ControlMol: Adding Substructure Control To Molecule Diffusion Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhengyang, Qi, Zijing, Liu, Jiying, Zhang, He, Cao, Yu, Li
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913622314188800
author Zhengyang, Qi
Zijing, Liu
Jiying, Zhang
He, Cao
Yu, Li
author_facet Zhengyang, Qi
Zijing, Liu
Jiying, Zhang
He, Cao
Yu, Li
contents Due to the vast design space of molecules, generating molecules conditioned on a specific sub-structure relevant to a particular function or therapeutic target is a crucial task in computer-aided drug design. Existing works mainly focus on specific tasks, such as linker design or scaffold hopping, each task requires training a model from scratch, and many well-pretrained De Novo molecule generation model parameters are not effectively utilized. To this end, we propose a two-stage training approach, consisting of condition learning and condition optimization. In the condition learning stage, we adopt the idea of ControlNet and design some meaningful adjustments to make the unconditional generative model learn sub-structure conditioned generation. In the condition optimization stage, by using human preference learning, we further enhance the stability and robustness of sub-structure control. In our experiments, only trained on randomly partitioned sub-structure data, the proposed method outperforms previous techniques by generating more valid and diverse molecules. Our method is easy to implement and can be quickly applied to various pre-trained molecule generation models.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06659
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ControlMol: Adding Substructure Control To Molecule Diffusion Models
Zhengyang, Qi
Zijing, Liu
Jiying, Zhang
He, Cao
Yu, Li
Biomolecules
Artificial Intelligence
Machine Learning
Chemical Physics
Due to the vast design space of molecules, generating molecules conditioned on a specific sub-structure relevant to a particular function or therapeutic target is a crucial task in computer-aided drug design. Existing works mainly focus on specific tasks, such as linker design or scaffold hopping, each task requires training a model from scratch, and many well-pretrained De Novo molecule generation model parameters are not effectively utilized. To this end, we propose a two-stage training approach, consisting of condition learning and condition optimization. In the condition learning stage, we adopt the idea of ControlNet and design some meaningful adjustments to make the unconditional generative model learn sub-structure conditioned generation. In the condition optimization stage, by using human preference learning, we further enhance the stability and robustness of sub-structure control. In our experiments, only trained on randomly partitioned sub-structure data, the proposed method outperforms previous techniques by generating more valid and diverse molecules. Our method is easy to implement and can be quickly applied to various pre-trained molecule generation models.
title ControlMol: Adding Substructure Control To Molecule Diffusion Models
topic Biomolecules
Artificial Intelligence
Machine Learning
Chemical Physics
url https://arxiv.org/abs/2405.06659