# Decomposed Direct Preference Optimization for Structure-Based Drug Design

arXiv: https://arxiv.org/abs/2407.13981 · HTML: https://mlsanity.com/paper/2407.13981/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 37 of its 58 references that are in the map.
- First posted on arXiv 19 Jul 2024.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 30 of 37)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Structure-based Drug Design with Equivariant Diffusion Models](https://mlsanity.com/paper/2210.13695/) (2022)
- [Pocket2Mol: Efficient Molecular Sampling Based on 3D Protein Pockets](https://mlsanity.com/paper/2205.07249/) (2022)
- [3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction](https://mlsanity.com/paper/2303.03543/) (2023)
- [A 3D Generative Model for Structure-Based Drug Design](https://mlsanity.com/paper/2203.10446/) (2022)
- [MARS: Markov Molecular Sampling for Multi-objective Drug Discovery](https://mlsanity.com/paper/2103.10432/) (2021)
- [Diffusion-based Molecule Generation with Informative Prior Bridges](https://mlsanity.com/paper/2209.00865/) (2022)
- [Generating 3D Molecules for Target Protein Binding](https://mlsanity.com/paper/2204.09410/) (2022)
- [DecompDiff: Diffusion Models with Decomposed Priors for Structure-Based Drug Design](https://mlsanity.com/paper/2403.07902/) (2024)
- [Large-scale Reinforcement Learning for Diffusion Models](https://mlsanity.com/paper/2401.12244/) (2024)
- [Generating 3D Molecules Conditional on Receptor Binding Sites with Deep Generative Models](https://mlsanity.com/paper/2110.15200/) (2021)
- [MolDiff: Addressing the Atom-Bond Inconsistency Problem in 3D Molecule Diffusion Generation](https://mlsanity.com/paper/2305.07508/) (2023)
- [DiffBP: Generative Diffusion of 3D Molecules for Target Protein Binding](https://mlsanity.com/paper/2211.11214/) (2022)
- [MolCRAFT: Structure-Based Drug Design in Continuous Parameter Space](https://mlsanity.com/paper/2404.12141/) (2024)
- [Reinforced Genetic Algorithm for Structure-based Drug Design](https://mlsanity.com/paper/2211.16508/) (2022)
- [Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization](https://mlsanity.com/paper/2403.16576/) (2024)

## Built on by (most cited first, 7 of 7)

- [Multi-domain Distribution Learning for De Novo Drug Design](https://mlsanity.com/paper/2508.17815/) (2025)
- [BalancedDPO: Adaptive Multi-Metric Alignment](https://mlsanity.com/paper/2503.12575/) (2025)
- [Integrating Protein Dynamics into Structure-Based Drug Design via Full-Atom Stochastic Flows](https://mlsanity.com/paper/2503.03989/) (2025)
- [MolChord: Structure-Sequence Alignment for Protein-Guided Drug Design](https://mlsanity.com/paper/2510.27671/) (2025)
- [Fine-tuning Pocket-Aware Diffusion Models via Denoising Policy Optimization](https://mlsanity.com/paper/2605.17693/) (2026)
- [Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design](https://mlsanity.com/paper/2606.00555/) (2026)
- [CORAL: Learning Amyloid Fibril Ligand Docking with Cooperative Binding Rewards](https://mlsanity.com/paper/2607.17412/) (2026)

## Abstract (arXiv)

Diffusion models have achieved promising results for Structure-Based Drug Design (SBDD). Nevertheless, high-quality protein subpocket and ligand data are relatively scarce, which hinders the models' generation capabilities. Recently, Direct Preference Optimization (DPO) has emerged as a pivotal tool for aligning generative models with human preferences. In this paper, we propose DecompDPO, a structure-based optimization method aligns diffusion models with pharmaceutical needs using multi-granularity preference pairs. DecompDPO introduces decomposition into the optimization objectives and obtains preference pairs at the molecule or decomposed substructure level based on each objective's decomposability. Additionally, DecompDPO introduces a physics-informed energy term to ensure reasonable molecular conformations in the optimization results. Notably, DecompDPO can be effectively used for two main purposes: (1) fine-tuning pretrained diffusion models for molecule generation across various protein families, and (2) molecular optimization given a specific protein subpocket after generation. Extensive experiments on the CrossDocked2020 benchmark show that DecompDPO significantly improves model performance, achieving up to 95.2% Med. High Affinity and a 36.2% success rate for molecule generation, and 100% Med. High Affinity and a 52.1% success rate for molecular optimization. Code is available at https://github.com/laviaf/DecompDPO.