Combining machine learning and computational chemistry for predictive insights into chemical systems

JA Keith, V Vassilev-Galindo, B Cheng… - Chemical …, 2021 - ACS Publications
Machine learning models are poised to make a transformative impact on chemical sciences
by dramatically accelerating computational algorithms and amplifying insights available from …

Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations

AM Miksch, T Morawietz, J Kästner… - Machine Learning …, 2021 - iopscience.iop.org
Recent advances in machine-learning interatomic potentials have enabled the efficient
modeling of complex atomistic systems with an accuracy that is comparable to that of …

Realistic phase diagram of water from “first principles” data-driven quantum simulations

SL Bore, F Paesani - Nature communications, 2023 - nature.com
Since the experimental characterization of the low-pressure region of water's phase diagram
in the early 1900s, scientists have been on a quest to understand the thermodynamic …

Weakly hydrated anions bind to polymers but not monomers in aqueous solutions

BA Rogers, HI Okur, C Yan, T Yang, J Heyda… - Nature Chemistry, 2022 - nature.com
Weakly hydrated anions help to solubilize hydrophobic macromolecules in aqueous
solutions, but small molecules comprising the same chemical constituents precipitate out …

Coupled cluster molecular dynamics of condensed phase systems enabled by machine learning potentials: Liquid water benchmark

J Daru, H Forbert, J Behler, D Marx - Physical Review Letters, 2022 - APS
Coupled cluster theory is a general and systematic electronic structure method, but in
particular the highly accurate “gold standard” coupled cluster singles, doubles and …

Data-efficient machine learning potentials from transfer learning of periodic correlated electronic structure methods: Liquid water at AFQMC, CCSD, and CCSD (T) …

MS Chen, J Lee, HZ Ye, TC Berkelbach… - Journal of Chemical …, 2023 - ACS Publications
Obtaining the atomistic structure and dynamics of disordered condensed-phase systems
from first-principles remains one of the forefront challenges of chemical theory. Here we …

Dissecting the hydrogen bond network of water: Charge transfer and nuclear quantum effects

M Flór, DM Wilkins, M de la Puente, D Laage… - Science, 2024 - science.org
The molecular structure of water is dynamic, with intermolecular hydrogen (H) bond
interactions being modified by both electronic charge transfer and nuclear quantum effects …

Committee neural network potentials control generalization errors and enable active learning

C Schran, K Brezina, O Marsalek - The Journal of Chemical Physics, 2020 - pubs.aip.org
It is well known in the field of machine learning that committee models improve accuracy,
provide generalization error estimates, and enable active learning strategies. In this work …

First-principles spectroscopy of aqueous interfaces using machine-learned electronic and quantum nuclear effects

V Kapil, DP Kovács, G Csányi, A Michaelides - Faraday Discussions, 2024 - pubs.rsc.org
Vibrational spectroscopy is a powerful approach to visualising interfacial phenomena.
However, extracting structural and dynamical information from vibrational spectra is a …

The key role of solvent in condensation: Map** water in liquid-liquid phase-separated FUS

J Ahlers, EM Adams, V Bader, S Pezzotti… - Biophysical journal, 2021 - cell.com
Formation of biomolecular condensates through liquid-liquid phase separation (LLPS) has
emerged as a pervasive principle in cell biology, allowing compartmentalization and …