. 2021Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Modelscited by 72
  8. 2017Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedbackcited by 71
  9. 2024Feedback Efficient Online Fine-Tuning of Diffusion Modelscited by 52
  10. 2022State-specific protein-ligand complex structure prediction with a multi-scale deep generative modelcited by 35
  11. 2024Antigen-Specific Antibody Design via Direct Energy-based Preference Optimizationcited by 30
  12. 2023Learning Subpocket Prototypes for Generalizable Structure-based Drug Designcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 10; 2026: 12.

25 papers.

Sort:

By area:

  1. 2024Alignment of Diffusion Models: Fundamentals, Challenges, and Futurecited by 34
  2. 2025Multi-domain Distribution Learning for De Novo Drug Designcited by 15
  3. 2024Decomposed Direct Preference Optimization for Structure-Based Drug Designcited by 7
  4. 2025Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Numbercited by 6
  5. 2025Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHFcited by 5
  6. 2025Aligning Protein Conformation Ensemble Generation with Physical Feedbackcited by 5
  7. 2025De Novo Molecular Design Enabled by Direct Preference Optimization and Curriculum Learningcited by 4
  8. 2025Unraveling the Potential of Diffusion Models in Small Molecule Generationcited by 3
  9. 2025Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integrationcited by 2
  10. 2025MolChord: Structure-Sequence Alignment for Protein-Guided Drug Designcited by 2
  11. 2026Empowering LLMs for Structure-Based Drug Design via Exploration-Augmented Latent Inferencecited by 2
  12. 2025MolPIF: A Parameter Interpolation Flow Model for Molecule Generationcited by 1
13 more
  1. 2026Generating Developable 3D Molecules via Pocket-Conditioned Diffusion and Property-Aware Optimizationcited by 1
  2. 2024Fragment-Masked Diffusion for Molecular Optimizationcited by 0
  3. 2025TransDiffSBDD: Causality-Aware Multi-Modal Structure-Based Drug Designcited by 0
  4. 2026Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimizationcited by 0
  5. 2026Fine-Tuning Diffusion Models for Molecular Generation via Reinforcement Learning and Fast Samplingcited by 0
  6. 2026CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewardscited by 0
  7. 2026Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial Constraintscited by 0
  8. 2026Fused Bayesian Flow Networks for Dual-Target Molecular Designcited by 0
  9. 2026SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatchcited by 0
  10. 2026PocketVE: Stable and Property-Guided Structure-Based Drug Design with Variance-Exploding Diffusioncited by 0
  11. 2026A Systematic Evaluation of Molecule Generation Models for De Novo Drug Design: From Benchmarks to Practical Insightscited by 0
  12. 2026FestDPO: Few-step Generator Alignment with Direct Preference Optimizationcited by 0
  13. 2026RIDE: Reference-Anchored Inference-Time Diffusion Editing for Scaffold Hoppingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025BoKDiff: Best-of-K Diffusion Alignment for Target-Specific 3D Molecule Generation
  2. 2025A 3D pocket-aware and evolutionary conserved interaction guided diffusion model for molecular optimization
  3. 2022DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding
  4. 2025Molecule Generation for Target Protein Binding with Hierarchical Consistency Diffusion Model
  5. 2025READ: A Retrieval-Alignment Diffusion Framework for Structure-based Drug Design
  6. 2022Structure-based Drug Design with Equivariant Diffusion Models
  7. 2023Leveraging Side Information for Ligand Conformation Generation using Diffusion-Based Approaches
  8. 2024DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization