Local Variational Graph Coarsening for Machine Learning Coarse-Grained Molecular Dynamics Simulations

Soumya Mondal¹, Subhanu Halder², Debarchan Basu³, Franz Görlich⁴, Sandeep Kumar³, and Tarak Karmakar^1
1Department of Chemistry, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
²Department of Electrical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
³Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India
⁴Professorship of Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich, 80333 Munich, Germany

Journal of Chemical Theory and Computation | DOI: 10.1021/acs.jctc.6c00825

Mapping Still Matters: Coarse-Graining with Machine Learning Potentials

Franz Görlich¹ and Julija Zavadlav^1,2
1Professorship of Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich, 80333 Munich, Germany
²Atomistic Modeling Center (AMC), Munich Data Science Institute (MDSI), Technical University of Munich, 85748 Garching, Germany

Journal of Chemical Information and Modeling | DOI: 10.1021/acs.jcim.5c03035

Enhanced Sampling for Efficient Learning of Coarse-Grained Machine Learning Potentials

Weilong Chen¹, Franz Görlich¹, Paul Fuchs¹, and Julija Zavadlav^1,2
1Professorship of Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich, 80333 Munich, Germany
²Atomistic Modeling Center (AMC), Munich Data Science Institute (MDSI), Technical University of Munich, 85748 Garching, Germany

Journal of Chemical Theory and Computation | DOI: 10.1021/acs.jctc.5c01712

A chemical language model for molecular taste prediction

Yoel Zimmermann^1,2, Leif Sieben^1,2, Henrik Seng^1,2, Philipp Pestlin^1,2, & Franz Görlich^1,2
1Department of Chemistry and Applied Biosciences, ETH Zurich, Zurich, Switzerland
²These authors contributed equally (authors sorted rev. alphabetical)

npj Science of Food | DOI: 10.1038/s41538-025-00474-z

Equivariant MLIPs for Coarse-Grained Modelling: Pitfalls and Practical Adaptations

Selected Early-Career Talk at CG-ML 2026 · ENS de Lyon, France · 14 October 2026
Methods, Developments & Frontiers · 11:55–12:10

MS389 - Machine Learning for Molecular Simulations

Organized with Weilong Chen and Julija Zavadlav
WCCM-ECCOMAS 2026 · Munich, Germany · 19–24 July 2026
Keywords: Machine Learning, Molecular Dynamics, Sampling, Simulations

This minisymposium brought together researchers working at the interface of machine learning and molecular simulations, with a focus on methodological advances and applications in mechanics, materials, and structural design.

Enhanced Sampling for Coarse-Grained Machine Learning Potentials

Weilong Chen¹, Franz Görlich¹, Paul Fuchs¹, Julija Zavadlav^∗1,2
1Multiscale Modeling of Fluid Materials, Department of Engineering Physics and Computation, TUM School of Engineering and Design, Technical University of Munich, Germany
²Atomistic Modeling Center (AMC), Munich Data Science Institute (MDSI), Technical University of Munich, Germany
^∗Corresponding Author

EurIPS 2025 · Copenhagen 1st SIMBIOCHEM Workshop Machine Learning for Simulations in Biology and Chemistry | PDF

Hybrid ML and Physics-Based Docking for Metalloproteins

Wojtek Treyde^a,b, Franz Görlich^a,c, and Fernanda Duarte^a
aChemistry Research Laboratory, and ^bIneos Oxford Institute for Antimicrobial Research, 12 Mansfield Road, Oxford, OX1 3TA, UK. ^cDepartment of Chemistry and Applied Life Sciences, ETH Zurich, Vladimir-Prelog-Weg 1-5/10, 8093 Zurich, CH.

WATOC 2025 - 13th Triennial Congress of the World Association of Theoretical and Computational Chemists | PDF