analiza aiqbench
OrbitAll represents a significant advancement in the intersection of quantum chemistry and machine learning by leveraging spin-polarized orbital features within an SE(3)-equivariant graph neural network architecture. This framework achieves chemical accuracy with drastically reduced training data requirements while offering orders-of-magnitude speedups over traditional density functional theory calculations for complex molecular systems. Its ability to robustly handle charged, open-shell, and solvated molecules marks a critical step toward scalable AI-driven quantum mechanical simulations.
OrbitAll: A Unified Quantum Mechanical Representation Deep Learning Framework for All Molecular Systems
arXiv:2507.03853v2 Announce Type: replace Abstract: We introduce OrbitAll, a geometry- and physics-informed deep learning framework that encodes any molecular system with arbitrary charges, spins, and environmental effects using electronic structure information. It utilizes spin-polarized orbital features from the underlying quantum mechanical method and combines them with SE(3)-equivariant graph neural networks. OrbitAll demonstrates superior performance and generalization in predicting charged, open-shell, and solvated molecules, and robustly extrapolates to molecules significantly larger than the training data. OrbitAll achieves chemical accuracy using 10 times fewer training data than competing AI models, with approximately $10^3$ - $10^4$ speedup compared to density functional theory. Trained on a chemically diverse dataset, OrbitAll performs robustly on challenging molecular systems, and outperforms the foundational machine-learned interatomic potential, UMA, for highly charged species, despite using 35 times less molecular data and a 50-times-smaller model. After learning solvent effects, it accurately predicts solvent-dependent reaction pathways at about 100 times lower cost than explicit-solvation simulations using UMA.
Abstract:We introduce OrbitAll, a geometry- and physics-informed deep learning framework that encodes any molecular system with arbitrary charges, spins, and environmental effects using electronic structure information. It utilizes spin-polarized orbital features from the underlying quantum mechanical method and combines them with SE(3)-equivariant graph neural networks. OrbitAll demonstrates superior performance and generalization in predicting charged, open-shell, and solvated molecules, and robustly extrapolates to molecules significantly larger than the training data. OrbitAll achieves chemical accuracy using 10 times fewer training data than competing AI models, with approximately $10^3$ - $10^4$ speedup compared to density functional theory. Trained on a chemically diverse dataset, OrbitAll performs robustly on challenging molecular systems, and outperforms the foundational machine-learned interatomic potential, UMA, for highly charged species, despite using 35 times less molecular data and a 50-times-smaller model. After learning solvent effects, it accurately predicts solvent-dependent reaction pathways at about 100 times lower cost than explicit-solvation simulations using UMA.
Machine Learning (cs.LG); Chemical Physics (physics.chem-ph)
arXiv:2507.03853 [cs.LG]
(or arXiv:2507.03853v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2507.03853 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 246 cuvinte
