MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Zhanpeng, Gao, Weihao, Wang, Shunyu, Zhu, Yanan, Meng, Hong, Zou, Yuexian
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917140791033856
author Chen, Zhanpeng
Gao, Weihao
Wang, Shunyu
Zhu, Yanan
Meng, Hong
Zou, Yuexian
author_facet Chen, Zhanpeng
Gao, Weihao
Wang, Shunyu
Zhu, Yanan
Meng, Hong
Zou, Yuexian
contents Generating precise 3D molecular geometries is crucial for drug discovery and material science. While prior efforts leverage 1D representations like SELFIES to ensure molecular validity, they fail to fully exploit the rich chemical knowledge entangled within 1D models, leading to a disconnect between 1D syntactic generation and 3D geometric realization. To bridge this gap, we propose MolSculpt, a novel framework that "sculpts" 3D molecular geometries from chemical syntax. MolSculpt is built upon a frozen 1D molecular foundation model and a 3D molecular diffusion model. We introduce a set of learnable queries to extract inherent chemical knowledge from the foundation model, and a trainable projector then injects this cross-modal information into the conditioning space of the diffusion model to guide the 3D geometry generation. In this way, our model deeply integrates 1D latent chemical knowledge into the 3D generation process through end-to-end optimization. Experiments demonstrate that MolSculpt achieves state-of-the-art (SOTA) performance in \textit{de novo} 3D molecule generation and conditional 3D molecule generation, showing superior 3D fidelity and stability on both the GEOM-DRUGS and QM9 datasets. Code is available at https://github.com/SakuraTroyChen/MolSculpt.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10991
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
Chen, Zhanpeng
Gao, Weihao
Wang, Shunyu
Zhu, Yanan
Meng, Hong
Zou, Yuexian
Machine Learning
Artificial Intelligence
Chemical Physics
Quantitative Methods
Generating precise 3D molecular geometries is crucial for drug discovery and material science. While prior efforts leverage 1D representations like SELFIES to ensure molecular validity, they fail to fully exploit the rich chemical knowledge entangled within 1D models, leading to a disconnect between 1D syntactic generation and 3D geometric realization. To bridge this gap, we propose MolSculpt, a novel framework that "sculpts" 3D molecular geometries from chemical syntax. MolSculpt is built upon a frozen 1D molecular foundation model and a 3D molecular diffusion model. We introduce a set of learnable queries to extract inherent chemical knowledge from the foundation model, and a trainable projector then injects this cross-modal information into the conditioning space of the diffusion model to guide the 3D geometry generation. In this way, our model deeply integrates 1D latent chemical knowledge into the 3D generation process through end-to-end optimization. Experiments demonstrate that MolSculpt achieves state-of-the-art (SOTA) performance in \textit{de novo} 3D molecule generation and conditional 3D molecule generation, showing superior 3D fidelity and stability on both the GEOM-DRUGS and QM9 datasets. Code is available at https://github.com/SakuraTroyChen/MolSculpt.
title MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
topic Machine Learning
Artificial Intelligence
Chemical Physics
Quantitative Methods
url https://arxiv.org/abs/2512.10991