OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features
By Zhuoran Qiao, Matthew Welborn, Anima Anandkumar, Frederick R. Manby, Thomas F. Miller. 2020
263 citations recorded by the source corpus.
We introduce a machine learning method in which energy solutions from the Schrödinger equation are predicted using symmetry adapted atomic orbital features and a graph neural-network architecture. OrbNet is shown to outperform existing methods in terms of learning efficiency and transferability for the prediction of density functional theory results while employing low-cost features that are obtained from semi-empirical electronic structure calculations. For applications to datasets of drug-like molecules, including QM7b-T, QM9, GDB-13-T, DrugBank, and the conformer benchmark dataset of Folmsbee and Hutchison [Int. J. Quantum Chem. (published online) (2020)], OrbNet predicts energies within chemical accuracy of density functional theory at a computational cost that is 1000-fold or more reduced.
Subfields: Artificial Intelligence, Computational Theory and Mathematics, Materials Chemistry
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Devi Parikh
- Dhruv Batra
- Mohit Bansal
- Abhishek Das
- C. Lawrence Zitnick
- Trevor Darrell
- Jianfeng Gao
- Hanwang Zhang
In Computational Theory and Mathematics
- Francesca Grisoni
- Gisbert Schneider
- José Jiménez-Luna
- Nils Weskamp
- Tianfan Fu
- Devi Parikh
- Shengchao Liu
- C. Lawrence Zitnick
In Materials Chemistry
- Francesca Grisoni
- Gisbert Schneider
- José Jiménez-Luna
- Nils Weskamp
- Shengchao Liu
- Jimeng Sun
- Brandon Wood
- Abhishek Das
Citations in the corpus
- Artificial intelligence in drug discovery: recent advances and future perspectives (2021, methodology): “These architectures have already been applied to several molecular tasks, such as the prediction of electronic properties of molecules [88].”
- MolGenSurvey: A Systematic Survey in Machine Learning Models for Molecule Design (2022, methodology): “This research line includes SchNet [47], OrbNet [48], DimeNet [49], [50], TFN [51], SE(3)-Transformer [51], EGNN [52], Spin-Conv [53], SphereNet [54], EVFN [55], UNiTE [56], SEGNN [57], PaiNN [58], and GemNet [59].”
- An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage (2020, background): “A promising approach to achieving higher accuracy while improving efficiency is the incorporation of more domain specific features, such as those obtained from mean-field electronic structure methods [116], or atomic orbital interaction features for crystal structures [129].”