Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Qiu, Keyue, Song, Yuxuan, Yu, Jie, Ma, Hongbo, Cao, Ziyao, Zhang, Zhilong, Wu, Yushuai, Zheng, Mingyue, Zhou, Hao, Ma, Wei-Ying
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909637950832640
author Qiu, Keyue
Song, Yuxuan
Yu, Jie
Ma, Hongbo
Cao, Ziyao
Zhang, Zhilong
Wu, Yushuai
Zheng, Mingyue
Zhou, Hao
Ma, Wei-Ying
author_facet Qiu, Keyue
Song, Yuxuan
Yu, Jie
Ma, Hongbo
Cao, Ziyao
Zhang, Zhilong
Wu, Yushuai
Zheng, Mingyue
Zhou, Hao
Ma, Wei-Ying
contents Structure-Based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets. A promising direction is to exert gradient guidance on generative models given its remarkable success in images, but it is challenging to guide discrete data and risks inconsistencies between modalities. To this end, we leverage a continuous and differentiable space derived through Bayesian inference, presenting Molecule Joint Optimization (MolJO), the gradient-based SBMO framework that facilitates joint guidance signals across different modalities while preserving SE(3)-equivariance. We introduce a novel backward correction strategy that optimizes within a sliding window of the past histories, allowing for a seamless trade-off between explore-and-exploit during optimization. MolJO achieves state-of-the-art performance on CrossDocked2020 benchmark (Success Rate 51.3%, Vina Dock -9.05 and SA 0.78), more than 4x improvement in Success Rate compared to the gradient-based counterpart, and 2x "Me-Better" Ratio as much as 3D baselines. Furthermore, we extend MolJO to a wide range of optimization settings, including multi-objective optimization and challenging tasks in drug design such as R-group optimization and scaffold hopping, further underscoring its versatility. Code is available at https://github.com/AlgoMole/MolCRAFT.
format Preprint
id arxiv_https___arxiv_org_abs_2411_13280
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
Qiu, Keyue
Song, Yuxuan
Yu, Jie
Ma, Hongbo
Cao, Ziyao
Zhang, Zhilong
Wu, Yushuai
Zheng, Mingyue
Zhou, Hao
Ma, Wei-Ying
Biomolecules
Artificial Intelligence
Structure-Based molecule optimization (SBMO) aims to optimize molecules with both continuous coordinates and discrete types against protein targets. A promising direction is to exert gradient guidance on generative models given its remarkable success in images, but it is challenging to guide discrete data and risks inconsistencies between modalities. To this end, we leverage a continuous and differentiable space derived through Bayesian inference, presenting Molecule Joint Optimization (MolJO), the gradient-based SBMO framework that facilitates joint guidance signals across different modalities while preserving SE(3)-equivariance. We introduce a novel backward correction strategy that optimizes within a sliding window of the past histories, allowing for a seamless trade-off between explore-and-exploit during optimization. MolJO achieves state-of-the-art performance on CrossDocked2020 benchmark (Success Rate 51.3%, Vina Dock -9.05 and SA 0.78), more than 4x improvement in Success Rate compared to the gradient-based counterpart, and 2x "Me-Better" Ratio as much as 3D baselines. Furthermore, we extend MolJO to a wide range of optimization settings, including multi-objective optimization and challenging tasks in drug design such as R-group optimization and scaffold hopping, further underscoring its versatility. Code is available at https://github.com/AlgoMole/MolCRAFT.
title Empower Structure-Based Molecule Optimization with Gradient Guided Bayesian Flow Networks
topic Biomolecules
Artificial Intelligence
url https://arxiv.org/abs/2411.13280