Data generation for machine learning interatomic potentials and beyond

M Kulichenko, B Nebgen, N Lubbers, JS Smith… - Chemical …, 2024 - ACS Publications
The field of data-driven chemistry is undergoing an evolution, driven by innovations in
machine learning models for predicting molecular properties and behavior. Recent strides in …

Recent Advances in Machine Learning‐Assisted Multiscale Design of Energy Materials

B Mortazavi - Advanced Energy Materials, 2024 - Wiley Online Library
This review highlights recent advances in machine learning (ML)‐assisted design of energy
materials. Initially, ML algorithms were successfully applied to screen materials databases …

A Euclidean transformer for fast and stable machine learned force fields

JT Frank, OT Unke, KR Müller, S Chmiela - Nature Communications, 2024 - nature.com
Recent years have seen vast progress in the development of machine learned force fields
(MLFFs) based on ab-initio reference calculations. Despite achieving low test errors, the …

Ab initio characterization of protein molecular dynamics with AI2BMD

T Wang, X He, M Li, Y Li, R Bi, Y Wang, C Cheng… - Nature, 2024 - nature.com
Biomolecular dynamics simulation is a fundamental technology for life sciences research,
and its usefulness depends on its accuracy and efficiency,–. Classical molecular dynamics …

Prospective de novo drug design with deep interactome learning

K Atz, L Cotos, C Isert, M Håkansson, D Focht… - Nature …, 2024 - nature.com
De novo drug design aims to generate molecules from scratch that possess specific
chemical and pharmacological properties. We present a computational approach utilizing …

ArcaNN: automated enhanced sampling generation of training sets for chemically reactive machine learning interatomic potentials

R David, M de la Puente, A Gomez, O Anton… - Digital …, 2025 - pubs.rsc.org
The emergence of artificial intelligence is profoundly impacting computational chemistry,
particularly through machine-learning interatomic potentials (MLIPs). Unlike traditional …

Grappa–a machine learned molecular mechanics force field

L Seute, E Hartmann, J Stühmer, F Gräter - Chemical Science, 2025 - pubs.rsc.org
Simulating large molecular systems over long timescales requires force fields that are both
accurate and efficient. In recent years, E (3) equivariant neural networks have lifted the …

Molecular simulations with a pretrained neural network and universal pairwise force fields

A Kabylda, JT Frank, SS Dou, A Khabibrakhmanov… - 2025 - chemrxiv.org
Machine Learning Force Fields (MLFFs) promise to enable general molecular simulations
that can simultaneously achieve efficiency, accuracy, transferability, and scalability for …

Peering inside the black box: Learning the relevance of many-body functions in Neural Network potentials

K Bonneau, J Lederer, C Templeton… - arxiv preprint arxiv …, 2024 - arxiv.org
Machine learned potentials are becoming a popular tool to define an effective energy model
for complex systems, either incorporating electronic structure effects at the atomistic …

Towards symbolic XAI–explanation through human understandable logical relationships between features

T Schnake, FR Jafari, J Lederer, P **ong, S Nakajima… - Information …, 2025 - Elsevier
Abstract Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency
and trust in AI systems. Traditional XAI methods typically provide a single level of abstraction …