MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914475678892032 |
|---|---|
| author | Lahouari, Adam Ai, Shen Han, Jihye Hoffstadt, Jillian Hoellmer, Philipp Infante, Charlotte Jain, Pulkita Kadam, Sangram Martirossyan, Maya M. McCune, Amara Newton, Hypatia Paul, Shlok J. Pena, Willmor Raghoonanan, Jonathan Sahu, Sumon Tan, Oliver Vergara, Andrea Rogal, Jutta Tuckerman, Mark E. |
| author_facet | Lahouari, Adam Ai, Shen Han, Jihye Hoffstadt, Jillian Hoellmer, Philipp Infante, Charlotte Jain, Pulkita Kadam, Sangram Martirossyan, Maya M. McCune, Amara Newton, Hypatia Paul, Shlok J. Pena, Willmor Raghoonanan, Jonathan Sahu, Sumon Tan, Oliver Vergara, Andrea Rogal, Jutta Tuckerman, Mark E. |
| contents | We present an open Molecular Crystal (MC) database of Machine-Learned Interatomic Potentials (MLIP) called MolCryst-MLIPs. The first release comprises fine-tuned MACE models for nine molecular crystal systems -- Benzamide, Benzoic acid, Coumarin, Durene, Isonicotinamide, Niacinamide, Nicotinamide, Pyrazinamide, and Resorcinol -- developed using the Automated Machine Learning Pipeline (AMLP), which streamlines the entire MLIP development workflow, from reference data generation to model training and validation, into a reproducible and user-friendly pipeline. Models are fine-tuned from the MACE-MH-1 foundation model (omol head), yielding a mean energy MAE of 0.141 kJ/mol/atom and a mean force MAE of 0.648 kJ/mol/Angstrom across all systems. Dynamical stability and structural integrity, as assessed through energy conservation, P2 orientational order parameters, and radial distribution functions, are evaluated using molecular dynamics simulations. The released models and datasets constitute a growing open database of validated MLIPs, ready for production MD simulations of molecular crystal polymorphism under different thermodynamic conditions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13897 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals Lahouari, Adam Ai, Shen Han, Jihye Hoffstadt, Jillian Hoellmer, Philipp Infante, Charlotte Jain, Pulkita Kadam, Sangram Martirossyan, Maya M. McCune, Amara Newton, Hypatia Paul, Shlok J. Pena, Willmor Raghoonanan, Jonathan Sahu, Sumon Tan, Oliver Vergara, Andrea Rogal, Jutta Tuckerman, Mark E. Machine Learning Computational Physics We present an open Molecular Crystal (MC) database of Machine-Learned Interatomic Potentials (MLIP) called MolCryst-MLIPs. The first release comprises fine-tuned MACE models for nine molecular crystal systems -- Benzamide, Benzoic acid, Coumarin, Durene, Isonicotinamide, Niacinamide, Nicotinamide, Pyrazinamide, and Resorcinol -- developed using the Automated Machine Learning Pipeline (AMLP), which streamlines the entire MLIP development workflow, from reference data generation to model training and validation, into a reproducible and user-friendly pipeline. Models are fine-tuned from the MACE-MH-1 foundation model (omol head), yielding a mean energy MAE of 0.141 kJ/mol/atom and a mean force MAE of 0.648 kJ/mol/Angstrom across all systems. Dynamical stability and structural integrity, as assessed through energy conservation, P2 orientational order parameters, and radial distribution functions, are evaluated using molecular dynamics simulations. The released models and datasets constitute a growing open database of validated MLIPs, ready for production MD simulations of molecular crystal polymorphism under different thermodynamic conditions. |
| title | MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals |
| topic | Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2604.13897 |