Assessing Conformer Energies using Electronic Structure and Machine Learning Methods

Folmsbee, Dakota; Hutchison, Geoffrey

doi:10.22541/au.158980890.00617691/v2

Cited by 1 publication

(1 citation statement)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we add the state-ofthe-art D4 dispersion corrections 18,19 including with Axilrod-Teller-Muto three-body contributions 20,21 -the third part of AIQM1 method. These corrections are essential to describe properly dispersion terms in noncovalent interactions as they are described poorly by both SQM 5 and local NN approaches such as ANI-1ccx 22 . For the second part, we took the ANI-type of NN potentials.…”

Section: Methods Structurementioning

confidence: 99%

Artificial Intelligence-Enhanced Quantum Chemical Method with Broad Applicability

Zheng

Zubatyuk

et al. 2021

Preprint

View full text Add to dashboard Cite

High-level quantum mechanical (QM) calculations are indispensable for accurate explanation of natural phenomena on the atomistic level. Their staggering computational cost, however, poses great limitations, which luckily can be lifted to a great extent by exploiting advances in artificial intelligence (AI). Here we introduce the general-purpose, highly transferable artificial intelligence-quantum mechanical method 1 (AIQM1). It approaches the accuracy of the 'gold-standard' coupled cluster QM method with low computational speed of the approximate low-level semiempirical QM methods. AIQM1 can provide accurate groundstate energies for diverse organic compounds as well as geometries for even challenging systems such as large conjugated compounds (fullerene C60) close to experiment. Noteworthy, our method's accuracy is also good for ions and excited-state properties, although the neural network part of AIQM1 was never fitted to these properties.

show abstract

Section: Methods Structurementioning

confidence: 99%

Artificial Intelligence-Enhanced Quantum Chemical Method with Broad Applicability

Zheng

Zubatyuk

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Assessing Conformer Energies using Electronic Structure and Machine Learning Methods

Abstract: This a preprint and has not been peer reviewed. Data may be preliminary.

Cited by 1 publication

References 91 publications

Artificial Intelligence-Enhanced Quantum Chemical Method with Broad Applicability

Artificial Intelligence-Enhanced Quantum Chemical Method with Broad Applicability

Contact Info

Product

Resources

About