Despite the success of deep learning methods in quantum chemistry, their representational capacity is most often confined to neutral, closed-shell molecules. However, real-world chemical systems often exhibit complex characteristics, including varying charges, spins, and environments. We introduce OrbitAll, a geometry- and physics-informed deep learning framework that can represent all molecular systems with electronic structure information. OrbitAll utilizes spin-polarized orbital features from the underlying quantum mechanical method, and combines it with graph neural networks satisfying SE(3)-equivariance. The resulting framework can represent and process any molecular system with arbitrary charges, spins, and environmental effects. OrbitAll demonstrates superior performance and generalization on predicting charged, open-shell, and solvated molecules, while also robustly extrapolating to molecules significantly larger than the training data by leveraging a physics-informed architecture. OrbitAll achieves chemical accuracy using 10 times fewer training data than competing AI models, with a speedup of approximately 103 - 104 compared to density functional theory.
@article{arxiv.2507.03853,
title = {OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systems},
author = {Beom Seok Kang and Vignesh C. Bhethanabotla and Amin Tavakoli and Maurice D. Hanisch and William A. Goddard and Anima Anandkumar},
journal= {arXiv preprint arXiv:2507.03853},
year = {2025}
}