subject Articles

GDML

Machine Learning of Accurate Energy-conserving Molecular Force Fields

Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, I., Schütt, K. T., Müller, K.-R., Science Advances, 3(5), 2017, e1603015.

Article Supplement BibTex


sGDML

Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields

Chmiela, S., Sauceda, H. E., Müller, K.-R., Tkatchenko, A., Nature Communications, 9(1), 2018, 3887.

Article Supplement BibTex


sGDML software paper

sGDML: Constructing Accurate and Data Efficient Molecular Force Fields Using Machine Learning

Chmiela, S., Sauceda, H. E., Poltavsky, I., Müller, K.-R., Tkatchenko, A., Computer Physics Communications, 240, 2019, 38-45.

Article Supplement BibTex


sGDML application paper

Molecular Force Fields with Gradient-Domain Machine Learning: Construction and Application to Dynamics of Small Molecules with Coupled Cluster Forces

Sauceda, H. E., Chmiela, S., Poltavsky, I., Müller, K.-R., Tkatchenko, A., The Journal of Chemical Physics, 150, 2019, 114102.

Article Supplement BibTex


sGDML applications book chapter

Construction of Machine Learned Force Fields with Quantum Chemical Accuracy: Applications and Chemical Insights

Sauceda, H. E., Chmiela, S., Poltavsky, I., Müller, K.-R., Tkatchenko, A., In: Machine Learning for Quantum Simulations of Molecules and Materials, in press.

Article BibTex


sGDML foundations book chapter

Accurate Molecular Dynamics Enabled by Efficient Physically-Constrained Machine Learning Approaches

Chmiela, S., Sauceda, H. E., Tkatchenko, A., Müller, K.-R., In: Machine Learning for Quantum Simulations of Molecules and Materials, in press.

Article BibTex


sGDML coarse graining

Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach

Wang, J., Chmiela, S., Müller, K.-R., Noè, F., Clementi, C., The Journal of Chemical Physics, 152, 2020, 194106.

Article Supplement BibTex


code Code (latest: v0.4.3)

Replicate our numerical results or reconstruct a force field from your own dataset with a Python implementation of sGDML.

GitHub Documentation


Test a pre-trained model on one of the published datasets

1. Download the aspirin model & dataset.

$ sgdml-get model aspirin
$ sgdml-get dataset aspirin_dft

2. Test the model on 10k data points.

$ sgdml test aspirin.npz aspirin_dft.npz 10000



view_agenda Datasets

All geometries in Å, energy labels in kcal mol-1 and force labels in kcal mol-1 Å-1.
Name Size Download
DFT [FHI-aims, light tier 1]
Benzene (Chmiela et al., 2018) 49 863
NumPy Ext. XYZExtended XYZ
a.k.a. MD17 dataset (Chmiela et al., 2017)
Benzene 627 983
NumPy Ext. XYZExtended XYZ
Uracil 133 770
NumPy Ext. XYZExtended XYZ
Naphthalene 326 250
NumPy Ext. XYZExtended XYZ
Aspirin 211 762
NumPy Ext. XYZExtended XYZ
Salicylic acid 320 231
NumPy Ext. XYZExtended XYZ
Malonaldehyde 993 237
NumPy Ext. XYZExtended XYZ
Ethanol 555 092
NumPy Ext. XYZExtended XYZ
Toluene 442 790
NumPy Ext. XYZExtended XYZ
NEW Paracetamol 106 490
NumPy Ext. XYZExtended XYZ
NEW Azobenzene 99 999
NumPy Ext. XYZExtended XYZ
CCSD [Psi4, cc-pVDZ]
NEW Aspirin 1 500
NumPy Ext. XYZExtended XYZ
CCSD(T) [Psi4, cc-pVDZ]
NEW Benzene 1 500
NumPy Ext. XYZExtended XYZ
NEW Malonaldehyde 1 500
NumPy Ext. XYZExtended XYZ
NEW Toluene 1 500
NumPy Ext. XYZExtended XYZ
[Psi4, cc-pVTZ]
NEW Ethanol 2 000
NumPy Ext. XYZExtended XYZ