Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments

2024/04/05 by Oliver T. Unke, Martin Stöhr, Stefan Ganscha +9 · 1 voice · 5 citations
Biochemistry, Genetics and Molecular Biology · Materials Science · #Advanced Electron Microscopy Techniques and Applications #Machine Learning in Materials Science #Protein Structure and Dynamics

paper · pdf · doi:10.1126/sciadv.adn4397

openalex publication_date 2024/04/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The GEMS method enables molecular dynamics simulations of large heterogeneous systems at ab initio quality.

Citations

• Polymorphic transitions in single crystals: A new molecular dynamics method
• Molecular dynamics simulations of biomolecules
• Knowledge‐based protein secondary structure assignment
• Improved side‐chain torsion potentials for the Amber ff99SB protein force field
• <i>Ab initio</i> solution of the many-electron Schrödinger equation with deep neural networks
• Machine Learning for Molecular Simulation
• Improved protein structure prediction using potentials from deep learning
• Cryo-EM structure of the 2019-nCoV spike in the prefusion conformation
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Four Generations of High-Dimensional Neural Network Potentials
• Highly accurate protein structure prediction with AlphaFold
• Highly accurate protein structure prediction for the human proteome

Cited by

• On the design space between molecular mechanics and machine learning force fields
• Cluster Models for Next-Generation, Machine-Learning-Based Energy Functions for Molecular Simulations
• Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields
• aims-PAX: Parallel Active eXploration for the automated construction of Machine Learning Force Fields
• Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations

Discussions

• 2/3 Unke et al. (2024) https://doi.org/10.1126/sciadv.adn4397 developed GEMS—machine-learned quantum-mechanical force fields trained on diverse fragments. They achieve ab initio accuracy at orders-of- [bsky, 0 points, 1 comments]

Related

• Biomolecular dynamics with machine-learned quantum-mechanical force fields trained on diverse chemical fragments
• Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
• Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields
• Molecular Dynamics Simulations: Principles, Algorithms, and Emerging Applications
• QCell: Comprehensive Quantum-Mechanical Dataset Spanning Diverse Biomolecular Fragments