Decomposed Direct Preference Optimization for Structure-Based Drug Design
- URL: http://arxiv.org/abs/2407.13981v1
- Date: Fri, 19 Jul 2024 02:12:25 GMT
- Title: Decomposed Direct Preference Optimization for Structure-Based Drug Design
- Authors: Xiwei Cheng, Xiangxin Zhou, Yuwei Yang, Yu Bao, Quanquan Gu,
- Abstract summary: We propose a new structure-based molecular optimization method called DecompDPO.
It decomposes the molecule into arms and scaffolds and performs preference optimization at both local substructure and global molecule levels.
Experiments on the CrossDocked 2020 benchmark show that DecompDPO significantly improves model performance in both molecule generation and optimization.
- Score: 47.561983733291804
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: 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 the alignment of generative models such as large language models and diffusion models, providing greater flexibility and accuracy by directly aligning model outputs with human preferences. Building on this advancement, we introduce DPO to SBDD in this paper. We tailor diffusion models to pharmaceutical needs by aligning them with elaborately designed chemical score functions. We propose a new structure-based molecular optimization method called DecompDPO, which decomposes the molecule into arms and scaffolds and performs preference optimization at both local substructure and global molecule levels, allowing for more precise control with fine-grained preferences. 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 in both molecule generation and optimization, with up to 100% Median High Affinity and a 54.9% Success Rate.
Related papers
- Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization [147.7899503829411]
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.
We 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.
arXiv Detail & Related papers (2024-07-01T06:10:29Z) - TAGMol: Target-Aware Gradient-guided Molecule Generation [19.977071499171903]
3D generative models have shown significant promise in structure-based drug design (SBDD)
We decouple the problem into molecular generation and property prediction.
The latter synergistically guides the diffusion sampling process, facilitating guided diffusion and resulting in the creation of meaningful molecules with the desired properties.
We call this guided molecular generation process as TAGMol.
arXiv Detail & Related papers (2024-06-03T14:43:54Z) - PILOT: Equivariant diffusion for pocket conditioned de novo ligand generation with multi-objective guidance via importance sampling [8.619610909783441]
We propose an in-silico approach for the $textitde novo$ generation of 3D ligand structures using the equivariant diffusion model PILOT.
Its multi-objective-based importance sampling strategy is designed to direct the model towards molecules that exhibit desired characteristics.
We employ PILOT to generate novel metrics for unseen protein pockets from the Kinodata-3D dataset.
arXiv Detail & Related papers (2024-05-23T17:58:28Z) - Guided Multi-objective Generative AI to Enhance Structure-based Drug Design [0.0]
We describe IDOLpro, a novel generative chemistry AI combining deep diffusion with multi-objective optimization.
IDOLpro produces with binding affinities over 10% higher than the next best state-of-the-art on each test set.
arXiv Detail & Related papers (2024-05-20T05:08:55Z) - DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization [49.85944390503957]
DecompOpt is a structure-based molecular optimization method based on a controllable and diffusion model.
We show that DecompOpt can efficiently generate molecules with improved properties than strong de novo baselines.
arXiv Detail & Related papers (2024-03-07T02:53:40Z) - Diffusion Model Alignment Using Direct Preference Optimization [103.2238655827797]
Diffusion-DPO is a method to align diffusion models to human preferences by directly optimizing on human comparison data.
We fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO.
We also develop a variant that uses AI feedback and has comparable performance to training on human preferences.
arXiv Detail & Related papers (2023-11-21T15:24:05Z) - Protein Design with Guided Discrete Diffusion [67.06148688398677]
A popular approach to protein design is to combine a generative model with a discriminative model for conditional sampling.
We propose diffusioN Optimized Sampling (NOS), a guidance method for discrete diffusion models.
NOS makes it possible to perform design directly in sequence space, circumventing significant limitations of structure-based methods.
arXiv Detail & Related papers (2023-05-31T16:31:24Z) - Molecular Attributes Transfer from Non-Parallel Data [57.010952598634944]
We formulate molecular optimization as a style transfer problem and present a novel generative model that could automatically learn internal differences between two groups of non-parallel data.
Experiments on two molecular optimization tasks, toxicity modification and synthesizability improvement, demonstrate that our model significantly outperforms several state-of-the-art methods.
arXiv Detail & Related papers (2021-11-30T06:10:22Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.