Data-driven quantum chemical property prediction leveraging 3D conformations with Uni-Mol

Quantum chemical (QC) property prediction is crucial for computational materials and drug design, but relies on expensive electronic structure calculations like density functional theory (DFT). Recent deep learning methods accelerate this process using 1D SMILES or 2D graphs as inputs but struggle t...

Full description

Saved in:
Bibliographic Details
Published inNature communications Vol. 15; no. 1; pp. 7104 - 11
Main Authors Lu, Shuqi, Gao, Zhifeng, He, Di, Zhang, Linfeng, Ke, Guolin
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 19.08.2024
Nature Publishing Group
Nature Portfolio
Subjects
639/638/563/606
639/705/1042
Accuracy
Computational chemistry
Computer applications
Conformation
Deep learning
Density functional theory
Drug development
Electronic structure
Humanities and Social Sciences
Iterative methods
Molecular structure
multidisciplinary
Neural networks
Predictions
Quantum chemistry
Science
Science (multidisciplinary)
Online AccessGet full text

Cover

More Information
Summary:Quantum chemical (QC) property prediction is crucial for computational materials and drug design, but relies on expensive electronic structure calculations like density functional theory (DFT). Recent deep learning methods accelerate this process using 1D SMILES or 2D graphs as inputs but struggle to achieve high accuracy as most QC properties depend on refined 3D molecular equilibrium conformations. We introduce Uni-Mol+, a deep learning approach that leverages 3D conformations for accurate QC property prediction. Uni-Mol+ first generates a raw 3D conformation using RDKit then iteratively refines it towards DFT equilibrium conformation using neural networks, which is finally used to predict the QC properties. To effectively learn this conformation update process, we introduce a two-track Transformer model backbone and a novel training approach. Our benchmarking results demonstrate that the proposed Uni-Mol+ significantly improves the accuracy of QC property prediction in various datasets. Quantum chemical (QC) property prediction is crucial in computational chemistry. Here, the authors introduce Uni-Mol+, a deep model that uses iterative updates of 3D molecular conformations to improves the accuracy of QC property prediction.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2041-1723
2041-1723
DOI:10.1038/s41467-024-51321-w